форкнуто от main/is_dnn
Вы не можете выбрать более 25 тем
Темы должны начинаться с буквы или цифры, могут содержать дефисы(-) и должны содержать не более 35 символов.
1 строка
432 KiB
Plaintext
1 строка
432 KiB
Plaintext
{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[],"gpuType":"T4","mount_file_id":"1VmO4hQEAPfDizDdcqCwl1OYwcYnBO7VX","authorship_tag":"ABX9TyPx/jrfcAOBzaFB1nFJAJPh"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"},"accelerator":"GPU"},"cells":[{"cell_type":"code","source":["from google.colab import drive\n","drive.mount('/content/drive')"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"3d-xZ2lZy7Rb","executionInfo":{"status":"ok","timestamp":1758369423029,"user_tz":-180,"elapsed":12109,"user":{"displayName":"Александр Ли","userId":"11169366018002229978"}},"outputId":"21c74634-c993-4623-d694-4c286cba12d6"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"]}]},{"cell_type":"code","execution_count":null,"metadata":{"id":"sY7hrfuDep2o"},"outputs":[],"source":["import os\n","os.chdir('/content/drive/MyDrive/Colab Notebooks')"]},{"cell_type":"code","source":["from tensorflow import keras\n","import matplotlib.pyplot as plt\n","import numpy as np\n","import sklearn"],"metadata":{"id":"Tacr_fcxzVhL"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["from keras.datasets import mnist"],"metadata":{"id":"El-7TrohzlH4"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["(X_train,y_train),(X_test,y_test)=mnist.load_data()\n","from sklearn.model_selection import train_test_split\n","#объединяем в один набор\n","X=np.concatenate((X_train,X_test))\n","y=np.concatenate((y_train,y_test))\n","#разбиваем по вариантам\n","X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=10000,train_size=60000,random_state=11)\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"61fC3tqdzqfp","executionInfo":{"status":"ok","timestamp":1758369430032,"user_tz":-180,"elapsed":2485,"user":{"displayName":"Александр Ли","userId":"11169366018002229978"}},"outputId":"23c968f8-d50a-47fa-b5af-c171ff3d6885"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz\n","\u001b[1m11490434/11490434\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 0us/step\n"]}]},{"cell_type":"code","source":["#вывод размерностей\n","print('Shape of X train:',X_train.shape)\n","print('Shape of y train:',y_train.shape)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"CRqr_1wv0Hv0","executionInfo":{"status":"ok","timestamp":1758369430051,"user_tz":-180,"elapsed":17,"user":{"displayName":"Александр Ли","userId":"11169366018002229978"}},"outputId":"2b87a31d-db96-47db-e6cf-dd02d00faf64"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Shape of X train: (60000, 28, 28)\n","Shape of y train: (60000,)\n"]}]},{"cell_type":"code","source":["#вывод изображения\n","plt.imshow(X_train[1],cmap=plt.get_cmap('gray'))\n","plt.show()\n","print(y_train[1])\n","\n","plt.imshow(X_train[2],cmap=plt.get_cmap('gray'))\n","plt.show()\n","print(y_train[2])\n","\n","plt.imshow(X_train[3],cmap=plt.get_cmap('gray'))\n","plt.show()\n","print(y_train[3])\n","\n","plt.imshow(X_train[4],cmap=plt.get_cmap('gray'))\n","plt.show()\n","print(y_train[4])"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":1000},"id":"u5l41yUK0PkK","executionInfo":{"status":"ok","timestamp":1758369430460,"user_tz":-180,"elapsed":405,"user":{"displayName":"Александр Ли","userId":"11169366018002229978"}},"outputId":"bcad7ac2-5a2c-401a-8a7b-c5d09238748c"},"execution_count":null,"outputs":[{"output_type":"display_data","data":{"text/plain":["<Figure size 640x480 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["9\n"]},{"output_type":"display_data","data":{"text/plain":["<Figure size 640x480 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["6\n"]},{"output_type":"display_data","data":{"text/plain":["<Figure size 640x480 with 1 Axes>"],"image/png":"iVBORw0KGgoAAAANSUhEUgAAAaAAAAGdCAYAAABU0qcqAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQAAGqFJREFUeJzt3X1slXf9//HXgcGBbe3BUtrTM+4KbGAGdBGhdkBl0lCqmdzFbGwqLLgFLETA3Vh1wNTkbBh1mUHmHwZGHGxDBTKiXbayFm8KBAYheNNQrGsJtDhiz4EChbSf3x/8dr470MKuwzl9t+X5SD4JPef69Lx3ecLTq+dw6nPOOQEA0MX6WA8AALg9ESAAgAkCBAAwQYAAACYIEADABAECAJggQAAAEwQIAGDiDusBrtXe3q5Tp04pLS1NPp/PehwAgEfOOZ07d06hUEh9+nR+ndPtAnTq1CkNGzbMegwAwC1qaGjQ0KFDO72/2/0ILi0tzXoEAEAS3Ozv85QFaMOGDRo5cqQGDBig/Px8HThw4FPt48duANA73Ozv85QE6M0339Tq1au1du1affDBB8rLy1NxcbHOnDmTiocDAPRELgWmTJniSktLY1+3tbW5UCjkwuHwTfdGIhEnicVisVg9fEUikRv+fZ/0K6DLly/r0KFDKioqit3Wp08fFRUVqbq6+rrjW1tbFY1G4xYAoPdLeoA++ugjtbW1KTs7O+727OxsNTY2Xnd8OBxWIBCILd4BBwC3B/N3wZWVlSkSicRWQ0OD9UgAgC6Q9H8HlJmZqb59+6qpqSnu9qamJgWDweuO9/v98vv9yR4DANDNJf0KqH///po0aZIqKipit7W3t6uiokIFBQXJfjgAQA+Vkk9CWL16tRYtWqTPf/7zmjJlil5++WW1tLToiSeeSMXDAQB6oJQE6JFHHtF///tfrVmzRo2NjXrggQdUXl5+3RsTAAC3L59zzlkP8UnRaFSBQMB6DADALYpEIkpPT+/0fvN3wQEAbk8ECABgggABAEwQIACACQIEADBBgAAAJggQAMAEAQIAmCBAAAATBAgAYIIAAQBMECAAgAkCBAAwQYAAACYIEADABAECAJggQAAAEwQIAGCCAAEATBAgAIAJAgQAMEGAAAAmCBAAwAQBAgCYIEAAABMECABg4g7rAQD0Dnl5eZ73lJeXe95TW1vrec/06dM970HqcQUEADBBgAAAJggQAMAEAQIAmCBAAAATBAgAYIIAAQBMECAAgAkCBAAwQYAAACYIEADABAECAJjgw0gBJEU4HPa8Jysry/OeHTt2eN6D7okrIACACQIEADBBgAAAJggQAMAEAQIAmCBAAAATBAgAYIIAAQBMECAAgAkCBAAwQYAAACYIEADABB9GCuA6P/jBDzzveeihhzzv+fDDDz3vefHFFz3vQffEFRAAwAQBAgCYSHqA1q1bJ5/PF7fGjRuX7IcBAPRwKXkN6P7779d77733fw9yBy81AQDipaQMd9xxh4LBYCq+NQCgl0jJa0DHjx9XKBTSqFGj9Pjjj6u+vr7TY1tbWxWNRuMWAKD3S3qA8vPztXnzZpWXl2vjxo2qq6vT9OnTde7cuQ6PD4fDCgQCsTVs2LBkjwQA6IaSHqCSkhJ97Wtf08SJE1VcXKw//vGPam5u1ltvvdXh8WVlZYpEIrHV0NCQ7JEAAN1Qyt8dMGjQIN13332qra3t8H6/3y+/35/qMQAA3UzK/x3Q+fPndeLECeXk5KT6oQAAPUjSA/T000+rqqpK//nPf/S3v/1N8+bNU9++fbVw4cJkPxQAoAdL+o/gTp48qYULF+rs2bMaMmSIpk2bpn379mnIkCHJfigAQA+W9AC98cYbyf6WABIUCoUS2vfNb34zyZN0bN26dZ733OifdaBn4bPgAAAmCBAAwAQBAgCYIEAAABMECABgggABAEwQIACACQIEADBBgAAAJggQAMAEAQIAmCBAAAATKf+FdADsbN26NaF9Y8aM8bznZz/7mec9W7Zs8bwHvQdXQAAAEwQIAGCCAAEATBAgAIAJAgQAMEGAAAAmCBAAwAQBAgCYIEAAABMECABgggABAEwQIACACQIEADDBp2EDPcSyZcs87yksLEzosd555x3Pe9asWZPQY+H2xRUQAMAEAQIAmCBAAAATBAgAYIIAAQBMECAAgAkCBAAwQYAAACYIEADABAECAJggQAAAEwQIAGCCDyMFDEycONHzng0bNnje45zzvEeSNm7c6HnPpUuXEnos3L64AgIAmCBAAAATBAgAYIIAAQBMECAAgAkCBAAwQYAAACYIEADABAECAJggQAAAEwQIAGCCAAEATPBhpMAtSktL87znpZdeSsEk1zt27FhC+w4cOJDkSYDrcQUEADBBgAAAJjwHaO/evXr44YcVCoXk8/m0c+fOuPudc1qzZo1ycnI0cOBAFRUV6fjx48maFwDQS3gOUEtLi/Ly8jr95Vjr16/XK6+8oldffVX79+/XXXfdpeLiYn5ZFQAgjuc3IZSUlKikpKTD+5xzevnll/XDH/5Qc+bMkSRt2bJF2dnZ2rlzpx599NFbmxYA0Gsk9TWguro6NTY2qqioKHZbIBBQfn6+qqurO9zT2tqqaDQatwAAvV9SA9TY2ChJys7Ojrs9Ozs7dt+1wuGwAoFAbA0bNiyZIwEAuinzd8GVlZUpEonEVkNDg/VIAIAukNQABYNBSVJTU1Pc7U1NTbH7ruX3+5Wenh63AAC9X1IDlJubq2AwqIqKitht0WhU+/fvV0FBQTIfCgDQw3l+F9z58+dVW1sb+7qurk5HjhxRRkaGhg8frpUrV+onP/mJ7r33XuXm5ur5559XKBTS3Llzkzk3AKCH8xyggwcP6qGHHop9vXr1aknSokWLtHnzZj377LNqaWnRU089pebmZk2bNk3l5eUaMGBA8qYGAPR4Puecsx7ik6LRqAKBgPUYwKf29a9/3fOe1157zfMen8/nec8DDzzgeY8kHT16NKF9wCdFIpEbvq5v/i44AMDtiQABAEwQIACACQIEADBBgAAAJggQAMAEAQIAmCBAAAATBAgAYIIAAQBMECAAgAkCBAAwQYAAACY8/zoGoDcbMWKE5z1r165NwSTX+/3vf+95z/Hjx1MwCZAcXAEBAEwQIACACQIEADBBgAAAJggQAMAEAQIAmCBAAAATBAgAYIIAAQBMECAAgAkCBAAwQYAAACb4MFJ0e+np6Z73hMPhhB5r2bJlCe3rCnywKHobroAAACYIEADABAECAJggQAAAEwQIAGCCAAEATBAgAIAJAgQAMEGAAAAmCBAAwAQBAgCYIEAAABN8GCm6vStXrnjeEwqFEnos55znPW1tbZ73/O9///O853vf+57nPSNHjvS8R5Iee+yxhPYBXnAFBAAwQYAAACYIEADABAECAJggQAAAEwQIAGCCAAEATBAgAIAJAgQAMEGAAAAmCBAAwAQBAgCY4MNI0e3deeednvdkZmamYJKOVVRUeN5TUlLieU9dXZ3nPfPmzfO8R5KmTJniec+BAwcSeizcvrgCAgCYIEAAABOeA7R37149/PDDCoVC8vl82rlzZ9z9ixcvls/ni1uzZ89O1rwAgF7Cc4BaWlqUl5enDRs2dHrM7Nmzdfr06djatm3bLQ0JAOh9PL8JoaSk5KYvoPr9fgWDwYSHAgD0fil5DaiyslJZWVkaO3asli1bprNnz3Z6bGtrq6LRaNwCAPR+SQ/Q7NmztWXLFlVUVOill15SVVWVSkpK1NbW1uHx4XBYgUAgtoYNG5bskQAA3VDS/x3Qo48+GvvzhAkTNHHiRI0ePVqVlZWaOXPmdceXlZVp9erVsa+j0SgRAoDbQMrfhj1q1ChlZmaqtra2w/v9fr/S09PjFgCg90t5gE6ePKmzZ88qJycn1Q8FAOhBPP8I7vz583FXM3V1dTpy5IgyMjKUkZGhF154QQsWLFAwGNSJEyf07LPPasyYMSouLk7q4ACAns1zgA4ePKiHHnoo9vXHr98sWrRIGzdu1NGjR/Xaa6+publZoVBIs2bN0o9//GP5/f7kTQ0A6PE8B2jGjBlyznV6/zvvvHNLAwHX+sY3vuF5z4MPPpjQY/3973/3vGfhwoUJPZZXiXzo6RNPPJHQY/Hv+NAV+Cw4AIAJAgQAMEGAAAAmCBAAwAQBAgCYIEAAABMECABgggABAEwQIACACQIEADBBgAAAJggQAMAEAQIAmEj6r+QGkm3+/Pld9lh/+tOfPO9pbm5O/iDAbYArIACACQIEADBBgAAAJggQAMAEAQIAmCBAAAATBAgAYIIAAQBMECAAgAkCBAAwQYAAACYIEADABB9Gii41bdo0z3umT5/ueU9tba3nPZK0YcOGhPZ1hSVLlnje45xLwSRAcnAFBAAwQYAAACYIEADABAECAJggQAAAEwQIAGCCAAEATBAgAIAJAgQAMEGAAAAmCBAAwAQBAgCY4MNI0aWee+45z3sS+UDN3/3ud573SFJ9fb3nPYMHD/a8JxwOe96TyHl45513PO+RpD179iS0D/CCKyAAgAkCBAAwQYAAACYIEADABAECAJggQAAAEwQIAGCCAAEATBAgAIAJAgQAMEGAAAAmCBAAwAQfRoouNWjQoC55nEQ+VFSSVqxY4XnPV7/6Vc97vvSlL3nec/bsWc97vvWtb3neI0nnz59PaB/gBVdAAAATBAgAYMJTgMLhsCZPnqy0tDRlZWVp7ty5qqmpiTvm0qVLKi0t1eDBg3X33XdrwYIFampqSurQAICez1OAqqqqVFpaqn379undd9/VlStXNGvWLLW0tMSOWbVqld5++21t375dVVVVOnXqlObPn5/0wQEAPZunNyGUl5fHfb1582ZlZWXp0KFDKiwsVCQS0W9+8xtt3bo19iLrpk2b9NnPflb79u3TF77wheRNDgDo0W7pNaBIJCJJysjIkCQdOnRIV65cUVFRUeyYcePGafjw4aquru7we7S2tioajcYtAEDvl3CA2tvbtXLlSk2dOlXjx4+XJDU2Nqp///7XvdU2OztbjY2NHX6fcDisQCAQW8OGDUt0JABAD5JwgEpLS3Xs2DG98cYbtzRAWVmZIpFIbDU0NNzS9wMA9AwJ/UPU5cuXa/fu3dq7d6+GDh0auz0YDOry5ctqbm6OuwpqampSMBjs8Hv5/X75/f5ExgAA9GCeroCcc1q+fLl27NihPXv2KDc3N+7+SZMmqV+/fqqoqIjdVlNTo/r6ehUUFCRnYgBAr+DpCqi0tFRbt27Vrl27lJaWFntdJxAIaODAgQoEAlqyZIlWr16tjIwMpaena8WKFSooKOAdcACAOJ4CtHHjRknSjBkz4m7ftGmTFi9eLEn6xS9+oT59+mjBggVqbW1VcXGxfvWrXyVlWABA7+FzzjnrIT4pGo0qEAhYj4EU+fOf/+x5z9SpUz3vuXjxouc9kjRgwADPey5fvux5z7///W/Pex588EHPez7+pxKAhUgkovT09E7v57PgAAAmCBAAwAQBAgCYIEAAABMECABgggABAEwQIACACQIEADBBgAAAJggQAMAEAQIAmCBAAAATBAgAYCKh34gKJOrll1/2vCeRT8NO5FOtJenDDz/0vGfdunWe92zZssXzHqC34QoIAGCCAAEATBAgAIAJAgQAMEGAAAAmCBAAwAQBAgCYIEAAABMECABgggABAEwQIACACQIEADDhc8456yE+KRqNKhAIWI8BALhFkUhE6enpnd7PFRAAwAQBAgCYIEAAABMECABgggABAEwQIACACQIEADBBgAAAJggQAMAEAQIAmCBAAAATBAgAYIIAAQBMECAAgAkCBAAwQYAAACYIEADABAECAJggQAAAEwQIAGCCAAEATBAgAIAJAgQAMEGAAAAmCBAAwAQBAgCYIEAAABMECABgwlOAwuGwJk+erLS0NGVlZWnu3LmqqamJO2bGjBny+Xxxa+nSpUkdGgDQ83kKUFVVlUpLS7Vv3z69++67unLlimbNmqWWlpa445588kmdPn06ttavX5/UoQEAPd8dXg4uLy+P+3rz5s3KysrSoUOHVFhYGLv9zjvvVDAYTM6EAIBe6ZZeA4pEIpKkjIyMuNtff/11ZWZmavz48SorK9OFCxc6/R6tra2KRqNxCwBwG3AJamtrc1/5ylfc1KlT427/9a9/7crLy93Ro0fdb3/7W3fPPfe4efPmdfp91q5d6ySxWCwWq5etSCRyw44kHKClS5e6ESNGuIaGhhseV1FR4SS52traDu+/dOmSi0QisdXQ0GB+0lgsFot16+tmAfL0GtDHli9frt27d2vv3r0aOnToDY/Nz8+XJNXW1mr06NHX3e/3++X3+xMZAwDQg3kKkHNOK1as0I4dO1RZWanc3Nyb7jly5IgkKScnJ6EBAQC9k6cAlZaWauvWrdq1a5fS0tLU2NgoSQoEAho4cKBOnDihrVu36stf/rIGDx6so0ePatWqVSosLNTEiRNT8h8AAOihvLzuo05+zrdp0ybnnHP19fWusLDQZWRkOL/f78aMGeOeeeaZm/4c8JMikYj5zy1ZLBaLdevrZn/3+/5/WLqNaDSqQCBgPQYA4BZFIhGlp6d3ej+fBQcAMEGAAAAmCBAAwAQBAgCYIEAAABMECABgggABAEwQIACACQIEADBBgAAAJggQAMAEAQIAmCBAAAATBAgAYIIAAQBMECAAgAkCBAAwQYAAACYIEADABAECAJggQAAAEwQIAGCCAAEATBAgAIAJAgQAMNHtAuScsx4BAJAEN/v7vNsF6Ny5c9YjAACS4GZ/n/tcN7vkaG9v16lTp5SWliafzxd3XzQa1bBhw9TQ0KD09HSjCe1xHq7iPFzFebiK83BVdzgPzjmdO3dOoVBIffp0fp1zRxfO9Kn06dNHQ4cOveEx6enpt/UT7GOch6s4D1dxHq7iPFxlfR4CgcBNj+l2P4IDANweCBAAwESPCpDf79fatWvl9/utRzHFebiK83AV5+EqzsNVPek8dLs3IQAAbg896goIANB7ECAAgAkCBAAwQYAAACZ6TIA2bNigkSNHasCAAcrPz9eBAwesR+py69atk8/ni1vjxo2zHivl9u7dq4cfflihUEg+n087d+6Mu985pzVr1ignJ0cDBw5UUVGRjh8/bjNsCt3sPCxevPi658fs2bNthk2RcDisyZMnKy0tTVlZWZo7d65qamrijrl06ZJKS0s1ePBg3X333VqwYIGampqMJk6NT3MeZsyYcd3zYenSpUYTd6xHBOjNN9/U6tWrtXbtWn3wwQfKy8tTcXGxzpw5Yz1al7v//vt1+vTp2PrLX/5iPVLKtbS0KC8vTxs2bOjw/vXr1+uVV17Rq6++qv379+uuu+5ScXGxLl261MWTptbNzoMkzZ49O+75sW3bti6cMPWqqqpUWlqqffv26d1339WVK1c0a9YstbS0xI5ZtWqV3n77bW3fvl1VVVU6deqU5s+fbzh18n2a8yBJTz75ZNzzYf369UYTd8L1AFOmTHGlpaWxr9va2lwoFHLhcNhwqq63du1al5eXZz2GKUlux44dsa/b29tdMBh0P/3pT2O3NTc3O7/f77Zt22YwYde49jw459yiRYvcnDlzTOaxcubMGSfJVVVVOeeu/m/fr18/t3379tgx//znP50kV11dbTVmyl17Hpxz7otf/KL7zne+YzfUp9Dtr4AuX76sQ4cOqaioKHZbnz59VFRUpOrqasPJbBw/flyhUEijRo3S448/rvr6euuRTNXV1amxsTHu+REIBJSfn39bPj8qKyuVlZWlsWPHatmyZTp79qz1SCkViUQkSRkZGZKkQ4cO6cqVK3HPh3Hjxmn48OG9+vlw7Xn42Ouvv67MzEyNHz9eZWVlunDhgsV4nep2H0Z6rY8++khtbW3Kzs6Ouz07O1v/+te/jKaykZ+fr82bN2vs2LE6ffq0XnjhBU2fPl3Hjh1TWlqa9XgmGhsbJanD58fH990uZs+erfnz5ys3N1cnTpzQ97//fZWUlKi6ulp9+/a1Hi/p2tvbtXLlSk2dOlXjx4+XdPX50L9/fw0aNCju2N78fOjoPEjSY489phEjRigUCuno0aN67rnnVFNToz/84Q+G08br9gHC/ykpKYn9eeLEicrPz9eIESP01ltvacmSJYaToTt49NFHY3+eMGGCJk6cqNGjR6uyslIzZ840nCw1SktLdezYsdviddAb6ew8PPXUU7E/T5gwQTk5OZo5c6ZOnDih0aNHd/WYHer2P4LLzMxU3759r3sXS1NTk4LBoNFU3cOgQYN03333qba21noUMx8/B3h+XG/UqFHKzMzslc+P5cuXa/fu3Xr//ffjfn1LMBjU5cuX1dzcHHd8b30+dHYeOpKfny9J3er50O0D1L9/f02aNEkVFRWx29rb21VRUaGCggLDyeydP39eJ06cUE5OjvUoZnJzcxUMBuOeH9FoVPv377/tnx8nT57U2bNne9Xzwzmn5cuXa8eOHdqzZ49yc3Pj7p80aZL69esX93yoqalRfX19r3o+3Ow8dOTIkSOS1L2eD9bvgvg03njjDef3+93mzZvdP/7xD/fUU0+5QYMGucbGRuvRutR3v/tdV1lZ6erq6txf//pXV1RU5DIzM92ZM2esR0upc+fOucOHD7vDhw87Se7nP/+5O3z4sPvwww+dc869+OKLbtCgQW7Xrl3u6NGjbs6cOS43N9ddvHjRePLkutF5OHfunHv66adddXW1q6urc++995773Oc+5+6991536dIl69GTZtmyZS4QCLjKykp3+vTp2Lpw4ULsmKVLl7rhw4e7PXv2uIMHD7qCggJXUFBgOHXy3ew81NbWuh/96Efu4MGDrq6uzu3atcuNGjXKFRYWGk8er0cEyDnnfvnLX7rhw4e7/v37uylTprh9+/ZZj9TlHnnkEZeTk+P69+/v7rnnHvfII4+42tpa67FS7v3333eSrluLFi1yzl19K/bzzz/vsrOznd/vdzNnznQ1NTW2Q6fAjc7DhQsX3KxZs9yQIUNcv3793IgRI9yTTz7Z6/5PWkf//ZLcpk2bYsdcvHjRffvb33af+cxn3J133unmzZvnTp8+bTd0CtzsPNTX17vCwkKXkZHh/H6/GzNmjHvmmWdcJBKxHfwa/DoGAICJbv8aEACgdyJAAAATBAgAYIIAAQBMECAAgAkCBAAwQYAAACYIEADABAECAJggQAAAEwQIAGCCAAEATPw/vyZspkdIVMgAAAAASUVORK5CYII=\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["6\n"]},{"output_type":"display_data","data":{"text/plain":["<Figure size 640x480 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["8\n"]}]},{"cell_type":"code","source":["#развернем каждое изображение 8*228 в вектор 784\n","num_pixels=X_train.shape[1]*X_train.shape[2]\n","X_train=X_train.reshape(X_train.shape[0],num_pixels) / 255\n","X_test=X_test.reshape(X_test.shape[0],num_pixels) / 255\n","print('Shape of transformed X train:',X_train.shape)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"saLoJeVw0gM9","executionInfo":{"status":"ok","timestamp":1758369430616,"user_tz":-180,"elapsed":139,"user":{"displayName":"Александр Ли","userId":"11169366018002229978"}},"outputId":"3bc965d3-16ea-4e16-c6e1-c8cf708d0f39"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Shape of transformed X train: (60000, 784)\n"]}]},{"cell_type":"code","source":["#переведем метки в one-hot\n","import keras.utils\n","y_train=keras.utils.to_categorical(y_train)\n","y_test=keras.utils.to_categorical(y_test)\n","print('Shape of transformed y train:',y_train.shape)\n","num_classes=y_train.shape[1]"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"Rqe4rjxW07Pc","executionInfo":{"status":"ok","timestamp":1758369430625,"user_tz":-180,"elapsed":16,"user":{"displayName":"Александр Ли","userId":"11169366018002229978"}},"outputId":"b7accfe8-5ce2-4b6d-af17-d7588091d328"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Shape of transformed y train: (60000, 10)\n"]}]},{"cell_type":"code","source":["from keras.models import Sequential\n","from keras.layers import Dense"],"metadata":{"id":"eoxg_hKM2hrk"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["model_1 = Sequential()\n","model_1.add(Dense(units=num_classes, input_dim=num_pixels, activation='softmax'))\n","model_1.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"XUtTRNgq3f_W","executionInfo":{"status":"ok","timestamp":1758369432898,"user_tz":-180,"elapsed":2266,"user":{"displayName":"Александр Ли","userId":"11169366018002229978"}},"outputId":"5f2b3354-8113-4aa0-e6e6-f190e07b4fa4"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.12/dist-packages/keras/src/layers/core/dense.py:93: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n"," super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"]}]},{"cell_type":"code","source":["# вывод информации об архитектуре модели\n","print(model_1.summary())"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":178},"id":"P1mTGIIw9icA","executionInfo":{"status":"ok","timestamp":1758369444913,"user_tz":-180,"elapsed":102,"user":{"displayName":"Александр Ли","userId":"11169366018002229978"}},"outputId":"144d0f8b-4023-4f10-e220-da130de7d757"},"execution_count":null,"outputs":[{"output_type":"display_data","data":{"text/plain":["\u001b[1mModel: \"sequential\"\u001b[0m\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential\"</span>\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ dense (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m) │ \u001b[38;5;34m7,850\u001b[0m │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃<span style=\"font-weight: bold\"> Layer (type) </span>┃<span style=\"font-weight: bold\"> Output Shape </span>┃<span style=\"font-weight: bold\"> Param # </span>┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ dense (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">10</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">7,850</span> │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Total params: \u001b[0m\u001b[38;5;34m7,850\u001b[0m (30.66 KB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">7,850</span> (30.66 KB)\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m7,850\u001b[0m (30.66 KB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">7,850</span> (30.66 KB)\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n","</pre>\n"]},"metadata":{}},{"output_type":"stream","name":"stdout","text":["None\n"]}]},{"cell_type":"code","source":["# Обучаем модель\n","H = model_1.fit(X_train, y_train, validation_split=0.1, epochs=50)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"7R-bwn519mT-","executionInfo":{"status":"ok","timestamp":1758369764107,"user_tz":-180,"elapsed":309485,"user":{"displayName":"Александр Ли","userId":"11169366018002229978"}},"outputId":"9fe5c897-8c13-43cc-dcba-8239490348b5"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Epoch 1/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 3ms/step - accuracy: 0.6924 - loss: 1.1951 - val_accuracy: 0.8775 - val_loss: 0.5033\n","Epoch 2/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.8750 - loss: 0.4945 - val_accuracy: 0.8910 - val_loss: 0.4130\n","Epoch 3/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.8868 - loss: 0.4267 - val_accuracy: 0.8982 - val_loss: 0.3762\n","Epoch 4/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 2ms/step - accuracy: 0.8957 - loss: 0.3878 - val_accuracy: 0.9040 - val_loss: 0.3548\n","Epoch 5/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.8996 - loss: 0.3671 - val_accuracy: 0.9060 - val_loss: 0.3400\n","Epoch 6/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 3ms/step - accuracy: 0.9047 - loss: 0.3520 - val_accuracy: 0.9078 - val_loss: 0.3298\n","Epoch 7/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9052 - loss: 0.3455 - val_accuracy: 0.9093 - val_loss: 0.3222\n","Epoch 8/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9060 - loss: 0.3435 - val_accuracy: 0.9110 - val_loss: 0.3159\n","Epoch 9/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 3ms/step - accuracy: 0.9079 - loss: 0.3307 - val_accuracy: 0.9132 - val_loss: 0.3113\n","Epoch 10/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.9084 - loss: 0.3254 - val_accuracy: 0.9143 - val_loss: 0.3073\n","Epoch 11/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9109 - loss: 0.3197 - val_accuracy: 0.9138 - val_loss: 0.3026\n","Epoch 12/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m13s\u001b[0m 5ms/step - accuracy: 0.9109 - loss: 0.3193 - val_accuracy: 0.9147 - val_loss: 0.3002\n","Epoch 13/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9129 - loss: 0.3147 - val_accuracy: 0.9168 - val_loss: 0.2967\n","Epoch 14/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9137 - loss: 0.3119 - val_accuracy: 0.9178 - val_loss: 0.2941\n","Epoch 15/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9158 - loss: 0.3038 - val_accuracy: 0.9170 - val_loss: 0.2916\n","Epoch 16/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9138 - loss: 0.3103 - val_accuracy: 0.9180 - val_loss: 0.2898\n","Epoch 17/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 4ms/step - accuracy: 0.9169 - loss: 0.3053 - val_accuracy: 0.9188 - val_loss: 0.2885\n","Epoch 18/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m8s\u001b[0m 3ms/step - accuracy: 0.9165 - loss: 0.3043 - val_accuracy: 0.9193 - val_loss: 0.2867\n","Epoch 19/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9185 - loss: 0.2985 - val_accuracy: 0.9192 - val_loss: 0.2851\n","Epoch 20/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9177 - loss: 0.2991 - val_accuracy: 0.9195 - val_loss: 0.2843\n","Epoch 21/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9188 - loss: 0.2936 - val_accuracy: 0.9197 - val_loss: 0.2827\n","Epoch 22/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9171 - loss: 0.2970 - val_accuracy: 0.9200 - val_loss: 0.2812\n","Epoch 23/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 3ms/step - accuracy: 0.9173 - loss: 0.2986 - val_accuracy: 0.9200 - val_loss: 0.2805\n","Epoch 24/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9186 - loss: 0.2948 - val_accuracy: 0.9200 - val_loss: 0.2796\n","Epoch 25/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9186 - loss: 0.2960 - val_accuracy: 0.9208 - val_loss: 0.2783\n","Epoch 26/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9172 - loss: 0.2986 - val_accuracy: 0.9203 - val_loss: 0.2781\n","Epoch 27/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.9205 - loss: 0.2849 - val_accuracy: 0.9218 - val_loss: 0.2770\n","Epoch 28/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9206 - loss: 0.2893 - val_accuracy: 0.9210 - val_loss: 0.2763\n","Epoch 29/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 3ms/step - accuracy: 0.9203 - loss: 0.2814 - val_accuracy: 0.9227 - val_loss: 0.2748\n","Epoch 30/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9209 - loss: 0.2856 - val_accuracy: 0.9223 - val_loss: 0.2751\n","Epoch 31/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9227 - loss: 0.2793 - val_accuracy: 0.9222 - val_loss: 0.2736\n","Epoch 32/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9209 - loss: 0.2865 - val_accuracy: 0.9225 - val_loss: 0.2728\n","Epoch 33/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9205 - loss: 0.2833 - val_accuracy: 0.9223 - val_loss: 0.2726\n","Epoch 34/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9210 - loss: 0.2844 - val_accuracy: 0.9228 - val_loss: 0.2726\n","Epoch 35/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 4ms/step - accuracy: 0.9218 - loss: 0.2759 - val_accuracy: 0.9225 - val_loss: 0.2715\n","Epoch 36/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.9212 - loss: 0.2881 - val_accuracy: 0.9225 - val_loss: 0.2709\n","Epoch 37/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9219 - loss: 0.2815 - val_accuracy: 0.9227 - val_loss: 0.2706\n","Epoch 38/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9214 - loss: 0.2791 - val_accuracy: 0.9233 - val_loss: 0.2704\n","Epoch 39/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9222 - loss: 0.2802 - val_accuracy: 0.9228 - val_loss: 0.2698\n","Epoch 40/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9218 - loss: 0.2844 - val_accuracy: 0.9237 - val_loss: 0.2694\n","Epoch 41/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 2ms/step - accuracy: 0.9255 - loss: 0.2677 - val_accuracy: 0.9237 - val_loss: 0.2692\n","Epoch 42/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9218 - loss: 0.2784 - val_accuracy: 0.9240 - val_loss: 0.2682\n","Epoch 43/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 2ms/step - accuracy: 0.9238 - loss: 0.2749 - val_accuracy: 0.9235 - val_loss: 0.2682\n","Epoch 44/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9237 - loss: 0.2748 - val_accuracy: 0.9240 - val_loss: 0.2678\n","Epoch 45/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9228 - loss: 0.2793 - val_accuracy: 0.9230 - val_loss: 0.2678\n","Epoch 46/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.9227 - loss: 0.2794 - val_accuracy: 0.9248 - val_loss: 0.2672\n","Epoch 47/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9236 - loss: 0.2743 - val_accuracy: 0.9240 - val_loss: 0.2664\n","Epoch 48/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9245 - loss: 0.2699 - val_accuracy: 0.9243 - val_loss: 0.2669\n","Epoch 49/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9251 - loss: 0.2690 - val_accuracy: 0.9243 - val_loss: 0.2665\n","Epoch 50/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.9247 - loss: 0.2718 - val_accuracy: 0.9243 - val_loss: 0.2662\n"]}]},{"cell_type":"code","source":["# вывод графика ошибки по эпохам\n","plt.plot(H.history['loss'])\n","plt.plot(H.history['val_loss'])\n","plt.grid()\n","plt.xlabel('Epochs')\n","plt.ylabel('loss')\n","plt.legend(['train_loss', 'val_loss'])\n","plt.title('Loss by epochs')\n","plt.show()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":472},"id":"GRTe79ph9py0","executionInfo":{"status":"ok","timestamp":1758369764261,"user_tz":-180,"elapsed":146,"user":{"displayName":"Александр Ли","userId":"11169366018002229978"}},"outputId":"fdace35a-b407-42af-f1d8-cedfe2c44604"},"execution_count":null,"outputs":[{"output_type":"display_data","data":{"text/plain":["<Figure size 640x480 with 1 Axes>"],"image/png":"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\n"},"metadata":{}}]},{"cell_type":"code","source":["# Оценка качества работы модели на тестовых данных\n","scores = model_1.evaluate(X_test, y_test)\n","print('Loss on test data:', scores[0])\n","print('Accuracy on test data:', scores[1])"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"UIYWFwAV_bdy","executionInfo":{"status":"ok","timestamp":1758369792230,"user_tz":-180,"elapsed":2750,"user":{"displayName":"Александр Ли","userId":"11169366018002229978"}},"outputId":"bb1cb8b6-bd0a-43f0-af8d-028ac6f1e989"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 8ms/step - accuracy: 0.9219 - loss: 0.2787\n","Loss on test data: 0.2803967595100403\n","Accuracy on test data: 0.9203000068664551\n"]}]},{"cell_type":"code","source":["model_2 = Sequential()\n","model_2.add(Dense(units=100, input_dim=num_pixels, activation='sigmoid'))\n","model_2.add(Dense(units=num_classes, activation='softmax'))\n","model_2.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])\n","\n","print(model_2.summary())\n","\n","H_2 = model_2.fit(X_train, y_train, validation_split=0.1, epochs=50)\n","\n","# вывод графика ошибки по эпохам\n","plt.plot(H_2.history['loss'])\n","plt.plot(H_2.history['val_loss'])\n","plt.grid()\n","plt.xlabel('Epochs')\n","plt.ylabel('loss')\n","plt.legend(['train_loss', 'val_loss'])\n","plt.title('Loss by epochs')\n","plt.show()\n","\n","# Оценка качества работы модели на тестовых данных\n","scores = model_2.evaluate(X_test, y_test)\n","print('Loss on test data:', scores[0])\n","print('Accuracy on test data:', scores[1])"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":1000},"id":"3s9ndeb6AbQa","executionInfo":{"status":"ok","timestamp":1758370826938,"user_tz":-180,"elapsed":320780,"user":{"displayName":"Александр Ли","userId":"11169366018002229978"}},"outputId":"212790d0-0f50-4724-cc0a-3c26d7e8e64a"},"execution_count":null,"outputs":[{"output_type":"display_data","data":{"text/plain":["\u001b[1mModel: \"sequential_2\"\u001b[0m\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential_2\"</span>\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ dense_3 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m100\u001b[0m) │ \u001b[38;5;34m78,500\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_4 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m) │ \u001b[38;5;34m1,010\u001b[0m │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃<span style=\"font-weight: bold\"> Layer (type) </span>┃<span style=\"font-weight: bold\"> Output Shape </span>┃<span style=\"font-weight: bold\"> Param # </span>┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ dense_3 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">100</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">78,500</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_4 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">10</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">1,010</span> │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Total params: \u001b[0m\u001b[38;5;34m79,510\u001b[0m (310.59 KB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">79,510</span> (310.59 KB)\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m79,510\u001b[0m (310.59 KB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">79,510</span> (310.59 KB)\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n","</pre>\n"]},"metadata":{}},{"output_type":"stream","name":"stdout","text":["None\n","Epoch 1/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m13s\u001b[0m 7ms/step - accuracy: 0.5381 - loss: 1.9126 - val_accuracy: 0.8087 - val_loss: 0.9749\n","Epoch 2/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m14s\u001b[0m 3ms/step - accuracy: 0.8265 - loss: 0.8623 - val_accuracy: 0.8630 - val_loss: 0.6228\n","Epoch 3/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.8605 - loss: 0.6000 - val_accuracy: 0.8820 - val_loss: 0.4961\n","Epoch 4/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 4ms/step - accuracy: 0.8774 - loss: 0.4944 - val_accuracy: 0.8940 - val_loss: 0.4310\n","Epoch 5/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.8871 - loss: 0.4343 - val_accuracy: 0.9012 - val_loss: 0.3918\n","Epoch 6/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.8920 - loss: 0.4062 - val_accuracy: 0.9023 - val_loss: 0.3659\n","Epoch 7/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.8970 - loss: 0.3845 - val_accuracy: 0.9057 - val_loss: 0.3470\n","Epoch 8/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9016 - loss: 0.3584 - val_accuracy: 0.9073 - val_loss: 0.3329\n","Epoch 9/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9040 - loss: 0.3462 - val_accuracy: 0.9113 - val_loss: 0.3207\n","Epoch 10/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9071 - loss: 0.3384 - val_accuracy: 0.9120 - val_loss: 0.3122\n","Epoch 11/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9081 - loss: 0.3263 - val_accuracy: 0.9143 - val_loss: 0.3034\n","Epoch 12/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9103 - loss: 0.3180 - val_accuracy: 0.9155 - val_loss: 0.2959\n","Epoch 13/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m11s\u001b[0m 3ms/step - accuracy: 0.9100 - loss: 0.3185 - val_accuracy: 0.9188 - val_loss: 0.2894\n","Epoch 14/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.9145 - loss: 0.3035 - val_accuracy: 0.9197 - val_loss: 0.2842\n","Epoch 15/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9186 - loss: 0.2940 - val_accuracy: 0.9213 - val_loss: 0.2794\n","Epoch 16/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9177 - loss: 0.2976 - val_accuracy: 0.9212 - val_loss: 0.2741\n","Epoch 17/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9190 - loss: 0.2885 - val_accuracy: 0.9232 - val_loss: 0.2695\n","Epoch 18/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9204 - loss: 0.2838 - val_accuracy: 0.9238 - val_loss: 0.2659\n","Epoch 19/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9179 - loss: 0.2884 - val_accuracy: 0.9238 - val_loss: 0.2620\n","Epoch 20/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9222 - loss: 0.2768 - val_accuracy: 0.9265 - val_loss: 0.2580\n","Epoch 21/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9210 - loss: 0.2751 - val_accuracy: 0.9265 - val_loss: 0.2550\n","Epoch 22/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9227 - loss: 0.2669 - val_accuracy: 0.9275 - val_loss: 0.2506\n","Epoch 23/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 4ms/step - accuracy: 0.9257 - loss: 0.2629 - val_accuracy: 0.9275 - val_loss: 0.2484\n","Epoch 24/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9273 - loss: 0.2615 - val_accuracy: 0.9283 - val_loss: 0.2448\n","Epoch 25/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9275 - loss: 0.2552 - val_accuracy: 0.9288 - val_loss: 0.2416\n","Epoch 26/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.9277 - loss: 0.2585 - val_accuracy: 0.9305 - val_loss: 0.2382\n","Epoch 27/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9291 - loss: 0.2463 - val_accuracy: 0.9332 - val_loss: 0.2366\n","Epoch 28/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.9320 - loss: 0.2426 - val_accuracy: 0.9340 - val_loss: 0.2325\n","Epoch 29/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9321 - loss: 0.2448 - val_accuracy: 0.9325 - val_loss: 0.2301\n","Epoch 30/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 3ms/step - accuracy: 0.9319 - loss: 0.2410 - val_accuracy: 0.9325 - val_loss: 0.2275\n","Epoch 31/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9297 - loss: 0.2455 - val_accuracy: 0.9357 - val_loss: 0.2242\n","Epoch 32/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9343 - loss: 0.2323 - val_accuracy: 0.9358 - val_loss: 0.2227\n","Epoch 33/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9331 - loss: 0.2341 - val_accuracy: 0.9362 - val_loss: 0.2204\n","Epoch 34/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9348 - loss: 0.2314 - val_accuracy: 0.9375 - val_loss: 0.2178\n","Epoch 35/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9353 - loss: 0.2272 - val_accuracy: 0.9377 - val_loss: 0.2153\n","Epoch 36/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 4ms/step - accuracy: 0.9350 - loss: 0.2273 - val_accuracy: 0.9377 - val_loss: 0.2134\n","Epoch 37/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m8s\u001b[0m 3ms/step - accuracy: 0.9396 - loss: 0.2177 - val_accuracy: 0.9395 - val_loss: 0.2105\n","Epoch 38/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9363 - loss: 0.2202 - val_accuracy: 0.9390 - val_loss: 0.2088\n","Epoch 39/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9361 - loss: 0.2188 - val_accuracy: 0.9412 - val_loss: 0.2056\n","Epoch 40/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9393 - loss: 0.2134 - val_accuracy: 0.9418 - val_loss: 0.2033\n","Epoch 41/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9392 - loss: 0.2131 - val_accuracy: 0.9408 - val_loss: 0.2020\n","Epoch 42/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9396 - loss: 0.2138 - val_accuracy: 0.9422 - val_loss: 0.1998\n","Epoch 43/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9432 - loss: 0.2040 - val_accuracy: 0.9422 - val_loss: 0.1980\n","Epoch 44/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.9412 - loss: 0.2090 - val_accuracy: 0.9425 - val_loss: 0.1961\n","Epoch 45/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9420 - loss: 0.2017 - val_accuracy: 0.9442 - val_loss: 0.1947\n","Epoch 46/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.9431 - loss: 0.2001 - val_accuracy: 0.9438 - val_loss: 0.1918\n","Epoch 47/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9428 - loss: 0.2012 - val_accuracy: 0.9442 - val_loss: 0.1906\n","Epoch 48/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 3ms/step - accuracy: 0.9458 - loss: 0.1891 - val_accuracy: 0.9442 - val_loss: 0.1889\n","Epoch 49/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9452 - loss: 0.1932 - val_accuracy: 0.9453 - val_loss: 0.1870\n","Epoch 50/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9461 - loss: 0.1935 - val_accuracy: 0.9468 - val_loss: 0.1850\n"]},{"output_type":"display_data","data":{"text/plain":["<Figure size 640x480 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - accuracy: 0.9416 - loss: 0.1984\n","Loss on test data: 0.19959478080272675\n","Accuracy on test data: 0.9416999816894531\n"]}]},{"cell_type":"code","source":["model_3 = Sequential()\n","model_3.add(Dense(units=300, input_dim=num_pixels, activation='sigmoid'))\n","model_3.add(Dense(units=num_classes, activation='softmax'))\n","model_3.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])\n","\n","print(model_3.summary())\n","\n","H_3 = model_3.fit(X_train, y_train, validation_split=0.1, epochs=50)\n","\n","# вывод графика ошибки по эпохам\n","plt.plot(H_3.history['loss'])\n","plt.plot(H_3.history['val_loss'])\n","plt.grid()\n","plt.xlabel('Epochs')\n","plt.ylabel('loss')\n","plt.legend(['train_loss', 'val_loss'])\n","plt.title('Loss by epochs')\n","plt.show()\n","\n","# Оценка качества работы модели на тестовых данных\n","scores = model_3.evaluate(X_test, y_test)\n","print('Loss on test data:', scores[0])\n","print('Accuracy on test data:', scores[1])"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":1000},"id":"mS7oysm8DKOp","executionInfo":{"status":"ok","timestamp":1758372239145,"user_tz":-180,"elapsed":300145,"user":{"displayName":"Александр Ли","userId":"11169366018002229978"}},"outputId":"22e1f660-5b4f-4e74-8602-f0f24e723244"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.12/dist-packages/keras/src/layers/core/dense.py:93: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n"," super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"]},{"output_type":"display_data","data":{"text/plain":["\u001b[1mModel: \"sequential_3\"\u001b[0m\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential_3\"</span>\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ dense_5 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m300\u001b[0m) │ \u001b[38;5;34m235,500\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_6 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m) │ \u001b[38;5;34m3,010\u001b[0m │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃<span style=\"font-weight: bold\"> Layer (type) </span>┃<span style=\"font-weight: bold\"> Output Shape </span>┃<span style=\"font-weight: bold\"> Param # </span>┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ dense_5 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">300</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">235,500</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_6 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">10</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">3,010</span> │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Total params: \u001b[0m\u001b[38;5;34m238,510\u001b[0m (931.68 KB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">238,510</span> (931.68 KB)\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m238,510\u001b[0m (931.68 KB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">238,510</span> (931.68 KB)\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n","</pre>\n"]},"metadata":{}},{"output_type":"stream","name":"stdout","text":["None\n","Epoch 1/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m8s\u001b[0m 4ms/step - accuracy: 0.5441 - loss: 1.7974 - val_accuracy: 0.8262 - val_loss: 0.8458\n","Epoch 2/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 3ms/step - accuracy: 0.8401 - loss: 0.7551 - val_accuracy: 0.8723 - val_loss: 0.5551\n","Epoch 3/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.8712 - loss: 0.5370 - val_accuracy: 0.8888 - val_loss: 0.4523\n","Epoch 4/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.8813 - loss: 0.4575 - val_accuracy: 0.8987 - val_loss: 0.4022\n","Epoch 5/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.8888 - loss: 0.4144 - val_accuracy: 0.9017 - val_loss: 0.3716\n","Epoch 6/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.8959 - loss: 0.3869 - val_accuracy: 0.9050 - val_loss: 0.3520\n","Epoch 7/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.8968 - loss: 0.3717 - val_accuracy: 0.9070 - val_loss: 0.3369\n","Epoch 8/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.8992 - loss: 0.3572 - val_accuracy: 0.9108 - val_loss: 0.3244\n","Epoch 9/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.9017 - loss: 0.3492 - val_accuracy: 0.9103 - val_loss: 0.3153\n","Epoch 10/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9023 - loss: 0.3384 - val_accuracy: 0.9118 - val_loss: 0.3084\n","Epoch 11/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9092 - loss: 0.3224 - val_accuracy: 0.9127 - val_loss: 0.3043\n","Epoch 12/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9099 - loss: 0.3210 - val_accuracy: 0.9142 - val_loss: 0.2977\n","Epoch 13/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9136 - loss: 0.3090 - val_accuracy: 0.9150 - val_loss: 0.2929\n","Epoch 14/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9118 - loss: 0.3096 - val_accuracy: 0.9170 - val_loss: 0.2885\n","Epoch 15/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9111 - loss: 0.3080 - val_accuracy: 0.9185 - val_loss: 0.2836\n","Epoch 16/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9145 - loss: 0.3025 - val_accuracy: 0.9195 - val_loss: 0.2807\n","Epoch 17/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9153 - loss: 0.2973 - val_accuracy: 0.9210 - val_loss: 0.2770\n","Epoch 18/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9155 - loss: 0.2925 - val_accuracy: 0.9205 - val_loss: 0.2738\n","Epoch 19/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9173 - loss: 0.2955 - val_accuracy: 0.9227 - val_loss: 0.2733\n","Epoch 20/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9170 - loss: 0.2884 - val_accuracy: 0.9233 - val_loss: 0.2697\n","Epoch 21/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9185 - loss: 0.2857 - val_accuracy: 0.9237 - val_loss: 0.2670\n","Epoch 22/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9184 - loss: 0.2877 - val_accuracy: 0.9243 - val_loss: 0.2640\n","Epoch 23/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9207 - loss: 0.2761 - val_accuracy: 0.9243 - val_loss: 0.2624\n","Epoch 24/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.9218 - loss: 0.2744 - val_accuracy: 0.9260 - val_loss: 0.2589\n","Epoch 25/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9208 - loss: 0.2764 - val_accuracy: 0.9272 - val_loss: 0.2581\n","Epoch 26/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 3ms/step - accuracy: 0.9230 - loss: 0.2705 - val_accuracy: 0.9277 - val_loss: 0.2553\n","Epoch 27/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9243 - loss: 0.2641 - val_accuracy: 0.9288 - val_loss: 0.2537\n","Epoch 28/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9245 - loss: 0.2704 - val_accuracy: 0.9278 - val_loss: 0.2506\n","Epoch 29/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9224 - loss: 0.2662 - val_accuracy: 0.9290 - val_loss: 0.2493\n","Epoch 30/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.9232 - loss: 0.2669 - val_accuracy: 0.9288 - val_loss: 0.2472\n","Epoch 31/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9270 - loss: 0.2545 - val_accuracy: 0.9305 - val_loss: 0.2462\n","Epoch 32/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9253 - loss: 0.2616 - val_accuracy: 0.9317 - val_loss: 0.2437\n","Epoch 33/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9276 - loss: 0.2536 - val_accuracy: 0.9305 - val_loss: 0.2415\n","Epoch 34/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9277 - loss: 0.2523 - val_accuracy: 0.9297 - val_loss: 0.2389\n","Epoch 35/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m11s\u001b[0m 3ms/step - accuracy: 0.9277 - loss: 0.2565 - val_accuracy: 0.9312 - val_loss: 0.2369\n","Epoch 36/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9306 - loss: 0.2473 - val_accuracy: 0.9322 - val_loss: 0.2360\n","Epoch 37/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9294 - loss: 0.2479 - val_accuracy: 0.9323 - val_loss: 0.2339\n","Epoch 38/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9326 - loss: 0.2420 - val_accuracy: 0.9322 - val_loss: 0.2326\n","Epoch 39/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9284 - loss: 0.2475 - val_accuracy: 0.9335 - val_loss: 0.2297\n","Epoch 40/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9320 - loss: 0.2388 - val_accuracy: 0.9343 - val_loss: 0.2273\n","Epoch 41/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9324 - loss: 0.2407 - val_accuracy: 0.9340 - val_loss: 0.2252\n","Epoch 42/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 3ms/step - accuracy: 0.9337 - loss: 0.2351 - val_accuracy: 0.9355 - val_loss: 0.2236\n","Epoch 43/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 3ms/step - accuracy: 0.9341 - loss: 0.2343 - val_accuracy: 0.9352 - val_loss: 0.2228\n","Epoch 44/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9342 - loss: 0.2344 - val_accuracy: 0.9343 - val_loss: 0.2199\n","Epoch 45/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9363 - loss: 0.2275 - val_accuracy: 0.9355 - val_loss: 0.2174\n","Epoch 46/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9369 - loss: 0.2206 - val_accuracy: 0.9360 - val_loss: 0.2168\n","Epoch 47/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9360 - loss: 0.2243 - val_accuracy: 0.9363 - val_loss: 0.2151\n","Epoch 48/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9392 - loss: 0.2185 - val_accuracy: 0.9375 - val_loss: 0.2129\n","Epoch 49/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9378 - loss: 0.2183 - val_accuracy: 0.9377 - val_loss: 0.2115\n","Epoch 50/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9378 - loss: 0.2168 - val_accuracy: 0.9393 - val_loss: 0.2094\n"]},{"output_type":"display_data","data":{"text/plain":["<Figure size 640x480 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - accuracy: 0.9337 - loss: 0.2223\n","Loss on test data: 0.224356010556221\n","Accuracy on test data: 0.9345999956130981\n"]}]},{"cell_type":"code","source":["model_4 = Sequential()\n","model_4.add(Dense(units=500, input_dim=num_pixels, activation='sigmoid'))\n","model_4.add(Dense(units=num_classes, activation='softmax'))\n","model_4.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])\n","\n","print(model_4.summary())\n","\n","H_4 = model_4.fit(X_train, y_train, validation_split=0.1, epochs=50)\n","\n","# вывод графика ошибки по эпохам\n","plt.plot(H_4.history['loss'])\n","plt.plot(H_4.history['val_loss'])\n","plt.grid()\n","plt.xlabel('Epochs')\n","plt.ylabel('loss')\n","plt.legend(['train_loss', 'val_loss'])\n","plt.title('Loss by epochs')\n","plt.show()\n","\n","# Оценка качества работы модели на тестовых данных\n","scores = model_4.evaluate(X_test, y_test)\n","print('Loss on test data:', scores[0])\n","print('Accuracy on test data:', scores[1])"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":1000},"id":"7A7oVRCpKUJS","executionInfo":{"status":"ok","timestamp":1758372762730,"user_tz":-180,"elapsed":328859,"user":{"displayName":"Александр Ли","userId":"11169366018002229978"}},"outputId":"03ed3fa9-7c9e-4e2d-bc76-bf0f384ee551"},"execution_count":null,"outputs":[{"output_type":"display_data","data":{"text/plain":["\u001b[1mModel: \"sequential_5\"\u001b[0m\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential_5\"</span>\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ dense_9 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m500\u001b[0m) │ \u001b[38;5;34m392,500\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_10 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m) │ \u001b[38;5;34m5,010\u001b[0m │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃<span style=\"font-weight: bold\"> Layer (type) </span>┃<span style=\"font-weight: bold\"> Output Shape </span>┃<span style=\"font-weight: bold\"> Param # </span>┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ dense_9 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">500</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">392,500</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_10 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">10</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">5,010</span> │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Total params: \u001b[0m\u001b[38;5;34m397,510\u001b[0m (1.52 MB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">397,510</span> (1.52 MB)\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m397,510\u001b[0m (1.52 MB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">397,510</span> (1.52 MB)\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n","</pre>\n"]},"metadata":{}},{"output_type":"stream","name":"stdout","text":["None\n","Epoch 1/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m8s\u001b[0m 4ms/step - accuracy: 0.5638 - loss: 1.7612 - val_accuracy: 0.8435 - val_loss: 0.8013\n","Epoch 2/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.8456 - loss: 0.7243 - val_accuracy: 0.8770 - val_loss: 0.5333\n","Epoch 3/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 2ms/step - accuracy: 0.8735 - loss: 0.5205 - val_accuracy: 0.8895 - val_loss: 0.4400\n","Epoch 4/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.8837 - loss: 0.4442 - val_accuracy: 0.8958 - val_loss: 0.3946\n","Epoch 5/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m13s\u001b[0m 5ms/step - accuracy: 0.8904 - loss: 0.4080 - val_accuracy: 0.8998 - val_loss: 0.3667\n","Epoch 6/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 2ms/step - accuracy: 0.8913 - loss: 0.3851 - val_accuracy: 0.9023 - val_loss: 0.3510\n","Epoch 7/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.8972 - loss: 0.3645 - val_accuracy: 0.9082 - val_loss: 0.3334\n","Epoch 8/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.8988 - loss: 0.3582 - val_accuracy: 0.9082 - val_loss: 0.3255\n","Epoch 9/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9034 - loss: 0.3431 - val_accuracy: 0.9123 - val_loss: 0.3146\n","Epoch 10/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9051 - loss: 0.3330 - val_accuracy: 0.9115 - val_loss: 0.3099\n","Epoch 11/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9077 - loss: 0.3276 - val_accuracy: 0.9100 - val_loss: 0.3068\n","Epoch 12/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9069 - loss: 0.3227 - val_accuracy: 0.9155 - val_loss: 0.2990\n","Epoch 13/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9092 - loss: 0.3177 - val_accuracy: 0.9165 - val_loss: 0.2951\n","Epoch 14/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 2ms/step - accuracy: 0.9102 - loss: 0.3145 - val_accuracy: 0.9147 - val_loss: 0.2922\n","Epoch 15/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m8s\u001b[0m 4ms/step - accuracy: 0.9139 - loss: 0.3057 - val_accuracy: 0.9172 - val_loss: 0.2880\n","Epoch 16/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 2ms/step - accuracy: 0.9119 - loss: 0.3094 - val_accuracy: 0.9175 - val_loss: 0.2859\n","Epoch 17/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9138 - loss: 0.3044 - val_accuracy: 0.9207 - val_loss: 0.2830\n","Epoch 18/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9180 - loss: 0.2912 - val_accuracy: 0.9220 - val_loss: 0.2792\n","Epoch 19/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 3ms/step - accuracy: 0.9146 - loss: 0.3003 - val_accuracy: 0.9203 - val_loss: 0.2788\n","Epoch 20/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9140 - loss: 0.3027 - val_accuracy: 0.9203 - val_loss: 0.2776\n","Epoch 21/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 3ms/step - accuracy: 0.9163 - loss: 0.2868 - val_accuracy: 0.9217 - val_loss: 0.2732\n","Epoch 22/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.9191 - loss: 0.2871 - val_accuracy: 0.9217 - val_loss: 0.2716\n","Epoch 23/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9186 - loss: 0.2900 - val_accuracy: 0.9225 - val_loss: 0.2689\n","Epoch 24/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.9186 - loss: 0.2836 - val_accuracy: 0.9252 - val_loss: 0.2683\n","Epoch 25/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9192 - loss: 0.2884 - val_accuracy: 0.9250 - val_loss: 0.2665\n","Epoch 26/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9199 - loss: 0.2827 - val_accuracy: 0.9240 - val_loss: 0.2644\n","Epoch 27/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9215 - loss: 0.2765 - val_accuracy: 0.9250 - val_loss: 0.2639\n","Epoch 28/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9208 - loss: 0.2798 - val_accuracy: 0.9267 - val_loss: 0.2623\n","Epoch 29/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9218 - loss: 0.2738 - val_accuracy: 0.9260 - val_loss: 0.2595\n","Epoch 30/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 3ms/step - accuracy: 0.9228 - loss: 0.2685 - val_accuracy: 0.9272 - val_loss: 0.2578\n","Epoch 31/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.9223 - loss: 0.2759 - val_accuracy: 0.9285 - val_loss: 0.2569\n","Epoch 32/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9226 - loss: 0.2701 - val_accuracy: 0.9277 - val_loss: 0.2559\n","Epoch 33/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 3ms/step - accuracy: 0.9250 - loss: 0.2640 - val_accuracy: 0.9273 - val_loss: 0.2534\n","Epoch 34/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9232 - loss: 0.2671 - val_accuracy: 0.9285 - val_loss: 0.2522\n","Epoch 35/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9257 - loss: 0.2574 - val_accuracy: 0.9292 - val_loss: 0.2506\n","Epoch 36/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9254 - loss: 0.2621 - val_accuracy: 0.9295 - val_loss: 0.2489\n","Epoch 37/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9270 - loss: 0.2576 - val_accuracy: 0.9290 - val_loss: 0.2487\n","Epoch 38/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9287 - loss: 0.2542 - val_accuracy: 0.9308 - val_loss: 0.2459\n","Epoch 39/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9284 - loss: 0.2571 - val_accuracy: 0.9288 - val_loss: 0.2471\n","Epoch 40/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9274 - loss: 0.2570 - val_accuracy: 0.9295 - val_loss: 0.2456\n","Epoch 41/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9279 - loss: 0.2534 - val_accuracy: 0.9310 - val_loss: 0.2431\n","Epoch 42/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9296 - loss: 0.2461 - val_accuracy: 0.9307 - val_loss: 0.2406\n","Epoch 43/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 3ms/step - accuracy: 0.9291 - loss: 0.2524 - val_accuracy: 0.9317 - val_loss: 0.2388\n","Epoch 44/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.9284 - loss: 0.2565 - val_accuracy: 0.9320 - val_loss: 0.2368\n","Epoch 45/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9302 - loss: 0.2444 - val_accuracy: 0.9328 - val_loss: 0.2351\n","Epoch 46/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.9305 - loss: 0.2418 - val_accuracy: 0.9318 - val_loss: 0.2368\n","Epoch 47/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9322 - loss: 0.2376 - val_accuracy: 0.9335 - val_loss: 0.2311\n","Epoch 48/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 3ms/step - accuracy: 0.9348 - loss: 0.2359 - val_accuracy: 0.9333 - val_loss: 0.2311\n","Epoch 49/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 3ms/step - accuracy: 0.9333 - loss: 0.2354 - val_accuracy: 0.9330 - val_loss: 0.2295\n","Epoch 50/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9338 - loss: 0.2346 - val_accuracy: 0.9352 - val_loss: 0.2277\n"]},{"output_type":"display_data","data":{"text/plain":["<Figure size 640x480 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - accuracy: 0.9269 - loss: 0.2416\n","Loss on test data: 0.2432917207479477\n","Accuracy on test data: 0.9279000163078308\n"]}]},{"cell_type":"code","source":["model_5 = Sequential()\n","model_5.add(Dense(units=100, input_dim=num_pixels, activation='sigmoid'))\n","model_5.add(Dense(units=50, activation='sigmoid'))\n","model_5.add(Dense(units=num_classes, activation='softmax'))\n","model_5.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])\n","\n","print(model_5.summary())\n","\n","H_5 = model_5.fit(X_train, y_train, validation_split=0.1, epochs=50)\n","\n","# вывод графика ошибки по эпохам\n","plt.plot(H_5.history['loss'])\n","plt.plot(H_5.history['val_loss'])\n","plt.grid()\n","plt.xlabel('Epochs')\n","plt.ylabel('loss')\n","plt.legend(['train_loss', 'val_loss'])\n","plt.title('Loss by epochs')\n","plt.show()\n","\n","# Оценка качества работы модели на тестовых данных\n","scores = model_5.evaluate(X_test, y_test)\n","print('Loss on test data:', scores[0])\n","print('Accuracy on test data:', scores[1])"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":1000},"id":"M9Lb-RmTKd8k","executionInfo":{"status":"ok","timestamp":1758373891077,"user_tz":-180,"elapsed":318176,"user":{"displayName":"Александр Ли","userId":"11169366018002229978"}},"outputId":"d7006a75-561a-4d88-f3b9-68e65e051362"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.12/dist-packages/keras/src/layers/core/dense.py:93: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n"," super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"]},{"output_type":"display_data","data":{"text/plain":["\u001b[1mModel: \"sequential_6\"\u001b[0m\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential_6\"</span>\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ dense_11 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m100\u001b[0m) │ \u001b[38;5;34m78,500\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_12 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m50\u001b[0m) │ \u001b[38;5;34m5,050\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_13 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m) │ \u001b[38;5;34m510\u001b[0m │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃<span style=\"font-weight: bold\"> Layer (type) </span>┃<span style=\"font-weight: bold\"> Output Shape </span>┃<span style=\"font-weight: bold\"> Param # </span>┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ dense_11 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">100</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">78,500</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_12 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">50</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">5,050</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_13 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">10</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">510</span> │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Total params: \u001b[0m\u001b[38;5;34m84,060\u001b[0m (328.36 KB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">84,060</span> (328.36 KB)\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m84,060\u001b[0m (328.36 KB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">84,060</span> (328.36 KB)\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n","</pre>\n"]},"metadata":{}},{"output_type":"stream","name":"stdout","text":["None\n","Epoch 1/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 3ms/step - accuracy: 0.1903 - loss: 2.2760 - val_accuracy: 0.4533 - val_loss: 2.0793\n","Epoch 2/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.5093 - loss: 1.9647 - val_accuracy: 0.6495 - val_loss: 1.5316\n","Epoch 3/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 4ms/step - accuracy: 0.6871 - loss: 1.3907 - val_accuracy: 0.7460 - val_loss: 1.0405\n","Epoch 4/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.7685 - loss: 0.9697 - val_accuracy: 0.8002 - val_loss: 0.7932\n","Epoch 5/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 4ms/step - accuracy: 0.8100 - loss: 0.7666 - val_accuracy: 0.8290 - val_loss: 0.6531\n","Epoch 6/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.8349 - loss: 0.6397 - val_accuracy: 0.8560 - val_loss: 0.5589\n","Epoch 7/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.8532 - loss: 0.5624 - val_accuracy: 0.8730 - val_loss: 0.4947\n","Epoch 8/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.8683 - loss: 0.4999 - val_accuracy: 0.8847 - val_loss: 0.4487\n","Epoch 9/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m11s\u001b[0m 3ms/step - accuracy: 0.8776 - loss: 0.4580 - val_accuracy: 0.8923 - val_loss: 0.4163\n","Epoch 10/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 3ms/step - accuracy: 0.8852 - loss: 0.4255 - val_accuracy: 0.8990 - val_loss: 0.3898\n","Epoch 11/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.8927 - loss: 0.4007 - val_accuracy: 0.9025 - val_loss: 0.3695\n","Epoch 12/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.8933 - loss: 0.3865 - val_accuracy: 0.9053 - val_loss: 0.3538\n","Epoch 13/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.8969 - loss: 0.3695 - val_accuracy: 0.9067 - val_loss: 0.3412\n","Epoch 14/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.8991 - loss: 0.3611 - val_accuracy: 0.9098 - val_loss: 0.3303\n","Epoch 15/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9015 - loss: 0.3470 - val_accuracy: 0.9090 - val_loss: 0.3202\n","Epoch 16/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9079 - loss: 0.3335 - val_accuracy: 0.9117 - val_loss: 0.3128\n","Epoch 17/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9048 - loss: 0.3358 - val_accuracy: 0.9118 - val_loss: 0.3046\n","Epoch 18/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9103 - loss: 0.3211 - val_accuracy: 0.9162 - val_loss: 0.2981\n","Epoch 19/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9098 - loss: 0.3192 - val_accuracy: 0.9158 - val_loss: 0.2933\n","Epoch 20/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.9117 - loss: 0.3106 - val_accuracy: 0.9183 - val_loss: 0.2861\n","Epoch 21/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9129 - loss: 0.3031 - val_accuracy: 0.9188 - val_loss: 0.2809\n","Epoch 22/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 3ms/step - accuracy: 0.9166 - loss: 0.2911 - val_accuracy: 0.9212 - val_loss: 0.2749\n","Epoch 23/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.9171 - loss: 0.2940 - val_accuracy: 0.9223 - val_loss: 0.2699\n","Epoch 24/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9202 - loss: 0.2830 - val_accuracy: 0.9225 - val_loss: 0.2658\n","Epoch 25/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.9199 - loss: 0.2805 - val_accuracy: 0.9252 - val_loss: 0.2611\n","Epoch 26/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9209 - loss: 0.2779 - val_accuracy: 0.9245 - val_loss: 0.2575\n","Epoch 27/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 3ms/step - accuracy: 0.9217 - loss: 0.2747 - val_accuracy: 0.9273 - val_loss: 0.2528\n","Epoch 28/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.9237 - loss: 0.2692 - val_accuracy: 0.9287 - val_loss: 0.2491\n","Epoch 29/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9264 - loss: 0.2625 - val_accuracy: 0.9295 - val_loss: 0.2447\n","Epoch 30/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9270 - loss: 0.2562 - val_accuracy: 0.9312 - val_loss: 0.2420\n","Epoch 31/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9261 - loss: 0.2583 - val_accuracy: 0.9318 - val_loss: 0.2368\n","Epoch 32/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9270 - loss: 0.2534 - val_accuracy: 0.9327 - val_loss: 0.2340\n","Epoch 33/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9295 - loss: 0.2413 - val_accuracy: 0.9342 - val_loss: 0.2292\n","Epoch 34/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 4ms/step - accuracy: 0.9279 - loss: 0.2497 - val_accuracy: 0.9327 - val_loss: 0.2273\n","Epoch 35/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m8s\u001b[0m 3ms/step - accuracy: 0.9307 - loss: 0.2415 - val_accuracy: 0.9347 - val_loss: 0.2229\n","Epoch 36/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9322 - loss: 0.2367 - val_accuracy: 0.9353 - val_loss: 0.2195\n","Epoch 37/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.9302 - loss: 0.2354 - val_accuracy: 0.9383 - val_loss: 0.2169\n","Epoch 38/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9357 - loss: 0.2267 - val_accuracy: 0.9377 - val_loss: 0.2134\n","Epoch 39/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.9356 - loss: 0.2249 - val_accuracy: 0.9378 - val_loss: 0.2106\n","Epoch 40/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9340 - loss: 0.2255 - val_accuracy: 0.9395 - val_loss: 0.2074\n","Epoch 41/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9389 - loss: 0.2156 - val_accuracy: 0.9395 - val_loss: 0.2042\n","Epoch 42/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9383 - loss: 0.2133 - val_accuracy: 0.9402 - val_loss: 0.2023\n","Epoch 43/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9389 - loss: 0.2140 - val_accuracy: 0.9407 - val_loss: 0.1988\n","Epoch 44/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9391 - loss: 0.2111 - val_accuracy: 0.9413 - val_loss: 0.1962\n","Epoch 45/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9398 - loss: 0.2090 - val_accuracy: 0.9425 - val_loss: 0.1939\n","Epoch 46/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9417 - loss: 0.2048 - val_accuracy: 0.9447 - val_loss: 0.1911\n","Epoch 47/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9436 - loss: 0.1994 - val_accuracy: 0.9457 - val_loss: 0.1888\n","Epoch 48/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9453 - loss: 0.1913 - val_accuracy: 0.9468 - val_loss: 0.1858\n","Epoch 49/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.9447 - loss: 0.1910 - val_accuracy: 0.9467 - val_loss: 0.1841\n","Epoch 50/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9462 - loss: 0.1894 - val_accuracy: 0.9475 - val_loss: 0.1818\n"]},{"output_type":"display_data","data":{"text/plain":["<Figure size 640x480 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - accuracy: 0.9384 - loss: 0.1992\n","Loss on test data: 0.19695913791656494\n","Accuracy on test data: 0.9402999877929688\n"]}]},{"cell_type":"code","source":["model_5 = Sequential()\n","model_5.add(Dense(units=100, input_dim=num_pixels, activation='sigmoid'))\n","model_5.add(Dense(units=100, activation='sigmoid'))\n","model_5.add(Dense(units=num_classes, activation='softmax'))\n","model_5.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])\n","\n","print(model_5.summary())\n","\n","H_5 = model_5.fit(X_train, y_train, validation_split=0.1, epochs=50)\n","\n","# вывод графика ошибки по эпохам\n","plt.plot(H_5.history['loss'])\n","plt.plot(H_5.history['val_loss'])\n","plt.grid()\n","plt.xlabel('Epochs')\n","plt.ylabel('loss')\n","plt.legend(['train_loss', 'val_loss'])\n","plt.title('Loss by epochs')\n","plt.show()\n","\n","# Оценка качества работы модели на тестовых данных\n","scores = model_5.evaluate(X_test, y_test)\n","print('Loss on test data:', scores[0])\n","print('Accuracy on test data:', scores[1])"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":1000},"id":"F64kmzaCO5so","executionInfo":{"status":"ok","timestamp":1758374222132,"user_tz":-180,"elapsed":331036,"user":{"displayName":"Александр Ли","userId":"11169366018002229978"}},"outputId":"7fede57c-1092-4c2c-9633-0a6bc315ed43"},"execution_count":null,"outputs":[{"output_type":"display_data","data":{"text/plain":["\u001b[1mModel: \"sequential_7\"\u001b[0m\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential_7\"</span>\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ dense_14 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m100\u001b[0m) │ \u001b[38;5;34m78,500\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_15 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m100\u001b[0m) │ \u001b[38;5;34m10,100\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_16 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m) │ \u001b[38;5;34m1,010\u001b[0m │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃<span style=\"font-weight: bold\"> Layer (type) </span>┃<span style=\"font-weight: bold\"> Output Shape </span>┃<span style=\"font-weight: bold\"> Param # </span>┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ dense_14 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">100</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">78,500</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_15 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">100</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">10,100</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_16 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">10</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">1,010</span> │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Total params: \u001b[0m\u001b[38;5;34m89,610\u001b[0m (350.04 KB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">89,610</span> (350.04 KB)\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m89,610\u001b[0m (350.04 KB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">89,610</span> (350.04 KB)\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n","</pre>\n"]},"metadata":{}},{"output_type":"stream","name":"stdout","text":["None\n","Epoch 1/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 4ms/step - accuracy: 0.1980 - loss: 2.2730 - val_accuracy: 0.5065 - val_loss: 2.1019\n","Epoch 2/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.5667 - loss: 1.9901 - val_accuracy: 0.6553 - val_loss: 1.5055\n","Epoch 3/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.6975 - loss: 1.3598 - val_accuracy: 0.7752 - val_loss: 0.9847\n","Epoch 4/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.7810 - loss: 0.9302 - val_accuracy: 0.8133 - val_loss: 0.7424\n","Epoch 5/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.8202 - loss: 0.7221 - val_accuracy: 0.8462 - val_loss: 0.6048\n","Epoch 6/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.8476 - loss: 0.5961 - val_accuracy: 0.8688 - val_loss: 0.5186\n","Epoch 7/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.8590 - loss: 0.5267 - val_accuracy: 0.8785 - val_loss: 0.4602\n","Epoch 8/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.8734 - loss: 0.4758 - val_accuracy: 0.8910 - val_loss: 0.4196\n","Epoch 9/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.8820 - loss: 0.4355 - val_accuracy: 0.8972 - val_loss: 0.3911\n","Epoch 10/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.8886 - loss: 0.4085 - val_accuracy: 0.9013 - val_loss: 0.3677\n","Epoch 11/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.8960 - loss: 0.3831 - val_accuracy: 0.9060 - val_loss: 0.3515\n","Epoch 12/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.8985 - loss: 0.3709 - val_accuracy: 0.9082 - val_loss: 0.3354\n","Epoch 13/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9021 - loss: 0.3499 - val_accuracy: 0.9092 - val_loss: 0.3241\n","Epoch 14/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9032 - loss: 0.3397 - val_accuracy: 0.9130 - val_loss: 0.3132\n","Epoch 15/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.9063 - loss: 0.3321 - val_accuracy: 0.9128 - val_loss: 0.3050\n","Epoch 16/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9076 - loss: 0.3246 - val_accuracy: 0.9143 - val_loss: 0.2976\n","Epoch 17/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9107 - loss: 0.3125 - val_accuracy: 0.9165 - val_loss: 0.2897\n","Epoch 18/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9125 - loss: 0.3082 - val_accuracy: 0.9160 - val_loss: 0.2837\n","Epoch 19/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9134 - loss: 0.3047 - val_accuracy: 0.9210 - val_loss: 0.2780\n","Epoch 20/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 3ms/step - accuracy: 0.9168 - loss: 0.2947 - val_accuracy: 0.9215 - val_loss: 0.2716\n","Epoch 21/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 3ms/step - accuracy: 0.9186 - loss: 0.2862 - val_accuracy: 0.9223 - val_loss: 0.2664\n","Epoch 22/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9194 - loss: 0.2859 - val_accuracy: 0.9235 - val_loss: 0.2618\n","Epoch 23/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.9205 - loss: 0.2760 - val_accuracy: 0.9252 - val_loss: 0.2569\n","Epoch 24/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9235 - loss: 0.2707 - val_accuracy: 0.9267 - val_loss: 0.2526\n","Epoch 25/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9248 - loss: 0.2616 - val_accuracy: 0.9272 - val_loss: 0.2486\n","Epoch 26/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9258 - loss: 0.2614 - val_accuracy: 0.9270 - val_loss: 0.2455\n","Epoch 27/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.9252 - loss: 0.2608 - val_accuracy: 0.9287 - val_loss: 0.2402\n","Epoch 28/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 4ms/step - accuracy: 0.9268 - loss: 0.2586 - val_accuracy: 0.9302 - val_loss: 0.2362\n","Epoch 29/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.9283 - loss: 0.2524 - val_accuracy: 0.9305 - val_loss: 0.2324\n","Epoch 30/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9305 - loss: 0.2441 - val_accuracy: 0.9313 - val_loss: 0.2293\n","Epoch 31/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 3ms/step - accuracy: 0.9313 - loss: 0.2405 - val_accuracy: 0.9308 - val_loss: 0.2261\n","Epoch 32/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.9316 - loss: 0.2404 - val_accuracy: 0.9338 - val_loss: 0.2224\n","Epoch 33/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9336 - loss: 0.2361 - val_accuracy: 0.9340 - val_loss: 0.2193\n","Epoch 34/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 3ms/step - accuracy: 0.9334 - loss: 0.2343 - val_accuracy: 0.9358 - val_loss: 0.2154\n","Epoch 35/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9354 - loss: 0.2263 - val_accuracy: 0.9353 - val_loss: 0.2133\n","Epoch 36/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9346 - loss: 0.2289 - val_accuracy: 0.9360 - val_loss: 0.2105\n","Epoch 37/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9369 - loss: 0.2206 - val_accuracy: 0.9385 - val_loss: 0.2064\n","Epoch 38/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9380 - loss: 0.2196 - val_accuracy: 0.9385 - val_loss: 0.2056\n","Epoch 39/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m11s\u001b[0m 4ms/step - accuracy: 0.9380 - loss: 0.2216 - val_accuracy: 0.9387 - val_loss: 0.2015\n","Epoch 40/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9406 - loss: 0.2072 - val_accuracy: 0.9412 - val_loss: 0.1985\n","Epoch 41/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9383 - loss: 0.2157 - val_accuracy: 0.9420 - val_loss: 0.1955\n","Epoch 42/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 3ms/step - accuracy: 0.9396 - loss: 0.2089 - val_accuracy: 0.9430 - val_loss: 0.1937\n","Epoch 43/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 3ms/step - accuracy: 0.9420 - loss: 0.2012 - val_accuracy: 0.9440 - val_loss: 0.1906\n","Epoch 44/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9438 - loss: 0.1977 - val_accuracy: 0.9450 - val_loss: 0.1895\n","Epoch 45/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9444 - loss: 0.1967 - val_accuracy: 0.9458 - val_loss: 0.1862\n","Epoch 46/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 3ms/step - accuracy: 0.9431 - loss: 0.1984 - val_accuracy: 0.9460 - val_loss: 0.1844\n","Epoch 47/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 4ms/step - accuracy: 0.9437 - loss: 0.1984 - val_accuracy: 0.9453 - val_loss: 0.1823\n","Epoch 48/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9453 - loss: 0.1914 - val_accuracy: 0.9467 - val_loss: 0.1797\n","Epoch 49/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9452 - loss: 0.1882 - val_accuracy: 0.9482 - val_loss: 0.1783\n","Epoch 50/50\n","\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9479 - loss: 0.1817 - val_accuracy: 0.9477 - val_loss: 0.1757\n"]},{"output_type":"display_data","data":{"text/plain":["<Figure size 640x480 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - accuracy: 0.9395 - loss: 0.1940\n","Loss on test data: 0.19388720393180847\n","Accuracy on test data: 0.9420999884605408\n"]}]},{"cell_type":"code","source":["model_5.save('best_model.keras')"],"metadata":{"id":"B0GTrE3OSZyv"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["# вывод тестового изображения и результата распознавания 1\n","n = 123\n","result = model_5.predict(X_test[n:n+1])\n","print('NN output:', result)\n","plt.imshow(X_test[n].reshape(28,28), cmap=plt.get_cmap('gray'))\n","plt.show()\n","print('Real mark: ', str(np.argmax(y_test[n])))\n","print('NN answer: ', str(np.argmax(result)))\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":517},"id":"LcMyQ0EoSz-e","executionInfo":{"status":"ok","timestamp":1758375571476,"user_tz":-180,"elapsed":492,"user":{"displayName":"Александр Ли","userId":"11169366018002229978"}},"outputId":"54f67d0d-ddcd-48b6-ce87-ff33555b325d"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 347ms/step\n","NN output: [[5.0932199e-01 3.2454227e-05 3.3057046e-03 5.1869772e-02 2.3799451e-04\n"," 5.4319475e-02 6.6690765e-05 1.3238982e-02 1.5642552e-01 2.1118149e-01]]\n"]},{"output_type":"display_data","data":{"text/plain":["<Figure size 640x480 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["Real mark: 0\n","NN answer: 0\n"]}]},{"cell_type":"code","source":["# вывод тестового изображения и результата распознавания 2\n","n = 111\n","result = model_5.predict(X_test[n:n+1])\n","print('NN output:', result)\n","9\n","plt.imshow(X_test[n].reshape(28,28), cmap=plt.get_cmap('gray'))\n","plt.show()\n","print('Real mark: ', str(np.argmax(y_test[n])))\n","print('NN answer: ', str(np.argmax(result)))\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":517},"id":"8xnFNh_fWkpW","executionInfo":{"status":"ok","timestamp":1758375636714,"user_tz":-180,"elapsed":369,"user":{"displayName":"Александр Ли","userId":"11169366018002229978"}},"outputId":"d56a0639-8ccb-4c76-8c45-b38748a75107"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 122ms/step\n","NN output: [[1.4791858e-06 9.4321764e-01 2.4574984e-02 9.0776198e-03 2.5022458e-04\n"," 1.8704976e-03 1.4549885e-04 8.7578883e-03 1.1556224e-02 5.4802326e-04]]\n"]},{"output_type":"display_data","data":{"text/plain":["<Figure size 640x480 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["Real mark: 1\n","NN answer: 1\n"]}]},{"cell_type":"code","source":["# загрузка собственного изображения\n","from PIL import Image\n","file_data = Image.open('5.png')\n","file_data = file_data.convert('L') # перевод в градации серого\n","test_img = np.array(file_data)\n","\n","# вывод собственного изображения\n","plt.imshow(test_img, cmap=plt.get_cmap('gray'))\n","plt.show()\n","# предобработка\n","test_img = test_img / 255\n","test_img = test_img.reshape(1, num_pixels)\n","# распознавание\n","result = model_5.predict(test_img)\n","print('I think it\\'s ', np.argmax(result))"],"metadata":{"id":"vLHbBjHFWqwp","colab":{"base_uri":"https://localhost:8080/","height":465},"executionInfo":{"status":"ok","timestamp":1758377378048,"user_tz":-180,"elapsed":490,"user":{"displayName":"Александр Ли","userId":"11169366018002229978"}},"outputId":"ce366287-bc90-4efd-bd13-3de09858bb88"},"execution_count":33,"outputs":[{"output_type":"display_data","data":{"text/plain":["<Figure size 640x480 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 91ms/step\n","I think it's 5\n"]}]},{"cell_type":"code","source":["file_data = Image.open('2.png')\n","file_data = file_data.convert('L') # перевод в градации серого\n","test_img = np.array(file_data)\n","\n","# вывод собственного изображения\n","plt.imshow(test_img, cmap=plt.get_cmap('gray'))\n","plt.show()\n","# предобработка\n","test_img = test_img / 255\n","test_img = test_img.reshape(1, num_pixels)\n","# распознавание\n","result = model_5.predict(test_img)\n","print('I think it\\'s ', np.argmax(result))"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":465},"id":"2YSqzMkvdSDb","executionInfo":{"status":"ok","timestamp":1758377443514,"user_tz":-180,"elapsed":287,"user":{"displayName":"Александр Ли","userId":"11169366018002229978"}},"outputId":"0899a020-e800-4ed0-c50e-c675a4d820dd"},"execution_count":34,"outputs":[{"output_type":"display_data","data":{"text/plain":["<Figure size 640x480 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 47ms/step\n","I think it's 2\n"]}]},{"cell_type":"code","source":["file_data = Image.open('2_1.png')\n","file_data = file_data.convert('L') # перевод в градации серого\n","test_img = np.array(file_data)\n","\n","# вывод собственного изображения\n","plt.imshow(test_img, cmap=plt.get_cmap('gray'))\n","plt.show()\n","# предобработка\n","test_img = test_img / 255\n","test_img = test_img.reshape(1, num_pixels)\n","# распознавание\n","result = model_5.predict(test_img)\n","print('I think it\\'s ', np.argmax(result))"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":465},"id":"24nABeDGlVJ0","executionInfo":{"status":"ok","timestamp":1758379686626,"user_tz":-180,"elapsed":353,"user":{"displayName":"Александр Ли","userId":"11169366018002229978"}},"outputId":"7c3aa1e5-ca6e-41de-a69c-65592ab5cc9f"},"execution_count":35,"outputs":[{"output_type":"display_data","data":{"text/plain":["<Figure size 640x480 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 52ms/step\n","I think it's 4\n"]}]},{"cell_type":"code","source":["file_data = Image.open('5_1.png')\n","file_data = file_data.convert('L') # перевод в градации серого\n","test_img = np.array(file_data)\n","\n","# вывод собственного изображения\n","plt.imshow(test_img, cmap=plt.get_cmap('gray'))\n","plt.show()\n","# предобработка\n","test_img = test_img / 255\n","test_img = test_img.reshape(1, num_pixels)\n","# распознавание\n","result = model_5.predict(test_img)\n","print('I think it\\'s ', np.argmax(result))"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":465},"id":"24fY8TDOmLd5","executionInfo":{"status":"ok","timestamp":1758379694838,"user_tz":-180,"elapsed":528,"user":{"displayName":"Александр Ли","userId":"11169366018002229978"}},"outputId":"931f30f7-3a6f-49ef-89bd-dba22680e9db"},"execution_count":36,"outputs":[{"output_type":"display_data","data":{"text/plain":["<Figure size 640x480 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 92ms/step\n","I think it's 7\n"]}]},{"cell_type":"code","source":[],"metadata":{"id":"3rt_YPmimNbl"},"execution_count":null,"outputs":[]}]} |