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.
256 строки
8.8 KiB
Python
256 строки
8.8 KiB
Python
# -*- coding: utf-8 -*-
|
|
"""lw3.ipynb
|
|
|
|
Automatically generated by Colab.
|
|
|
|
Original file is located at
|
|
https://colab.research.google.com/drive/1whkpae-DQ5QCfyJAnjIH0_Zff9zaT4po
|
|
"""
|
|
|
|
from google.colab import drive
|
|
drive.mount('/content/drive')
|
|
|
|
import os
|
|
os.chdir('/content/drive/MyDrive/Colab Notebooks/is_lab3')
|
|
|
|
import numpy as np
|
|
import matplotlib.pyplot as plt
|
|
|
|
from tensorflow import keras
|
|
from tensorflow.keras import layers
|
|
from tensorflow.keras.models import Sequential
|
|
|
|
from sklearn.metrics import classification_report, confusion_matrix, ConfusionMatrixDisplay
|
|
from sklearn.model_selection import train_test_split
|
|
|
|
import tensorflow as tf
|
|
tf.random.set_seed(123)
|
|
np.random.seed(123)
|
|
|
|
from keras.datasets import mnist
|
|
|
|
(X_train_full, y_train_full), (X_test_full, y_test_full) = mnist.load_data()
|
|
|
|
X = np.concatenate((X_train_full, X_test_full), axis=0)
|
|
y = np.concatenate((y_train_full, y_test_full), axis=0)
|
|
|
|
k = 5
|
|
random_state = 4 * k - 1
|
|
|
|
X_train, X_test, y_train, y_test = train_test_split(
|
|
X, y, train_size=60000, test_size=10000, random_state=random_state, shuffle=True
|
|
)
|
|
|
|
print('Shape of X_train:', X_train.shape)
|
|
print('Shape of y_train:', y_train.shape)
|
|
print('Shape of X_test:', X_test.shape)
|
|
print('Shape of y_test:', y_test.shape)
|
|
|
|
num_classes = 10
|
|
input_shape = (28, 28, 1)
|
|
|
|
# приведение значений к диапазону [0,1]
|
|
X_train = X_train.astype('float32') / 255.0
|
|
X_test = X_test.astype('float32') / 255.0
|
|
|
|
# добавление размерности каналов
|
|
X_train = np.expand_dims(X_train, -1)
|
|
X_test = np.expand_dims(X_test, -1)
|
|
|
|
# one-hot кодирование меток
|
|
y_train_cat = keras.utils.to_categorical(y_train, num_classes)
|
|
y_test_cat = keras.utils.to_categorical(y_test, num_classes)
|
|
|
|
print('Shape of transformed X_train:', X_train.shape)
|
|
print('Shape of transformed y_train:', y_train_cat.shape)
|
|
print('Shape of transformed X_test:', X_test.shape)
|
|
print('Shape of transformed y_test:', y_test_cat.shape)
|
|
|
|
batch_size = 512
|
|
epochs = 15
|
|
|
|
model = Sequential()
|
|
model.add(layers.Conv2D(32, kernel_size=(3,3), activation='relu', input_shape=input_shape))
|
|
model.add(layers.MaxPooling2D(pool_size=(2,2)))
|
|
model.add(layers.Conv2D(64, kernel_size=(3,3), activation='relu'))
|
|
model.add(layers.MaxPooling2D(pool_size=(2,2)))
|
|
model.add(layers.Dropout(0.5))
|
|
model.add(layers.Flatten())
|
|
model.add(layers.Dense(num_classes, activation='softmax'))
|
|
|
|
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
|
|
model.summary()
|
|
|
|
history = model.fit(X_train, y_train_cat, batch_size=batch_size, epochs=epochs, validation_split=0.1)
|
|
|
|
scores = model.evaluate(X_test, y_test_cat, verbose=2)
|
|
print('Loss on test data:', scores[0])
|
|
print('Accuracy on test data:', scores[1])
|
|
|
|
indices = [0, 1]
|
|
for n in indices:
|
|
result = model.predict(X_test[n:n+1])
|
|
plt.figure()
|
|
plt.imshow(X_test[n].reshape(28,28), cmap='gray')
|
|
plt.title(f"Real: {y_test[n]} Pred: {np.argmax(result)}")
|
|
plt.axis('off')
|
|
plt.show()
|
|
print('NN output vector:', result)
|
|
print('Real mark:', y_test[n])
|
|
print('NN answer:', np.argmax(result))
|
|
|
|
true_labels = y_test
|
|
predicted_labels = np.argmax(model.predict(X_test), axis=1)
|
|
|
|
print(classification_report(true_labels, predicted_labels))
|
|
conf_matrix = confusion_matrix(true_labels, predicted_labels)
|
|
display = ConfusionMatrixDisplay(confusion_matrix=conf_matrix)
|
|
display.plot()
|
|
plt.show()
|
|
|
|
from PIL import Image
|
|
|
|
img_path = '../5.png'
|
|
|
|
file_data = Image.open(img_path)
|
|
file_data = file_data.convert('L') # перевод в градации серого
|
|
test_img = np.array(file_data)
|
|
|
|
plt.imshow(test_img, cmap='gray')
|
|
plt.axis('off')
|
|
plt.show()
|
|
|
|
# нормализация и изменение формы
|
|
test_proc = test_img.astype('float32') / 255.0
|
|
test_proc = np.reshape(test_proc, (1, 28, 28, 1))
|
|
|
|
result = model.predict(test_proc)
|
|
print("NN output vector:", result)
|
|
print("I think it's", np.argmax(result))
|
|
|
|
model_lr1_path = '../best_model_2x100.h5'
|
|
|
|
if os.path.exists(model_lr1_path):
|
|
model_lr1 = load_model(model_lr1_path)
|
|
model_lr1.summary()
|
|
|
|
# подготовка данных специально для полносвязной модели ЛР1
|
|
X_test_lr1 = X_test.reshape((X_test.shape[0], 28*28))
|
|
X_test_lr1 = X_test_lr1.astype('float32') / 255.0
|
|
|
|
# здесь нужно использовать X_test_lr1 !
|
|
scores_lr1 = model_lr1.evaluate(X_test_lr1, y_test_cat, verbose=2)
|
|
|
|
print('LR1 model - Loss on test data:', scores_lr1[0])
|
|
print('LR1 model - Accuracy on test data:', scores_lr1[1])
|
|
|
|
else:
|
|
print(f"Файл {model_lr1_path} не найден. Поместите сохранённую модель ЛР1 в рабочую директорию.")
|
|
|
|
# возьмём оригинальные X, y — до всех преобразований для CNN
|
|
(X_train_full, y_train_full), (X_test_full, y_test_full) = mnist.load_data()
|
|
|
|
# объединим, чтобы сделать то же разбиение, что и в ЛР1
|
|
X_all = np.concatenate((X_train_full, X_test_full), axis=0)
|
|
y_all = np.concatenate((y_train_full, y_test_full), axis=0)
|
|
|
|
from sklearn.model_selection import train_test_split
|
|
X_train_l1, X_test_l1, y_train_l1, y_test_l1 = train_test_split(
|
|
X_all, y_all, train_size=60000, test_size=10000, random_state=19
|
|
)
|
|
|
|
# теперь — подготовка данных ЛР1
|
|
X_test_lr1 = X_test_l1.reshape((X_test_l1.shape[0], 28*28)).astype('float32') / 255.0
|
|
y_test_lr1 = keras.utils.to_categorical(y_test_l1, 10)
|
|
|
|
# оценка модели
|
|
scores_lr1 = model_lr1.evaluate(X_test_lr1, y_test_lr1, verbose=2)
|
|
print(scores_lr1)
|
|
|
|
# загрузка сохранённой модели ЛР1
|
|
model_lr1_path = '../best_model_2x100.h5'
|
|
model_lr1 = load_model(model_lr1_path)
|
|
model_lr1.summary()
|
|
|
|
# подготовка тестового набора для модели ЛР1
|
|
X_test_l1 = X_test_l1.reshape((X_test_l1.shape[0], 28 * 28)).astype('float32') / 255.0
|
|
y_test_l1_cat = keras.utils.to_categorical(y_test_l1, 10)
|
|
|
|
# оценка модели ЛР1
|
|
scores_lr1 = model_lr1.evaluate(X_test_l1, y_test_l1_cat, verbose=2)
|
|
print('LR1 model - Loss:', scores_lr1[0])
|
|
print('LR1 model - Accuracy:', scores_lr1[1])
|
|
|
|
# оценка сверточной модели ЛР3
|
|
scores_conv = model.evaluate(X_test, y_test_cat, verbose=2)
|
|
print('Conv model - Loss:', scores_conv[0])
|
|
print('Conv model - Accuracy:', scores_conv[1])
|
|
|
|
# вывод числа параметров обеих моделей
|
|
print('LR1 model parameters:', model_lr1.count_params())
|
|
print('Conv model parameters:', model.count_params())
|
|
|
|
from keras.datasets import cifar10
|
|
|
|
(X_train_c, y_train_c), (X_test_c, y_test_c) = cifar10.load_data()
|
|
|
|
print('Shapes (original):', X_train_c.shape, y_train_c.shape, X_test_c.shape, y_test_c.shape)
|
|
|
|
class_names = ['airplane', 'automobile', 'bird', 'cat', 'deer',
|
|
'dog', 'frog', 'horse', 'ship', 'truck']
|
|
|
|
# вывод 25 изображений
|
|
plt.figure(figsize=(10,10))
|
|
for i in range(25):
|
|
plt.subplot(5,5,i+1)
|
|
plt.xticks([])
|
|
plt.yticks([])
|
|
plt.grid(False)
|
|
plt.imshow(X_train_c[i])
|
|
plt.xlabel(class_names[y_train_c[i][0]])
|
|
plt.show()
|
|
|
|
num_classes = 10
|
|
input_shape_cifar = (32, 32, 3)
|
|
|
|
X_train_c = X_train_c.astype('float32') / 255.0
|
|
X_test_c = X_test_c.astype('float32') / 255.0
|
|
|
|
y_train_c_cat = keras.utils.to_categorical(y_train_c, num_classes)
|
|
y_test_c_cat = keras.utils.to_categorical(y_test_c, num_classes)
|
|
|
|
print('Transformed shapes:', X_train_c.shape, y_train_c_cat.shape, X_test_c.shape, y_test_c_cat.shape)
|
|
|
|
model_cifar = Sequential()
|
|
model_cifar.add(layers.Conv2D(32, (3,3), activation='relu', input_shape=input_shape_cifar))
|
|
model_cifar.add(layers.MaxPooling2D((2,2)))
|
|
model_cifar.add(layers.Conv2D(64, (3,3), activation='relu'))
|
|
model_cifar.add(layers.MaxPooling2D((2,2)))
|
|
model_cifar.add(layers.Conv2D(128, (3,3), activation='relu'))
|
|
model_cifar.add(layers.MaxPooling2D((2,2)))
|
|
model_cifar.add(layers.Flatten())
|
|
model_cifar.add(layers.Dense(128, activation='relu'))
|
|
model_cifar.add(layers.Dropout(0.5))
|
|
model_cifar.add(layers.Dense(num_classes, activation='softmax'))
|
|
|
|
model_cifar.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
|
|
model_cifar.summary()
|
|
|
|
batch_size = 512
|
|
epochs = 20
|
|
history_cifar = model_cifar.fit(X_train_c, y_train_c_cat, batch_size=batch_size, epochs=epochs, validation_split=0.1)
|
|
|
|
scores_cifar = model_cifar.evaluate(X_test_c, y_test_c_cat, verbose=2)
|
|
print('CIFAR - Loss on test data:', scores_cifar[0])
|
|
print('CIFAR - Accuracy on test data:', scores_cifar[1])
|
|
|
|
print(classification_report(true_cifar, preds_cifar, target_names=class_names))
|
|
|
|
conf_matrix_cifar = confusion_matrix(true_cifar, preds_cifar)
|
|
display = ConfusionMatrixDisplay(confusion_matrix=conf_matrix_cifar,
|
|
display_labels=class_names)
|
|
|
|
plt.figure(figsize=(10,10)) # figsize задаётся здесь
|
|
display.plot(cmap='Blues', colorbar=False) # без figsize
|
|
plt.xticks(rotation=45)
|
|
plt.show() |