MLA_Learn_Periodic_Functions/code/resnet18/resnet18_snake.py

# Réseau inspiré de http://yann.lecun.com/exdb/publis/pdf/lecun-98.pdf



from tensorflow.python.ops.gen_array_ops import tensor_scatter_min_eager_fallback
from resnet18 import ResNet18
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt


def displayConvFilers(model, layer_name, num_filter=4, filter_size=(3,3), num_channel=0, fig_size=(2,2)):
    
    layer_dict = dict([(layer.name, layer) for layer in model.layers])
    
    weight, biais = layer_dict[layer_name].get_weights()
    print(weight.shape) 
    plt.figure(figsize=fig_size)
    for i in range(num_filter):
        plt.subplot(fig_size[0],fig_size[1],i+1)
        plt.xticks([])
        plt.yticks([])
        plt.grid(False)
        vis = np.reshape(weight[:,:,num_channel,i],filter_size)
        plt.imshow(vis, cmap=plt.cm.binary)
    plt.show()


def snake(x):
    return x + tf.sin(x)**2


## Chargement et normalisation des données
resnet18 = tf.keras.datasets.cifar10
(train_images, train_labels), (test_images, test_labels) = resnet18.load_data()
train_images = train_images.astype('float32')
test_images = test_images.astype('float32')

from sklearn.model_selection import train_test_split
train_images, val_images, train_labels, val_labels = train_test_split(train_images,train_labels, test_size = 0.2,shuffle = True)



'''
val_images = train_images[40000:]
val_labels = train_labels[40000:]

train_images = train_images[:40000]
train_labels = train_labels[:40000]
'''

train_images = train_images / 255.0
val_images = val_images /255.0
test_images = test_images / 255.0

# POUR LES CNN : On rajoute une dimension pour spécifier qu'il s'agit d'imgages en NdG
train_images = train_images.reshape(max(np.shape(train_images)),32,32,3)
val_images = val_images.reshape(max(np.shape(val_images)),32,32,3)
test_images = test_images.reshape(max(np.shape(test_images)),32,32,3)


# One hot encoding
train_labels = tf.keras.utils.to_categorical(train_labels)
val_labels = tf.keras.utils.to_categorical(val_labels)
test_labels = tf.keras.utils.to_categorical(test_labels)

filter_size_conv1 = (3,3)

model = ResNet18(10)
model.build(input_shape = (None,32,32,3))

'''
filter_size_conv1 = (5,5)
## Définition de l'architecture du modèle
model = tf.keras.models.Sequential()
# Expliquez à quoi correspondent les valeurs numériques qui définissent les couches du réseau
model.add(tf.keras.layers.Conv2D(filters=6,kernel_size=filter_size_conv1,padding="same", activation=snake, input_shape=(32, 32, 3)))
model.add(tf.keras.layers.AveragePooling2D())
model.add(tf.keras.layers.Conv2D(filters=16,kernel_size=(5,5),padding="valid", activation=snake))
model.add(tf.keras.layers.AveragePooling2D())
model.add(tf.keras.layers.Flatten())
model.add(tf.keras.layers.Dense(120 , activation=snake))
#mnist_model.add(tf.keras.layers.Dropout(0.5))
model.add(tf.keras.layers.Dense(84 , activation=snake))
model.add(tf.keras.layers.Dense(10 , activation='softmax'))
'''

# expliquer le nombre de paramètre de ce réseau
print(model.summary())


sgd = tf.keras.optimizers.Adam()

model.compile(sgd, loss='categorical_crossentropy', metrics=['accuracy'])

# On visualise avant l'entrainement



history = model.fit(train_images,
         train_labels,
         batch_size=256,
         epochs=50,
         validation_data=(val_images, val_labels),
         )

## Evaluation du modèle 
test_loss, test_acc = model.evaluate(test_images, test_labels)
print('Test accuracy:', test_acc)

fig, axs = plt.subplots(2, 1, figsize=(15,15))

axs[0].plot(history.history['loss'])
axs[0].plot(history.history['val_loss'])
axs[0].title.set_text('Training Loss vs Validation Loss')
axs[0].legend(['Train', 'Val'])

axs[1].plot(history.history['accuracy'])
axs[1].plot(history.history['val_accuracy'])
axs[1].title.set_text('Training Accuracy vs Validation Accuracy')
axs[1].legend(['Train', 'Val'])
plt.savefig('./resnet18snake.png')


'''
displayConvFilers(mnist_model,
                    'conv2d', 
                    num_filter=6, 
                    filter_size=filter_size_conv1, 
                    num_channel=0, 
                    fig_size=(2,3)
                )
'''