Aller à la barre d’outils

Use pretrained models (transfer learning)

Plutôt que de réinventer la poudre, utilisons le tutoriel de TensorFlow.

Comme très souvent, il y est question de classification de chiens et chats, à partir d’images.

Le logiciel est ici.

Le modèle pré-entraîné est MobileNetV2.

Obtention des données

import os
import numpy as np
import matplotlib.pyplot as plt
import tensorflow as tf
import tensorflow_datasets as tfds
tfds.disable_progress_bar()
(raw_train, raw_validation, raw_test), metadata = tfds.load(
    'cats_vs_dogs',
    split=['train[:80%]', 'train[80%:90%]', 'train[90%:]'],
    with_info=True,
    as_supervised=True,
Downloading and preparing dataset cats_vs_dogs/4.0.0 (download: 786.68 MiB, generated: Unknown size, total: 786.68 MiB) to /root/tensorflow_datasets/cats_vs_dogs/4.0.0...
/usr/local/lib/python3.6/dist-packages/urllib3/connectionpool.py:847: InsecureRequestWarning: Unverified HTTPS request is being made. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#ssl-warnings
  InsecureRequestWarning)
WARNING:absl:1738 images were corrupted and were skipped
Shuffling and writing examples to /root/tensorflow_datasets/cats_vs_dogs/4.0.0.incomplete12R3AN/cats_vs_dogs-train.tfrecord
Dataset cats_vs_dogs downloaded and prepared to /root/tensorflow_datasets/cats_vs_dogs/4.0.0. Subsequent calls will reuse this data.
get_label_name = metadata.features['label'].int2str

for image, label in raw_train.take(4):
  plt.figure()
  plt.imshow(image)
  plt.title(get_label_name(label))

Format des données

Lorsqu’on utilise un CNN, il faut que les images soient de même taille et centrées.

IMG_SIZE = 160 # All images will be resized to 160x160 def format_example(image, label):  image = tf.cast(image, tf.float32)  image = (image/127.5) - 1  image = tf.image.resize(image, (IMG_SIZE, IMG_SIZE))  return image, label
train = raw_train.map(format_example)
validation = raw_validation.map(format_example)
test = raw_test.map(format_example)
BATCH_SIZE = 32
SHUFFLE_BUFFER_SIZE = 1000
train_batches = train.shuffle(SHUFFLE_BUFFER_SIZE).batch(BATCH_SIZE)
validation_batches = validation.batch(BATCH_SIZE)
test_batches = test.batch(BATCH_SIZE)

Le modèle

 MobileNet V2 a été entraîné sur 1,4 M d’images.

IMG_SHAPE = (IMG_SIZE, IMG_SIZE, 3)

# Create the base model from the pre-trained model MobileNet V2
base_model = tf.keras.applications.MobileNetV2(input_shape=IMG_SHAPE,
                                               include_top=False,
                                               weights='imagenet')

Nos images sont carrées et en couleur(s). On n’inclut pas la dernière couche (celle qui fait la classification) et on n’utilise les poids calculés sur le jeu de données ImageNet.

Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/mobilenet_v2/mobilenet_v2_weights_tf_dim_ordering_tf_kernels_1.0_160_no_top.h5
9412608/9406464 [==============================] - 0s 0us/step
feature_batch = base_model(image_batch)
print(feature_batch.shape)
(32, 5, 5, 1280)

On freeze le modèle afin que les poids ne soient pas recalculés.

base_model.trainable = False

Notre modèle est le suivant :

Model: "mobilenetv2_1.00_160"
__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
input_1 (InputLayer)            [(None, 160, 160, 3) 0                                            
__________________________________________________________________________________________________
Conv1_pad (ZeroPadding2D)       (None, 161, 161, 3)  0           input_1[0][0]                    
__________________________________________________________________________________________________
Conv1 (Conv2D)                  (None, 80, 80, 32)   864         Conv1_pad[0][0]                  
__________________________________________________________________________________________________
bn_Conv1 (BatchNormalization)   (None, 80, 80, 32)   128         Conv1[0][0]                      
__________________________________________________________________________________________________
Conv1_relu (ReLU)               (None, 80, 80, 32)   0           bn_Conv1[0][0]                   
__________________________________________________________________________________________________
expanded_conv_depthwise (Depthw (None, 80, 80, 32)   288         Conv1_relu[0][0]                 
__________________________________________________________________________________________________
expanded_conv_depthwise_BN (Bat (None, 80, 80, 32)   128         expanded_conv_depthwise[0][0]    
__________________________________________________________________________________________________
expanded_conv_depthwise_relu (R (None, 80, 80, 32)   0           expanded_conv_depthwise_BN[0][0] 
__________________________________________________________________________________________________
expanded_conv_project (Conv2D)  (None, 80, 80, 16)   512         expanded_conv_depthwise_relu[0][0
__________________________________________________________________________________________________
expanded_conv_project_BN (Batch (None, 80, 80, 16)   64          expanded_conv_project[0][0]      
__________________________________________________________________________________________________
block_1_expand (Conv2D)         (None, 80, 80, 96)   1536        expanded_conv_project_BN[0][0]   
__________________________________________________________________________________________________
block_1_expand_BN (BatchNormali (None, 80, 80, 96)   384         block_1_expand[0][0]             
__________________________________________________________________________________________________
block_1_expand_relu (ReLU)      (None, 80, 80, 96)   0           block_1_expand_BN[0][0]          
__________________________________________________________________________________________________
block_1_pad (ZeroPadding2D)     (None, 81, 81, 96)   0           block_1_expand_relu[0][0]        
__________________________________________________________________________________________________
block_1_depthwise (DepthwiseCon (None, 40, 40, 96)   864         block_1_pad[0][0]                
__________________________________________________________________________________________________
block_1_depthwise_BN (BatchNorm (None, 40, 40, 96)   384         block_1_depthwise[0][0]          
__________________________________________________________________________________________________
block_1_depthwise_relu (ReLU)   (None, 40, 40, 96)   0           block_1_depthwise_BN[0][0]       
__________________________________________________________________________________________________
block_1_project (Conv2D)        (None, 40, 40, 24)   2304        block_1_depthwise_relu[0][0]     
__________________________________________________________________________________________________
block_1_project_BN (BatchNormal (None, 40, 40, 24)   96          block_1_project[0][0]            
__________________________________________________________________________________________________
block_2_expand (Conv2D)         (None, 40, 40, 144)  3456        block_1_project_BN[0][0]         
__________________________________________________________________________________________________
block_2_expand_BN (BatchNormali (None, 40, 40, 144)  576         block_2_expand[0][0]             
__________________________________________________________________________________________________
block_2_expand_relu (ReLU)      (None, 40, 40, 144)  0           block_2_expand_BN[0][0]          
__________________________________________________________________________________________________
block_2_depthwise (DepthwiseCon (None, 40, 40, 144)  1296        block_2_expand_relu[0][0]        
__________________________________________________________________________________________________
block_2_depthwise_BN (BatchNorm (None, 40, 40, 144)  576         block_2_depthwise[0][0]          
__________________________________________________________________________________________________
block_2_depthwise_relu (ReLU)   (None, 40, 40, 144)  0           block_2_depthwise_BN[0][0]       
__________________________________________________________________________________________________
block_2_project (Conv2D)        (None, 40, 40, 24)   3456        block_2_depthwise_relu[0][0]     
__________________________________________________________________________________________________
block_2_project_BN (BatchNormal (None, 40, 40, 24)   96          block_2_project[0][0]            
__________________________________________________________________________________________________
block_2_add (Add)               (None, 40, 40, 24)   0           block_1_project_BN[0][0]         
                                                                 block_2_project_BN[0][0]         
__________________________________________________________________________________________________
block_3_expand (Conv2D)         (None, 40, 40, 144)  3456        block_2_add[0][0]                
__________________________________________________________________________________________________
block_3_expand_BN (BatchNormali (None, 40, 40, 144)  576         block_3_expand[0][0]             
__________________________________________________________________________________________________
block_3_expand_relu (ReLU)      (None, 40, 40, 144)  0           block_3_expand_BN[0][0]          
__________________________________________________________________________________________________
block_3_pad (ZeroPadding2D)     (None, 41, 41, 144)  0           block_3_expand_relu[0][0]        
__________________________________________________________________________________________________
block_3_depthwise (DepthwiseCon (None, 20, 20, 144)  1296        block_3_pad[0][0]                
__________________________________________________________________________________________________
block_3_depthwise_BN (BatchNorm (None, 20, 20, 144)  576         block_3_depthwise[0][0]          
__________________________________________________________________________________________________
block_3_depthwise_relu (ReLU)   (None, 20, 20, 144)  0           block_3_depthwise_BN[0][0]       
__________________________________________________________________________________________________
block_3_project (Conv2D)        (None, 20, 20, 32)   4608        block_3_depthwise_relu[0][0]     
__________________________________________________________________________________________________
block_3_project_BN (BatchNormal (None, 20, 20, 32)   128         block_3_project[0][0]            
__________________________________________________________________________________________________
block_4_expand (Conv2D)         (None, 20, 20, 192)  6144        block_3_project_BN[0][0]         
__________________________________________________________________________________________________
block_4_expand_BN (BatchNormali (None, 20, 20, 192)  768         block_4_expand[0][0]             
__________________________________________________________________________________________________
block_4_expand_relu (ReLU)      (None, 20, 20, 192)  0           block_4_expand_BN[0][0]          
__________________________________________________________________________________________________
block_4_depthwise (DepthwiseCon (None, 20, 20, 192)  1728        block_4_expand_relu[0][0]        
__________________________________________________________________________________________________
block_4_depthwise_BN (BatchNorm (None, 20, 20, 192)  768         block_4_depthwise[0][0]          
__________________________________________________________________________________________________
block_4_depthwise_relu (ReLU)   (None, 20, 20, 192)  0           block_4_depthwise_BN[0][0]       
__________________________________________________________________________________________________
block_4_project (Conv2D)        (None, 20, 20, 32)   6144        block_4_depthwise_relu[0][0]     
__________________________________________________________________________________________________
block_4_project_BN (BatchNormal (None, 20, 20, 32)   128         block_4_project[0][0]            
__________________________________________________________________________________________________
block_4_add (Add)               (None, 20, 20, 32)   0           block_3_project_BN[0][0]         
                                                                 block_4_project_BN[0][0]         
__________________________________________________________________________________________________
block_5_expand (Conv2D)         (None, 20, 20, 192)  6144        block_4_add[0][0]                
__________________________________________________________________________________________________
block_5_expand_BN (BatchNormali (None, 20, 20, 192)  768         block_5_expand[0][0]             
__________________________________________________________________________________________________
block_5_expand_relu (ReLU)      (None, 20, 20, 192)  0           block_5_expand_BN[0][0]          
__________________________________________________________________________________________________
block_5_depthwise (DepthwiseCon (None, 20, 20, 192)  1728        block_5_expand_relu[0][0]        
__________________________________________________________________________________________________
block_5_depthwise_BN (BatchNorm (None, 20, 20, 192)  768         block_5_depthwise[0][0]          
__________________________________________________________________________________________________
block_5_depthwise_relu (ReLU)   (None, 20, 20, 192)  0           block_5_depthwise_BN[0][0]       
__________________________________________________________________________________________________
block_5_project (Conv2D)        (None, 20, 20, 32)   6144        block_5_depthwise_relu[0][0]     
__________________________________________________________________________________________________
block_5_project_BN (BatchNormal (None, 20, 20, 32)   128         block_5_project[0][0]            
__________________________________________________________________________________________________
block_5_add (Add)               (None, 20, 20, 32)   0           block_4_add[0][0]                
                                                                 block_5_project_BN[0][0]         
__________________________________________________________________________________________________
block_6_expand (Conv2D)         (None, 20, 20, 192)  6144        block_5_add[0][0]                
__________________________________________________________________________________________________
block_6_expand_BN (BatchNormali (None, 20, 20, 192)  768         block_6_expand[0][0]             
__________________________________________________________________________________________________
block_6_expand_relu (ReLU)      (None, 20, 20, 192)  0           block_6_expand_BN[0][0]          
__________________________________________________________________________________________________
block_6_pad (ZeroPadding2D)     (None, 21, 21, 192)  0           block_6_expand_relu[0][0]        
__________________________________________________________________________________________________
block_6_depthwise (DepthwiseCon (None, 10, 10, 192)  1728        block_6_pad[0][0]                
__________________________________________________________________________________________________
block_6_depthwise_BN (BatchNorm (None, 10, 10, 192)  768         block_6_depthwise[0][0]          
__________________________________________________________________________________________________
block_6_depthwise_relu (ReLU)   (None, 10, 10, 192)  0           block_6_depthwise_BN[0][0]       
__________________________________________________________________________________________________
block_6_project (Conv2D)        (None, 10, 10, 64)   12288       block_6_depthwise_relu[0][0]     
__________________________________________________________________________________________________
block_6_project_BN (BatchNormal (None, 10, 10, 64)   256         block_6_project[0][0]            
__________________________________________________________________________________________________
block_7_expand (Conv2D)         (None, 10, 10, 384)  24576       block_6_project_BN[0][0]         
__________________________________________________________________________________________________
block_7_expand_BN (BatchNormali (None, 10, 10, 384)  1536        block_7_expand[0][0]             
__________________________________________________________________________________________________
block_7_expand_relu (ReLU)      (None, 10, 10, 384)  0           block_7_expand_BN[0][0]          
__________________________________________________________________________________________________
block_7_depthwise (DepthwiseCon (None, 10, 10, 384)  3456        block_7_expand_relu[0][0]        
__________________________________________________________________________________________________
block_7_depthwise_BN (BatchNorm (None, 10, 10, 384)  1536        block_7_depthwise[0][0]          
__________________________________________________________________________________________________
block_7_depthwise_relu (ReLU)   (None, 10, 10, 384)  0           block_7_depthwise_BN[0][0]       
__________________________________________________________________________________________________
block_7_project (Conv2D)        (None, 10, 10, 64)   24576       block_7_depthwise_relu[0][0]     
__________________________________________________________________________________________________
block_7_project_BN (BatchNormal (None, 10, 10, 64)   256         block_7_project[0][0]            
__________________________________________________________________________________________________
block_7_add (Add)               (None, 10, 10, 64)   0           block_6_project_BN[0][0]         
                                                                 block_7_project_BN[0][0]         
__________________________________________________________________________________________________
block_8_expand (Conv2D)         (None, 10, 10, 384)  24576       block_7_add[0][0]                
__________________________________________________________________________________________________
block_8_expand_BN (BatchNormali (None, 10, 10, 384)  1536        block_8_expand[0][0]             
__________________________________________________________________________________________________
block_8_expand_relu (ReLU)      (None, 10, 10, 384)  0           block_8_expand_BN[0][0]          
__________________________________________________________________________________________________
block_8_depthwise (DepthwiseCon (None, 10, 10, 384)  3456        block_8_expand_relu[0][0]        
__________________________________________________________________________________________________
block_8_depthwise_BN (BatchNorm (None, 10, 10, 384)  1536        block_8_depthwise[0][0]          
__________________________________________________________________________________________________
block_8_depthwise_relu (ReLU)   (None, 10, 10, 384)  0           block_8_depthwise_BN[0][0]       
__________________________________________________________________________________________________
block_8_project (Conv2D)        (None, 10, 10, 64)   24576       block_8_depthwise_relu[0][0]     
__________________________________________________________________________________________________
block_8_project_BN (BatchNormal (None, 10, 10, 64)   256         block_8_project[0][0]            
__________________________________________________________________________________________________
block_8_add (Add)               (None, 10, 10, 64)   0           block_7_add[0][0]                
                                                                 block_8_project_BN[0][0]         
__________________________________________________________________________________________________
block_9_expand (Conv2D)         (None, 10, 10, 384)  24576       block_8_add[0][0]                
__________________________________________________________________________________________________
block_9_expand_BN (BatchNormali (None, 10, 10, 384)  1536        block_9_expand[0][0]             
__________________________________________________________________________________________________
block_9_expand_relu (ReLU)      (None, 10, 10, 384)  0           block_9_expand_BN[0][0]          
__________________________________________________________________________________________________
block_9_depthwise (DepthwiseCon (None, 10, 10, 384)  3456        block_9_expand_relu[0][0]        
__________________________________________________________________________________________________
block_9_depthwise_BN (BatchNorm (None, 10, 10, 384)  1536        block_9_depthwise[0][0]          
__________________________________________________________________________________________________
block_9_depthwise_relu (ReLU)   (None, 10, 10, 384)  0           block_9_depthwise_BN[0][0]       
__________________________________________________________________________________________________
block_9_project (Conv2D)        (None, 10, 10, 64)   24576       block_9_depthwise_relu[0][0]     
__________________________________________________________________________________________________
block_9_project_BN (BatchNormal (None, 10, 10, 64)   256         block_9_project[0][0]            
__________________________________________________________________________________________________
block_9_add (Add)               (None, 10, 10, 64)   0           block_8_add[0][0]                
                                                                 block_9_project_BN[0][0]         
__________________________________________________________________________________________________
block_10_expand (Conv2D)        (None, 10, 10, 384)  24576       block_9_add[0][0]                
__________________________________________________________________________________________________
block_10_expand_BN (BatchNormal (None, 10, 10, 384)  1536        block_10_expand[0][0]            
__________________________________________________________________________________________________
block_10_expand_relu (ReLU)     (None, 10, 10, 384)  0           block_10_expand_BN[0][0]         
__________________________________________________________________________________________________
block_10_depthwise (DepthwiseCo (None, 10, 10, 384)  3456        block_10_expand_relu[0][0]       
__________________________________________________________________________________________________
block_10_depthwise_BN (BatchNor (None, 10, 10, 384)  1536        block_10_depthwise[0][0]         
__________________________________________________________________________________________________
block_10_depthwise_relu (ReLU)  (None, 10, 10, 384)  0           block_10_depthwise_BN[0][0]      
__________________________________________________________________________________________________
block_10_project (Conv2D)       (None, 10, 10, 96)   36864       block_10_depthwise_relu[0][0]    
__________________________________________________________________________________________________
block_10_project_BN (BatchNorma (None, 10, 10, 96)   384         block_10_project[0][0]           
__________________________________________________________________________________________________
block_11_expand (Conv2D)        (None, 10, 10, 576)  55296       block_10_project_BN[0][0]        
__________________________________________________________________________________________________
block_11_expand_BN (BatchNormal (None, 10, 10, 576)  2304        block_11_expand[0][0]            
__________________________________________________________________________________________________
block_11_expand_relu (ReLU)     (None, 10, 10, 576)  0           block_11_expand_BN[0][0]         
__________________________________________________________________________________________________
block_11_depthwise (DepthwiseCo (None, 10, 10, 576)  5184        block_11_expand_relu[0][0]       
__________________________________________________________________________________________________
block_11_depthwise_BN (BatchNor (None, 10, 10, 576)  2304        block_11_depthwise[0][0]         
__________________________________________________________________________________________________
block_11_depthwise_relu (ReLU)  (None, 10, 10, 576)  0           block_11_depthwise_BN[0][0]      
__________________________________________________________________________________________________
block_11_project (Conv2D)       (None, 10, 10, 96)   55296       block_11_depthwise_relu[0][0]    
__________________________________________________________________________________________________
block_11_project_BN (BatchNorma (None, 10, 10, 96)   384         block_11_project[0][0]           
__________________________________________________________________________________________________
block_11_add (Add)              (None, 10, 10, 96)   0           block_10_project_BN[0][0]        
                                                                 block_11_project_BN[0][0]        
__________________________________________________________________________________________________
block_12_expand (Conv2D)        (None, 10, 10, 576)  55296       block_11_add[0][0]               
__________________________________________________________________________________________________
block_12_expand_BN (BatchNormal (None, 10, 10, 576)  2304        block_12_expand[0][0]            
__________________________________________________________________________________________________
block_12_expand_relu (ReLU)     (None, 10, 10, 576)  0           block_12_expand_BN[0][0]         
__________________________________________________________________________________________________
block_12_depthwise (DepthwiseCo (None, 10, 10, 576)  5184        block_12_expand_relu[0][0]       
__________________________________________________________________________________________________
block_12_depthwise_BN (BatchNor (None, 10, 10, 576)  2304        block_12_depthwise[0][0]         
__________________________________________________________________________________________________
block_12_depthwise_relu (ReLU)  (None, 10, 10, 576)  0           block_12_depthwise_BN[0][0]      
__________________________________________________________________________________________________
block_12_project (Conv2D)       (None, 10, 10, 96)   55296       block_12_depthwise_relu[0][0]    
__________________________________________________________________________________________________
block_12_project_BN (BatchNorma (None, 10, 10, 96)   384         block_12_project[0][0]           
__________________________________________________________________________________________________
block_12_add (Add)              (None, 10, 10, 96)   0           block_11_add[0][0]               
                                                                 block_12_project_BN[0][0]        
__________________________________________________________________________________________________
block_13_expand (Conv2D)        (None, 10, 10, 576)  55296       block_12_add[0][0]               
__________________________________________________________________________________________________
block_13_expand_BN (BatchNormal (None, 10, 10, 576)  2304        block_13_expand[0][0]            
__________________________________________________________________________________________________
block_13_expand_relu (ReLU)     (None, 10, 10, 576)  0           block_13_expand_BN[0][0]         
__________________________________________________________________________________________________
block_13_pad (ZeroPadding2D)    (None, 11, 11, 576)  0           block_13_expand_relu[0][0]       
__________________________________________________________________________________________________
block_13_depthwise (DepthwiseCo (None, 5, 5, 576)    5184        block_13_pad[0][0]               
__________________________________________________________________________________________________
block_13_depthwise_BN (BatchNor (None, 5, 5, 576)    2304        block_13_depthwise[0][0]         
__________________________________________________________________________________________________
block_13_depthwise_relu (ReLU)  (None, 5, 5, 576)    0           block_13_depthwise_BN[0][0]      
__________________________________________________________________________________________________
block_13_project (Conv2D)       (None, 5, 5, 160)    92160       block_13_depthwise_relu[0][0]    
__________________________________________________________________________________________________
block_13_project_BN (BatchNorma (None, 5, 5, 160)    640         block_13_project[0][0]           
__________________________________________________________________________________________________
block_14_expand (Conv2D)        (None, 5, 5, 960)    153600      block_13_project_BN[0][0]        
__________________________________________________________________________________________________
block_14_expand_BN (BatchNormal (None, 5, 5, 960)    3840        block_14_expand[0][0]            
__________________________________________________________________________________________________
block_14_expand_relu (ReLU)     (None, 5, 5, 960)    0           block_14_expand_BN[0][0]         
__________________________________________________________________________________________________
block_14_depthwise (DepthwiseCo (None, 5, 5, 960)    8640        block_14_expand_relu[0][0]       
__________________________________________________________________________________________________
block_14_depthwise_BN (BatchNor (None, 5, 5, 960)    3840        block_14_depthwise[0][0]         
__________________________________________________________________________________________________
block_14_depthwise_relu (ReLU)  (None, 5, 5, 960)    0           block_14_depthwise_BN[0][0]      
__________________________________________________________________________________________________
block_14_project (Conv2D)       (None, 5, 5, 160)    153600      block_14_depthwise_relu[0][0]    
__________________________________________________________________________________________________
block_14_project_BN (BatchNorma (None, 5, 5, 160)    640         block_14_project[0][0]           
__________________________________________________________________________________________________
block_14_add (Add)              (None, 5, 5, 160)    0           block_13_project_BN[0][0]        
                                                                 block_14_project_BN[0][0]        
__________________________________________________________________________________________________
block_15_expand (Conv2D)        (None, 5, 5, 960)    153600      block_14_add[0][0]               
__________________________________________________________________________________________________
block_15_expand_BN (BatchNormal (None, 5, 5, 960)    3840        block_15_expand[0][0]            
__________________________________________________________________________________________________
block_15_expand_relu (ReLU)     (None, 5, 5, 960)    0           block_15_expand_BN[0][0]         
__________________________________________________________________________________________________
block_15_depthwise (DepthwiseCo (None, 5, 5, 960)    8640        block_15_expand_relu[0][0]       
__________________________________________________________________________________________________
block_15_depthwise_BN (BatchNor (None, 5, 5, 960)    3840        block_15_depthwise[0][0]         
__________________________________________________________________________________________________
block_15_depthwise_relu (ReLU)  (None, 5, 5, 960)    0           block_15_depthwise_BN[0][0]      
__________________________________________________________________________________________________
block_15_project (Conv2D)       (None, 5, 5, 160)    153600      block_15_depthwise_relu[0][0]    
__________________________________________________________________________________________________
block_15_project_BN (BatchNorma (None, 5, 5, 160)    640         block_15_project[0][0]           
__________________________________________________________________________________________________
block_15_add (Add)              (None, 5, 5, 160)    0           block_14_add[0][0]               
                                                                 block_15_project_BN[0][0]        
__________________________________________________________________________________________________
block_16_expand (Conv2D)        (None, 5, 5, 960)    153600      block_15_add[0][0]               
__________________________________________________________________________________________________
block_16_expand_BN (BatchNormal (None, 5, 5, 960)    3840        block_16_expand[0][0]            
__________________________________________________________________________________________________
block_16_expand_relu (ReLU)     (None, 5, 5, 960)    0           block_16_expand_BN[0][0]         
__________________________________________________________________________________________________
block_16_depthwise (DepthwiseCo (None, 5, 5, 960)    8640        block_16_expand_relu[0][0]       
__________________________________________________________________________________________________
block_16_depthwise_BN (BatchNor (None, 5, 5, 960)    3840        block_16_depthwise[0][0]         
__________________________________________________________________________________________________
block_16_depthwise_relu (ReLU)  (None, 5, 5, 960)    0           block_16_depthwise_BN[0][0]      
__________________________________________________________________________________________________
block_16_project (Conv2D)       (None, 5, 5, 320)    307200      block_16_depthwise_relu[0][0]    
__________________________________________________________________________________________________
block_16_project_BN (BatchNorma (None, 5, 5, 320)    1280        block_16_project[0][0]           
__________________________________________________________________________________________________
Conv_1 (Conv2D)                 (None, 5, 5, 1280)   409600      block_16_project_BN[0][0]        
__________________________________________________________________________________________________
Conv_1_bn (BatchNormalization)  (None, 5, 5, 1280)   5120        Conv_1[0][0]                     
__________________________________________________________________________________________________
out_relu (ReLU)                 (None, 5, 5, 1280)   0           Conv_1_bn[0][0]                  
==================================================================================================
Total params: 2,257,984
Trainable params: 0
Non-trainable params: 2,257,984
__________________________________________________________________________________________________

Notez que : Trainable params: 0

A ce modèle, on ajoute global_average_layer et prediction_layer.

global_average_layer = tf.keras.layers.GlobalAveragePooling2D()
prediction_layer = tf.keras.layers.Dense(1)
model = tf.keras.Sequential([
  base_model,
  global_average_layer,
  prediction_layer
])

Ne reste plus qu’à compiler le modèle et l’entraîner.

base_learning_rate = 0.0001
model.compile(optimizer=tf.keras.optimizers.RMSprop(lr=base_learning_rate),
              loss=tf.keras.losses.BinaryCrossentropy(from_logits=True),
              metrics=['accuracy'])

La fonction de perte est tf.keras.losses.BinaryCrossentropy puisque nous sommes dans un cas de classification binaire. L’optimizer est RMSprop, ce choix est à discuter ultérieurement.

model.summary()
Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
mobilenetv2_1.00_160 (Model) (None, 5, 5, 1280)        2257984   
_________________________________________________________________
global_average_pooling2d (Gl (None, 1280)              0         
_________________________________________________________________
dense (Dense)                (None, 1)                 1281      
=================================================================
Total params: 2,259,265
Trainable params: 1,281
Non-trainable params: 2,257,984

Si on n’entraîne pas le modèle, l’accuracy est faible.

initial_epochs = 10
validation_steps=20

loss0,accuracy0 = model.evaluate(validation_batches, steps = validation_steps)
20/20 [==============================] - 1s 54ms/step - loss: 0.8105 - accuracy: 0.4516

Mais si on l’entraîne :

history = model.fit(train_batches,
                    epochs=initial_epochs,
                    validation_data=validation_batches)

On arrive à plus de 98% d’accuracy.

Epoch 1/10
582/582 [==============================] - 44s 76ms/step - loss: 0.2200 - accuracy: 0.9005 - val_loss: 0.0894 - val_accuracy: 0.9665
Epoch 2/10
582/582 [==============================] - 44s 75ms/step - loss: 0.0729 - accuracy: 0.9740 - val_loss: 0.0640 - val_accuracy: 0.9733
Epoch 3/10
582/582 [==============================] - 45s 77ms/step - loss: 0.0583 - accuracy: 0.9784 - val_loss: 0.0559 - val_accuracy: 0.9764
Epoch 4/10
582/582 [==============================] - 44s 76ms/step - loss: 0.0522 - accuracy: 0.9808 - val_loss: 0.0522 - val_accuracy: 0.9776
Epoch 5/10
582/582 [==============================] - 45s 77ms/step - loss: 0.0487 - accuracy: 0.9821 - val_loss: 0.0495 - val_accuracy: 0.9819
Epoch 6/10
582/582 [==============================] - 45s 77ms/step - loss: 0.0463 - accuracy: 0.9833 - val_loss: 0.0483 - val_accuracy: 0.9819
Epoch 7/10
582/582 [==============================] - 45s 77ms/step - loss: 0.0446 - accuracy: 0.9836 - val_loss: 0.0470 - val_accuracy: 0.9828
Epoch 8/10
582/582 [==============================] - 46s 79ms/step - loss: 0.0434 - accuracy: 0.9842 - val_loss: 0.0463 - val_accuracy: 0.9824
Epoch 9/10
582/582 [==============================] - 45s 78ms/step - loss: 0.0421 - accuracy: 0.9849 - val_loss: 0.0455 - val_accuracy: 0.9832
Epoch 10/10
582/582 [==============================] - 45s 77ms/step - loss: 0.0414 - accuracy: 0.9850 - val_loss: 0.0451 - val_accuracy: 0.9828

Amélioration du modèle : fine tune

On ne freezer que les 100 premières couches.

base_model.trainable = True
# Let's take a look to see how many layers are in the base model
print("Number of layers in the base model: ", len(base_model.layers))

# Fine-tune from this layer onwards
fine_tune_at = 100

# Freeze all the layers before the `fine_tune_at` layer
for layer in base_model.layers[:fine_tune_at]:
  layer.trainable =  False
Number of layers in the base model:  155

Ne pas oublier de recompiler le modèle.

model.compile(loss=tf.keras.losses.BinaryCrossentropy(from_logits=True),
              optimizer = tf.keras.optimizers.RMSprop(lr=base_learning_rate/10),
              metrics=['accuracy'])

Notez que le learning rate est divisé par 10.

model.summary()
Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
mobilenetv2_1.00_160 (Model) (None, 5, 5, 1280)        2257984   
_________________________________________________________________
global_average_pooling2d (Gl (None, 1280)              0         
_________________________________________________________________
dense (Dense)                (None, 1)                 1281      
=================================================================
Total params: 2,259,265
Trainable params: 1,281
Non-trainable params: 2,257,984
fine_tune_epochs = 10
total_epochs =  initial_epochs + fine_tune_epochs

history_fine = model.fit(train_batches,
                         epochs=total_epochs,
                         initial_epoch =  history.epoch[-1],
                         validation_data=validation_batches)
Epoch 10/20
582/582 [==============================] - 45s 77ms/step - loss: 0.0404 - accuracy: 0.9857 - val_loss: 0.0451 - val_accuracy: 0.9837
Epoch 11/20
582/582 [==============================] - 46s 78ms/step - loss: 0.0403 - accuracy: 0.9858 - val_loss: 0.0450 - val_accuracy: 0.9841
Epoch 12/20
582/582 [==============================] - 44s 76ms/step - loss: 0.0403 - accuracy: 0.9859 - val_loss: 0.0450 - val_accuracy: 0.9841
Epoch 13/20
582/582 [==============================] - 45s 77ms/step - loss: 0.0401 - accuracy: 0.9859 - val_loss: 0.0449 - val_accuracy: 0.9845
Epoch 14/20
582/582 [==============================] - 45s 77ms/step - loss: 0.0400 - accuracy: 0.9860 - val_loss: 0.0449 - val_accuracy: 0.9845
Epoch 15/20
582/582 [==============================] - 45s 77ms/step - loss: 0.0400 - accuracy: 0.9860 - val_loss: 0.0449 - val_accuracy: 0.9845
Epoch 16/20
582/582 [==============================] - 45s 77ms/step - loss: 0.0399 - accuracy: 0.9860 - val_loss: 0.0448 - val_accuracy: 0.9845
Epoch 17/20
582/582 [==============================] - 45s 77ms/step - loss: 0.0398 - accuracy: 0.9860 - val_loss: 0.0448 - val_accuracy: 0.9845
Epoch 18/20
582/582 [==============================] - 44s 76ms/step - loss: 0.0398 - accuracy: 0.9862 - val_loss: 0.0448 - val_accuracy: 0.9845
Epoch 19/20
582/582 [==============================] - 44s 76ms/step - loss: 0.0397 - accuracy: 0.9861 - val_loss: 0.0447 - val_accuracy: 0.9845
Epoch 20/20
582/582 [==============================] - 44s 75ms/step - loss: 0.0396 - accuracy: 0.9861 - val_loss: 0.0447 - val_accuracy: 0.9845

On a augmenté l’accuracy à 98,45%