第5周 运动鞋识别

• 本文为365天深度学习训练营 中的学习记录博客
• 参考文章：365天深度学习训练营-第5周：运动鞋品牌识别（训练营内部成员可读）
• 原作者：K同学啊

from tensorflow       import keras
from tensorflow.keras import layers,models
import os, PIL, pathlib
import matplotlib.pyplot as plt
import tensorflow        as tf

data_dir = "D://jupyter notebook/46-data/"

data_dir = pathlib.Path(data_dir)

image_count = len(list(data_dir.glob('*/*/*.jpg')))

print("图片总数为：",image_count)

图片总数为： 578

roses = list(data_dir.glob('train/nike/*.jpg'))
PIL.Image.open(str(roses[0]))

batch_size = 32
img_height = 224
img_width = 224

train_ds = tf.keras.preprocessing.image_dataset_from_directory(
    "D://jupyter notebook/46-data/train",
    seed=123,
    image_size=(img_height, img_width),
    batch_size=batch_size)

Found 502 files belonging to 2 classes.

val_ds = tf.keras.preprocessing.image_dataset_from_directory(
    "D://jupyter notebook/46-data/test",
    seed=123,
    image_size=(img_height, img_width),
    batch_size=batch_size)

Found 76 files belonging to 2 classes.

class_names = train_ds.class_names
print(class_names)

['adidas', 'nike']

plt.figure(figsize=(20, 10))

for images, labels in train_ds.take(1):
    for i in range(20):
        ax = plt.subplot(5, 10, i + 1)

        plt.imshow(images[i].numpy().astype("uint8"))
        plt.title(class_names[labels[i]])
        
        plt.axis("off")

for image_batch, labels_batch in train_ds:
    print(image_batch.shape)
    print(labels_batch.shape)
    break

(32, 224, 224, 3)
(32,)

AUTOTUNE = tf.data.AUTOTUNE

train_ds = train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE)
val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)

model = models.Sequential([
    layers.experimental.preprocessing.Rescaling(1./255, input_shape=(img_height, img_width, 3)),
    
    layers.Conv2D(16, (3, 3), activation='relu', input_shape=(img_height, img_width, 3)), # 卷积层1，卷积核3*3  
    layers.AveragePooling2D((2, 2)),               # 池化层1，2*2采样
    layers.Conv2D(32, (3, 3), activation='relu'),  # 卷积层2，卷积核3*3
    layers.AveragePooling2D((2, 2)),               # 池化层2，2*2采样
    layers.Dropout(0.3),  
    layers.Conv2D(64, (3, 3), activation='relu'),  # 卷积层3，卷积核3*3
    layers.Dropout(0.3),  
    
    layers.Flatten(),                       # Flatten层，连接卷积层与全连接层
    layers.Dense(128, activation='relu'),   # 全连接层，特征进一步提取
    layers.Dense(len(class_names))               # 输出层，输出预期结果
])

model.summary()  # 打印网络结构

Model: "sequential"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 rescaling (Rescaling)       (None, 224, 224, 3)       0         
                                                                 
 conv2d (Conv2D)             (None, 222, 222, 16)      448       
                                                                 
 average_pooling2d (AverageP  (None, 111, 111, 16)     0         
 ooling2D)                                                       
                                                                 
 conv2d_1 (Conv2D)           (None, 109, 109, 32)      4640      
                                                                 
 average_pooling2d_1 (Averag  (None, 54, 54, 32)       0         
 ePooling2D)                                                     
                                                                 
 dropout (Dropout)           (None, 54, 54, 32)        0         
                                                                 
 conv2d_2 (Conv2D)           (None, 52, 52, 64)        18496     
                                                                 
 dropout_1 (Dropout)         (None, 52, 52, 64)        0         
                                                                 
 flatten (Flatten)           (None, 173056)            0         
                                                                 
 dense (Dense)               (None, 128)               22151296  
                                                                 
 dense_1 (Dense)             (None, 2)                 258       
                                                                 
=================================================================
Total params: 22,175,138
Trainable params: 22,175,138
Non-trainable params: 0
_________________________________________________________________

# 设置初始学习率
initial_learning_rate = 0.1

lr_schedule = tf.keras.optimizers.schedules.ExponentialDecay(
        initial_learning_rate, 
        decay_steps=10,      # 敲黑板！！！这里是指 steps，不是指epochs
        decay_rate=0.92,     # lr经过一次衰减就会变成 decay_rate*lr
        staircase=True)

# 将指数衰减学习率送入优化器
optimizer = tf.keras.optimizers.Adam(learning_rate=lr_schedule)

model.compile(optimizer=optimizer,
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])

from tensorflow.keras.callbacks import ModelCheckpoint, EarlyStopping

epochs = 50

# 保存最佳模型参数
checkpointer = ModelCheckpoint('best_model.h5',
                                monitor='val_accuracy',
                                verbose=1,
                                save_best_only=True,
                                save_weights_only=True)

# 设置早停
earlystopper = EarlyStopping(monitor='val_accuracy', 
                             min_delta=0.001,
                             patience=20, 
                             verbose=1)

history = model.fit(train_ds,
                    validation_data=val_ds,
                    epochs=epochs,
                    callbacks=[checkpointer, earlystopper])

Epoch 1/50
16/16 [==============================] - ETA: 0s - loss: 157536.0000 - accuracy: 0.5299
Epoch 1: val_accuracy improved from -inf to 0.51316, saving model to best_model.h5
16/16 [==============================] - 23s 1s/step - loss: 157536.0000 - accuracy: 0.5299 - val_loss: 1.0883 - val_accuracy: 0.5132
Epoch 2/50
16/16 [==============================] - ETA: 0s - loss: 1.4099 - accuracy: 0.5120
Epoch 2: val_accuracy did not improve from 0.51316
16/16 [==============================] - 13s 807ms/step - loss: 1.4099 - accuracy: 0.5120 - val_loss: 0.7797 - val_accuracy: 0.5000
Epoch 3/50
16/16 [==============================] - ETA: 0s - loss: 0.7208 - accuracy: 0.5000
Epoch 3: val_accuracy did not improve from 0.51316
16/16 [==============================] - 13s 805ms/step - loss: 0.7208 - accuracy: 0.5000 - val_loss: 0.6932 - val_accuracy: 0.5000
Epoch 4/50
16/16 [==============================] - ETA: 0s - loss: 0.6935 - accuracy: 0.5000
Epoch 4: val_accuracy did not improve from 0.51316
16/16 [==============================] - 13s 818ms/step - loss: 0.6935 - accuracy: 0.5000 - val_loss: 0.6952 - val_accuracy: 0.5000
Epoch 5/50
16/16 [==============================] - ETA: 0s - loss: 0.6964 - accuracy: 0.4721
Epoch 5: val_accuracy did not improve from 0.51316
16/16 [==============================] - 13s 809ms/step - loss: 0.6964 - accuracy: 0.4721 - val_loss: 0.6932 - val_accuracy: 0.5000
Epoch 6/50
16/16 [==============================] - ETA: 0s - loss: 0.6935 - accuracy: 0.4442
Epoch 6: val_accuracy did not improve from 0.51316
16/16 [==============================] - 13s 849ms/step - loss: 0.6935 - accuracy: 0.4442 - val_loss: 0.6932 - val_accuracy: 0.5000
Epoch 7/50
16/16 [==============================] - ETA: 0s - loss: 0.6937 - accuracy: 0.5000
Epoch 7: val_accuracy did not improve from 0.51316
16/16 [==============================] - 13s 831ms/step - loss: 0.6937 - accuracy: 0.5000 - val_loss: 0.6932 - val_accuracy: 0.5000
Epoch 8/50
16/16 [==============================] - ETA: 0s - loss: 0.6936 - accuracy: 0.4920
Epoch 8: val_accuracy did not improve from 0.51316
16/16 [==============================] - 14s 869ms/step - loss: 0.6936 - accuracy: 0.4920 - val_loss: 0.6935 - val_accuracy: 0.5000
Epoch 9/50
16/16 [==============================] - ETA: 0s - loss: 0.6938 - accuracy: 0.5000
Epoch 9: val_accuracy did not improve from 0.51316
16/16 [==============================] - 13s 824ms/step - loss: 0.6938 - accuracy: 0.5000 - val_loss: 0.6932 - val_accuracy: 0.5000
Epoch 10/50
16/16 [==============================] - ETA: 0s - loss: 0.6934 - accuracy: 0.5000
Epoch 10: val_accuracy did not improve from 0.51316
16/16 [==============================] - 13s 816ms/step - loss: 0.6934 - accuracy: 0.5000 - val_loss: 0.6931 - val_accuracy: 0.5000
Epoch 11/50
16/16 [==============================] - ETA: 0s - loss: 0.6934 - accuracy: 0.4801
Epoch 11: val_accuracy did not improve from 0.51316
16/16 [==============================] - 13s 819ms/step - loss: 0.6934 - accuracy: 0.4801 - val_loss: 0.6932 - val_accuracy: 0.5000
Epoch 12/50
16/16 [==============================] - ETA: 0s - loss: 0.6934 - accuracy: 0.4801
Epoch 12: val_accuracy did not improve from 0.51316
16/16 [==============================] - 13s 821ms/step - loss: 0.6934 - accuracy: 0.4801 - val_loss: 0.6932 - val_accuracy: 0.5000
Epoch 13/50
16/16 [==============================] - ETA: 0s - loss: 0.6945 - accuracy: 0.5000
Epoch 13: val_accuracy did not improve from 0.51316
16/16 [==============================] - 13s 816ms/step - loss: 0.6945 - accuracy: 0.5000 - val_loss: 0.6935 - val_accuracy: 0.5000
Epoch 14/50
16/16 [==============================] - ETA: 0s - loss: 0.6933 - accuracy: 0.4841
Epoch 14: val_accuracy did not improve from 0.51316
16/16 [==============================] - 14s 839ms/step - loss: 0.6933 - accuracy: 0.4841 - val_loss: 0.6932 - val_accuracy: 0.5000
Epoch 15/50
16/16 [==============================] - ETA: 0s - loss: 0.6935 - accuracy: 0.5000
Epoch 15: val_accuracy did not improve from 0.51316
16/16 [==============================] - 13s 821ms/step - loss: 0.6935 - accuracy: 0.5000 - val_loss: 0.6932 - val_accuracy: 0.5000
Epoch 16/50
16/16 [==============================] - ETA: 0s - loss: 0.6932 - accuracy: 0.5000
Epoch 16: val_accuracy did not improve from 0.51316
16/16 [==============================] - 13s 805ms/step - loss: 0.6932 - accuracy: 0.5000 - val_loss: 0.6932 - val_accuracy: 0.5000
Epoch 17/50
16/16 [==============================] - ETA: 0s - loss: 0.6933 - accuracy: 0.5000
Epoch 17: val_accuracy did not improve from 0.51316
16/16 [==============================] - 13s 828ms/step - loss: 0.6933 - accuracy: 0.5000 - val_loss: 0.6931 - val_accuracy: 0.5000
Epoch 18/50
16/16 [==============================] - ETA: 0s - loss: 0.6932 - accuracy: 0.4960
Epoch 18: val_accuracy did not improve from 0.51316
16/16 [==============================] - 13s 814ms/step - loss: 0.6932 - accuracy: 0.4960 - val_loss: 0.6932 - val_accuracy: 0.5000
Epoch 19/50
16/16 [==============================] - ETA: 0s - loss: 0.6933 - accuracy: 0.5000
Epoch 19: val_accuracy did not improve from 0.51316
16/16 [==============================] - 14s 904ms/step - loss: 0.6933 - accuracy: 0.5000 - val_loss: 0.6931 - val_accuracy: 0.5000
Epoch 20/50
16/16 [==============================] - ETA: 0s - loss: 0.6935 - accuracy: 0.5000
Epoch 20: val_accuracy did not improve from 0.51316
16/16 [==============================] - 13s 819ms/step - loss: 0.6935 - accuracy: 0.5000 - val_loss: 0.6932 - val_accuracy: 0.5000
Epoch 21/50
16/16 [==============================] - ETA: 0s - loss: 0.6932 - accuracy: 0.5000
Epoch 21: val_accuracy did not improve from 0.51316
16/16 [==============================] - 13s 820ms/step - loss: 0.6932 - accuracy: 0.5000 - val_loss: 0.6932 - val_accuracy: 0.5000
Epoch 21: early stopping

acc = history.history['accuracy']
val_acc = history.history['val_accuracy']

loss = history.history['loss']
val_loss = history.history['val_loss']

epochs_range = range(len(loss))

plt.figure(figsize=(12, 4))
plt.subplot(1, 2, 1)
plt.plot(epochs_range, acc, label='Training Accuracy')
plt.plot(epochs_range, val_acc, label='Validation Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')

plt.subplot(1, 2, 2)
plt.plot(epochs_range, loss, label='Training Loss')
plt.plot(epochs_range, val_loss, label='Validation Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()

# 加载效果最好的模型权重
model.load_weights('best_model.h5')

from PIL import Image
import numpy as np

# img = Image.open("D://jupyter notebook/45-data/Monkeypox/M06_01_04.jpg")  #这里选择你需要预测的图片
img = Image.open("D://jupyter notebook/46-data/test/nike/1.jpg")  #这里选择你需要预测的图片
num_img = np.asarray(img)
image = tf.image.resize(num_img, [img_height, img_width])

img_array = tf.expand_dims(image, 0) #/255.0  # 记得做归一化处理（与训练集处理方式保持一致）

predictions = model.predict(img_array) # 这里选用你已经训练好的模型
print("预测结果为：",class_names[np.argmax(predictions)])

1/1 [==============================] - 0s 311ms/step
预测结果为： nike