（深度学习记录）：第T8周：猫狗识别

我的环境

• 电脑系统：Windows 11
• 编译器：kaggle在线编译
• 深度学习环境：Tensorflow

代码及结果

import tensorflow as tf

gpus = tf.config.list_physical_devices("GPU")
import matplotlib.pyplot as plt
# 支持中文
plt.rcParams['font.sans-serif'] = ['SimHei']  # 用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False  # 用来正常显示负号

import os,PIL,pathlib

#隐藏警告
import warnings
warnings.filterwarnings('ignore')

data_dir = "/kaggle/input/t8data"
data_dir = pathlib.Path(data_dir)

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

print("图片总数为：",image_count)

batch_size = 8
img_height = 224
img_width = 224
train_ds = tf.keras.preprocessing.image_dataset_from_directory(
    data_dir,
    validation_split=0.2,
    subset="training",
    seed=12,
    image_size=(img_height, img_width),
    batch_size=batch_size)

val_ds = tf.keras.preprocessing.image_dataset_from_directory(
    data_dir,
    validation_split=0.2,
    subset="validation",
    seed=12,
    image_size=(img_height, img_width),
    batch_size=batch_size)

class_names = train_ds.class_names
print(class_names)

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

AUTOTUNE = tf.data.AUTOTUNE

def preprocess_image(image,label):
    return (image/255.0,label)

# 归一化处理
train_ds = train_ds.map(preprocess_image, num_parallel_calls=AUTOTUNE)
val_ds   = val_ds.map(preprocess_image, num_parallel_calls=AUTOTUNE)

train_ds = train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE)
val_ds   = val_ds.cache().prefetch(buffer_size=AUTOTUNE)
plt.figure(figsize=(15, 10))  # 图形的宽为15高为10

for images, labels in train_ds.take(1):
    for i in range(8):
        
        ax = plt.subplot(5, 8, i + 1) 
        plt.imshow(images[i])
        plt.title(class_names[labels[i]])
        
        plt.axis("off")

from tensorflow.keras import layers, models, Input
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Dense, Flatten, Dropout

def VGG16(nb_classes, input_shape):
    input_tensor = Input(shape=input_shape)
    # 1st block
    x = Conv2D(64, (3,3), activation='relu', padding='same',name='block1_conv1')(input_tensor)
    x = Conv2D(64, (3,3), activation='relu', padding='same',name='block1_conv2')(x)
    x = MaxPooling2D((2,2), strides=(2,2), name = 'block1_pool')(x)
    # 2nd block
    x = Conv2D(128, (3,3), activation='relu', padding='same',name='block2_conv1')(x)
    x = Conv2D(128, (3,3), activation='relu', padding='same',name='block2_conv2')(x)
    x = MaxPooling2D((2,2), strides=(2,2), name = 'block2_pool')(x)
    # 3rd block
    x = Conv2D(256, (3,3), activation='relu', padding='same',name='block3_conv1')(x)
    x = Conv2D(256, (3,3), activation='relu', padding='same',name='block3_conv2')(x)
    x = Conv2D(256, (3,3), activation='relu', padding='same',name='block3_conv3')(x)
    x = MaxPooling2D((2,2), strides=(2,2), name = 'block3_pool')(x)
    # 4th block
    x = Conv2D(512, (3,3), activation='relu', padding='same',name='block4_conv1')(x)
    x = Conv2D(512, (3,3), activation='relu', padding='same',name='block4_conv2')(x)
    x = Conv2D(512, (3,3), activation='relu', padding='same',name='block4_conv3')(x)
    x = MaxPooling2D((2,2), strides=(2,2), name = 'block4_pool')(x)
    # 5th block
    x = Conv2D(512, (3,3), activation='relu', padding='same',name='block5_conv1')(x)
    x = Conv2D(512, (3,3), activation='relu', padding='same',name='block5_conv2')(x)
    x = Conv2D(512, (3,3), activation='relu', padding='same',name='block5_conv3')(x)
    x = MaxPooling2D((2,2), strides=(2,2), name = 'block5_pool')(x)
    # full connection
    x = Flatten()(x)
    x = Dense(4096, activation='relu',  name='fc1')(x)
    x = Dense(4096, activation='relu', name='fc2')(x)
    output_tensor = Dense(nb_classes, activation='softmax', name='predictions')(x)

    model = Model(input_tensor, output_tensor)
    return model

model=VGG16(1000, (img_width, img_height, 3))
model.summary()

model.compile(optimizer="adam",
              loss     ='sparse_categorical_crossentropy',
              metrics  =['accuracy'])

from tqdm import tqdm
import tensorflow.keras.backend as K
import numpy as np

epochs = 5
lr = 1e-4

# 记录训练数据，方便后面的分析
history_train_loss     = []
history_train_accuracy = []
history_val_loss       = []
history_val_accuracy   = []

for epoch in range(epochs):
    train_total = len(train_ds)
    val_total   = len(val_ds)
    
    with tqdm(total=train_total, desc=f'Epoch {epoch + 1}/{epochs}', mininterval=1, ncols=100) as pbar:
        
        lr *= 0.92  # 更新学习率
        model.optimizer.learning_rate.assign(lr)

        train_loss     = []
        train_accuracy = []
        for image, label in train_ds:   
            history = model.train_on_batch(image, label)
            
            train_loss.append(history[0])
            train_accuracy.append(history[1])
            
            pbar.set_postfix({"train_loss": "%.4f" % history[0],
                              "train_acc": "%.4f" % history[1],
                              "lr": model.optimizer.learning_rate.numpy()})
            pbar.update(1)
            
        history_train_loss.append(np.mean(train_loss))
        history_train_accuracy.append(np.mean(train_accuracy))
            
    print('开始验证！')
    
    with tqdm(total=val_total, desc=f'Epoch {epoch + 1}/{epochs}', mininterval=0.3, ncols=100) as pbar:

        val_loss     = []
        val_accuracy = []
        for image, label in val_ds:      
            # 这里生成的是每一个batch的acc与loss
            history = model.test_on_batch(image, label)
            
            val_loss.append(history[0])
            val_accuracy.append(history[1])
            
            pbar.set_postfix({"val_loss": "%.4f" % history[0],
                              "val_acc": "%.4f" % history[1]})
            pbar.update(1)
        history_val_loss.append(np.mean(val_loss))
        history_val_accuracy.append(np.mean(val_accuracy))
            
    print('结束验证！')
    print("验证loss为：%.4f" % np.mean(val_loss))
    print("验证准确率为：%.4f" % np.mean(val_accuracy))

epochs_range = range(epochs)

plt.figure(figsize=(12, 4))
plt.subplot(1, 2, 1)

plt.plot(epochs_range, history_train_accuracy, label='Training Accuracy')
plt.plot(epochs_range, history_val_accuracy, label='Validation Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')

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

import numpy as np

# 采用加载的模型（new_model）来看预测结果
plt.figure(figsize=(18, 3))  # 图形的宽为18高为5
plt.suptitle("预测结果展示")

for images, labels in val_ds.take(1):
    for i in range(8):
        ax = plt.subplot(1,8, i + 1)  
        
        # 显示图片
        plt.imshow(images[i].numpy())
        
        # 需要给图片增加一个维度
        img_array = tf.expand_dims(images[i], 0) 
        
        # 使用模型预测图片中的人物
        predictions = model.predict(img_array)
        plt.title(class_names[np.argmax(predictions)])

        plt.axis("off")

个人总结：在kaggle上跑代码，他是不认lr的，只能把所有的lr改成learning_rate.有一句话一直编译不过去，如图，最后改成了model.optimizer.learning_rate.assign(lr)，就可以啦。

kaggle上的RAM给的不是很充足，一般运行到epoch=7的时候，就会因为RAM太满，停止，所有这次的epochs设成了5进行训练。当epochs=10的时候如图

错误代码已经改正，将每次循环前进度数组置空。