Tensorflow入门实战 T08-Vgg16网络进行猫狗识别

时间：2024-07-12 22:47:51

目录

1、前言

2、代码

3、运行结果

4、反思

  • 本文为????365天深度学习训练营 中的学习记录博客
  • ???? 原作者：K同学啊 | 接辅导、项目定制

1、前言

本周学习内容为，采用自己设置的vgg-16网络进行猫狗识别，并非官网提供的vgg16接口。

本周的代码运行，设置了新的运行展示进度条，更换不同风格；其他的模块和之前的很类似，没有很大的改动。主要是学会使用tensorflow完成先关实现。

2、代码

import tensorflow as tf

# 设置GPU
gpus = tf.config.list_physical_devices("GPU")

if gpus:
    tf.config.experimental.set_memory_growth(gpus[0], True)  #设置GPU显存用量按需使用
    tf.config.set_visible_devices([gpus[0]],"GPU")

# 打印显卡信息，确认GPU可用
print(gpus)

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 = "/Users/MsLiang/Documents/mySelf_project/pythonProject_pytorch/learn_demo/P_model/p08_v5_C3/data"
data_dir = pathlib.Path(data_dir)

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

print("图片总数为：",image_count)


# 加载数据
batch_size = 8
img_height = 224
img_width = 224

"""
关于image_dataset_from_directory()的详细介绍可以参考文章：https://mtyjkh.blog.****.net/article/details/117018789
"""
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)

"""
关于image_dataset_from_directory()的详细介绍可以参考文章：https://mtyjkh.blog.****.net/article/details/117018789
"""
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 keras.backend as K

epochs = 10
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)

    """
    total：预期的迭代数目
    ncols：控制进度条宽度
    mininterval：进度更新最小间隔，以秒为单位（默认值：0.1）
    """
    with tqdm(total=train_total, desc=f'Epoch {epoch + 1}/{epochs}', mininterval=1, ncols=100) as pbar:

        lr = lr * 0.92
        K.set_value(model.optimizer.lr, lr)

        for image, label in train_ds:
            """
            训练模型，简单理解train_on_batch就是：它是比model.fit()更高级的一个用法

            想详细了解 train_on_batch ，
            可以看看这篇文章：https://www.yuque.com/mingtian-fkmxf/hv4lcq/ztt4gy
            """
            history = model.train_on_batch(image, label)

            train_loss = history[0]
            train_accuracy = history[1]

            pbar.set_postfix({"loss": "%.4f" % train_loss,
                              "accuracy": "%.4f" % train_accuracy,
                              "lr": K.get_value(model.optimizer.lr)})
            pbar.update(1)
        history_train_loss.append(train_loss)
        history_train_accuracy.append(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:

        for image, label in val_ds:
            history = model.test_on_batch(image, label)

            val_loss = history[0]
            val_accuracy = history[1]

            pbar.set_postfix({"loss": "%.4f" % val_loss,
                              "accuracy": "%.4f" % val_accuracy})
            pbar.update(1)
        history_val_loss.append(val_loss)
        history_val_accuracy.append(val_accuracy)

    print('结束验证！')
    print("验证loss为：%.4f" % val_loss)
    print("验证准确率为：%.4f" % val_accuracy)

# 模型评估
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()

# 预测
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")

3、运行结果

预测结果展示：

4、反思

本周学习内容，让我更加了解了vgg16的网络模型结构；加深对于vgg16网络的使用，了解如何去搭建、修改网络结构等；可以将此搭建逻辑应用到自己的网络模型里面，确保shape是相互匹配的。

最近放暑假啦，回家继续学习咯；暑假暂定的目标是写完小论文初稿。加油咯！！！！

相关文章