【TF NOTE】T8猫狗识别

最新推荐文章于 2024-07-19 15:44:38 发布

Charlotte688

最新推荐文章于 2024-07-19 15:44:38 发布

阅读量267

点赞数 5

文章标签： tensorflow 深度学习

本文链接：https://blog.csdn.net/Charlotte688/article/details/139641247

版权

DL学习笔记 T8
【TF NOTE】T8 猫狗识别

文章目录

前言
一、设置GPU
二、使用步骤
总结

前言

🍨 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

一、设置GPU

import tensorflow as tf
gpus = tf.config.list_physical_devices("GPU")
if gpus:
    tf.config.experimental.set_memory_growth(gpus[0],True)
    tf.config.set_visible_devices(gpus[0],"GPU")

print(gpus)

输出
在这里插入图片描述

二、使用步骤

1.导入数据

#导入数据
import matplotlib.pyplot as plt

plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False

import os, PIL, pathlib

import warnings
warnings.filterwarnings('ignore')
data_dir = "D:/BaiduNetdiskDownload/T8"
data_dir = pathlib.Path(data_dir)

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

print("图片总数为：",image_count)

输出
在这里插入图片描述

2.加载数据

#加载数据
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)

输出
在这里插入图片描述

3.归一化

#归一化
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)

4.可视化数据

#可视化数据
plt.figure(figsize=(15,10))

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")

输出
在这里插入图片描述

5.建立模型

VGG模型
我感觉bug是这里的model = VGG16(1000, (img_width, img_height, 3))，这里1000是nb_classes，应该只有两类，我这里改成model = VGG16(2, (img_width, img_height, 3))

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)

    #block1
    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)

    #block2
    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)

    #block3
    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)

    #block4
    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)

    #block5
    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)

    #全连接
    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(2, (img_width, img_height, 3))
model.summary()

输出模型简介

Model: "model"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 input_1 (InputLayer)        [(None, 224, 224, 3)]     0         
                                                                 
 block1_conv1 (Conv2D)       (None, 224, 224, 64)      1792      
                                                                 
 block1_conv2 (Conv2D)       (None, 224, 224, 64)      36928     
                                                                 
 block1_pool (MaxPooling2D)  (None, 112, 112, 64)      0         
                                                                 
 block2_conv1 (Conv2D)       (None, 112, 112, 128)     73856     
                                                                 
 block2_conv2 (Conv2D)       (None, 112, 112, 128)     147584    
                                                                 
 block2_pool (MaxPooling2D)  (None, 56, 56, 128)       0         
                                                                 
 block3_conv1 (Conv2D)       (None, 56, 56, 256)       295168    
                                                                 
 block3_conv2 (Conv2D)       (None, 56, 56, 256)       590080    
                                                                 
 block3_conv3 (Conv2D)       (None, 56, 56, 256)       590080    
                                                                 
 block3_pool (MaxPooling2D)  (None, 28, 28, 256)       0         
                                                                 
 block4_conv1 (Conv2D)       (None, 28, 28, 512)       1180160   
                                                                 
 block4_conv2 (Conv2D)       (None, 28, 28, 512)       2359808   
                                                                 
 block4_conv3 (Conv2D)       (None, 28, 28, 512)       2359808   
                                                                 
 block4_pool (MaxPooling2D)  (None, 14, 14, 512)       0         
                                                                 
 block5_conv1 (Conv2D)       (None, 14, 14, 512)       2359808   
                                                                 
 block5_conv2 (Conv2D)       (None, 14, 14, 512)       2359808   
                                                                 
 block5_conv3 (Conv2D)       (None, 14, 14, 512)       2359808   
                                                                 
 block5_pool (MaxPooling2D)  (None, 7, 7, 512)         0         
                                                                 
 flatten (Flatten)           (None, 25088)             0         
                                                                 
 fc1 (Dense)                 (None, 4096)              102764544 
                                                                 
 fc2 (Dense)                 (None, 4096)              16781312  
                                                                 
 predictions (Dense)         (None, 2)                 8194      
                                                                 
=================================================================
Total params: 134,268,738
Trainable params: 134,268,738
Non-trainable params: 0
_________________________________________________________________

6.编译模型

#编译模型
model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])

7.训练模型

改用model.train_on_batch方法训练模型

#训练模型
from tqdm import tqdm
import tensorflow.keras.backend as K

epochs = 10
lr = 1e-4

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

        for image, label in train_ds:
            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)

8.评估模型

#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()

输出
这遍跑的指标特别好，其他跑的就很拉跨
在这里插入图片描述

9.预测

#预测
import numpy as np
plt.figure(figsize=(18,3))
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)

        plt.imshow(images[i].numpy())

        img_array = tf.expand_dims(images[i],0)

        predictions = model.predict(img_array)
        plt.title(class_names[np.argmax(predictions)])

        plt.axis("off")