- 🍨 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
🚀我的环境：
- 语言环境：python 3.12.6
- 编译器：jupyter lab
- 深度学习环境：TensorFlow 2.17.0
import numpy as np
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 = "C:/Users/PC/Desktop/365-8-data"
data_dir = pathlib.Path(data_dir)
image_count = len(list(data_dir.glob('*/*')))
print("图片总数为：",image_count)
图片总数为： 3400
数据预处理
batch_size = 64
img_height = 224
img_width = 224
import tensorflow as tf
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)
Found 3400 files belonging to 2 classes.
Using 2720 files for training.
"""
关于image_dataset_from_directory()的详细介绍可以参考文章：https://mtyjkh.blog.youkuaiyun.com/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)
Found 3400 files belonging to 2 classes.
Using 680 files for validation.
class_names = train_ds.class_names
print(class_names)
['cat', 'dog']
for image_batch, labels_batch in train_ds:
print(image_batch.shape)
print(labels_batch.shape)
break
(64, 224, 224, 3)
(64,)
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")
构建VGG-16网络
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: "functional"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓ ┃ Layer (type) ┃ Output Shape ┃ Param # ┃ ┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩ │ input_layer (InputLayer) │ (None, 224, 224, 3) │ 0 │ ├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤ │ block1_conv1 (Conv2D) │ (None, 224, 224, 64) │ 1,792 │ ├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤ │ block1_conv2 (Conv2D) │ (None, 224, 224, 64) │ 36,928 │ ├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤ │ block1_pool (MaxPooling2D) │ (None, 112, 112, 64) │ 0 │ ├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤ │ block2_conv1 (Conv2D) │ (None, 112, 112, 128) │ 73,856 │ ├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤ │ block2_conv2 (Conv2D) │ (None, 112, 112, 128) │ 147,584 │ ├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤ │ block2_pool (MaxPooling2D) │ (None, 56, 56, 128) │ 0 │ ├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤ │ block3_conv1 (Conv2D) │ (None, 56, 56, 256) │ 295,168 │ ├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤ │ block3_conv2 (Conv2D) │ (None, 56, 56, 256) │ 590,080 │ ├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤ │ block3_conv3 (Conv2D) │ (None, 56, 56, 256) │ 590,080 │ ├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤ │ block3_pool (MaxPooling2D) │ (None, 28, 28, 256) │ 0 │ ├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤ │ block4_conv1 (Conv2D) │ (None, 28, 28, 512) │ 1,180,160 │ ├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤ │ block4_conv2 (Conv2D) │ (None, 28, 28, 512) │ 2,359,808 │ ├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤ │ block4_conv3 (Conv2D) │ (None, 28, 28, 512) │ 2,359,808 │ ├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤ │ block4_pool (MaxPooling2D) │ (None, 14, 14, 512) │ 0 │ ├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤ │ block5_conv1 (Conv2D) │ (None, 14, 14, 512) │ 2,359,808 │ ├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤ │ block5_conv2 (Conv2D) │ (None, 14, 14, 512) │ 2,359,808 │ ├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤ │ block5_conv3 (Conv2D) │ (None, 14, 14, 512) │ 2,359,808 │ ├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤ │ block5_pool (MaxPooling2D) │ (None, 7, 7, 512) │ 0 │ ├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤ │ flatten (Flatten) │ (None, 25088) │ 0 │ ├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤ │ fc1 (Dense) │ (None, 4096) │ 102,764,544 │ ├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤ │ fc2 (Dense) │ (None, 4096) │ 16,781,312 │ ├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤ │ predictions (Dense) │ (None, 1000) │ 4,097,000 │ └──────────────────────────────────────┴─────────────────────────────┴─────────────────┘
Total params: 138,357,544 (527.79 MB)
Trainable params: 138,357,544 (527.79 MB)
Non-trainable params: 0 (0.00 B)
编译
model.compile(optimizer="adam",
loss ='sparse_categorical_crossentropy',
metrics =['accuracy'])
训练模型
from tqdm import tqdm
import tensorflow.keras.backend as K
import numpy as np
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
model.optimizer_learning_rate=lr
train_loss = []
train_accuracy = []
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 的同学，
可以看看我的这篇文章：https://www.yuque.com/mingtian-fkmxf/hv4lcq/ztt4gy
"""
# 这里生成的是每一个batch的acc与loss
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))
poch 1/10: 100%|████| 43/43 [33:41<00:00, 47.00s/it, train_loss=3.7940, train_acc=0.4926, lr=0.001]
开始验证！
poch 1/10: 100%|██████████████████| 11/11 [01:46<00:00, 9.64s/it, val_loss=3.1760, val_acc=0.4959]
结束验证！
验证loss为：3.4242
验证准确率为：0.4968
poch 2/10: 100%|████| 43/43 [35:36<00:00, 49.69s/it, train_loss=2.0747, train_acc=0.5010, lr=0.001]
开始验证！
poch 2/10: 100%|██████████████████| 11/11 [01:47<00:00, 9.80s/it, val_loss=1.9366, val_acc=0.5018]
结束验证！
验证loss为：1.9947
验证准确率为：0.5025
poch 3/10: 100%|████| 43/43 [35:48<00:00, 49.96s/it, train_loss=1.5831, train_acc=0.4987, lr=0.001]
开始验证！
poch 3/10: 100%|██████████████████| 11/11 [01:48<00:00, 9.87s/it, val_loss=1.5238, val_acc=0.4994]
结束验证！
验证loss为：1.5491
验证准确率为：0.4998
poch 4/10: 100%|████| 43/43 [35:48<00:00, 49.97s/it, train_loss=1.3494, train_acc=0.4974, lr=0.001]
开始验证！
poch 4/10: 100%|██████████████████| 11/11 [01:48<00:00, 9.88s/it, val_loss=1.3166, val_acc=0.4979]
结束验证！
验证loss为：1.3307
验证准确率为：0.4982
poch 5/10: 100%|████| 43/43 [35:50<00:00, 50.02s/it, train_loss=1.2133, train_acc=0.4964, lr=0.001]
开始验证！
poch 5/10: 100%|██████████████████| 11/11 [01:48<00:00, 9.85s/it, val_loss=1.1927, val_acc=0.4962]
结束验证！
验证loss为：1.2017
验证准确率为：0.4959
poch 6/10: 100%|████| 43/43 [35:54<00:00, 50.10s/it, train_loss=1.1245, train_acc=0.4961, lr=0.001]
开始验证！
poch 6/10: 100%|██████████████████| 11/11 [01:48<00:00, 9.89s/it, val_loss=1.1102, val_acc=0.4960]
结束验证！
验证loss为：1.1164
验证准确率为：0.4957
poch 7/10: 100%|████| 43/43 [35:55<00:00, 50.13s/it, train_loss=1.0617, train_acc=0.4958, lr=0.001]
开始验证！
poch 7/10: 100%|██████████████████| 11/11 [01:49<00:00, 9.93s/it, val_loss=1.0514, val_acc=0.4956]
结束验证！
验证loss为：1.0559
验证准确率为：0.4954
poch 8/10: 100%|████| 43/43 [35:49<00:00, 50.00s/it, train_loss=1.0151, train_acc=0.4975, lr=0.001]
开始验证！
poch 8/10: 100%|██████████████████| 11/11 [01:49<00:00, 9.98s/it, val_loss=1.0072, val_acc=0.4974]
结束验证！
验证loss为：1.0106
验证准确率为：0.4972
poch 9/10: 100%|████| 43/43 [35:58<00:00, 50.20s/it, train_loss=0.9790, train_acc=0.4977, lr=0.001]
开始验证！
poch 9/10: 100%|██████████████████| 11/11 [01:48<00:00, 9.89s/it, val_loss=0.9727, val_acc=0.4975]
结束验证！
验证loss为：0.9755
验证准确率为：0.4974
poch 10/10: 100%|███| 43/43 [35:53<00:00, 50.09s/it, train_loss=0.9502, train_acc=0.4966, lr=0.001]
开始验证！
Epoch 10/10: 100%|█████████████████| 11/11 [01:49<00:00, 9.91s/it, val_loss=0.9451, val_acc=0.4965]
结束验证！
验证loss为：0.9474
验证准确率为：0.4963
epochs_range = range(epochs)
plt.figure(figsize=(14, 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")
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 635ms/step
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 419ms/step
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 409ms/step
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 413ms/step
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 514ms/step
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 400ms/step
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 434ms/step
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 388ms/step
总结
将K.set_value(model.optimizer.lr, lr)的报错，改为model.optimizer_learning_rate=lr
“lr”: model.optimizer.learning_rate.numpy()})
扫一扫
145
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
