- 文为「365天深度学习训练营」内部文章
- 参考本文所写文章，请在文章开头带上「🔗 声明」
import tensorflow as tf
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 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 = "E:/T3/365-8-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
batch_size = 64
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.youkuaiyun.com/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)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")
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)
model.compile(optimizer="adam",
loss ='sparse_categorical_crossentropy',
metrics =['accuracy'])from tqdm import tqdm
import tensorflow.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
model.optimizer.learning_rate.assign(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))Epoch 1/10: 100%|███| 43/43 [07:03<00:00, 9.86s/it, train_loss=1.5739, train_acc=0.4752, lr=9.2e-5]
开始验证！
Epoch 1/10: 100%|██████████████████| 11/11 [00:30<00:00, 2.79s/it, val_loss=1.4039, val_acc=0.4818]
结束验证！ 验证loss为：1.4716 验证准确率为：0.4813
Epoch 2/10: 100%|██| 43/43 [07:42<00:00, 10.75s/it, train_loss=1.0875, train_acc=0.5082, lr=8.46e-5]
开始验证！
Epoch 2/10: 100%|██████████████████| 11/11 [00:31<00:00, 2.85s/it, val_loss=1.0451, val_acc=0.5223]
结束验证！ 验证loss为：1.0630 验证准确率为：0.5157
Epoch 3/10: 100%|██| 43/43 [07:50<00:00, 10.94s/it, train_loss=0.9377, train_acc=0.5479, lr=7.79e-5]
开始验证！
Epoch 3/10: 100%|██████████████████| 11/11 [00:32<00:00, 2.94s/it, val_loss=0.9184, val_acc=0.5582]
结束验证！ 验证loss为：0.9267 验证准确率为：0.5532
Epoch 4/10: 100%|██| 43/43 [07:46<00:00, 10.84s/it, train_loss=0.8519, train_acc=0.5814, lr=7.16e-5]
开始验证！
Epoch 4/10: 100%|██████████████████| 11/11 [00:34<00:00, 3.10s/it, val_loss=0.8373, val_acc=0.5876]
结束验证！ 验证loss为：0.8435 验证准确率为：0.5850
Epoch 5/10: 100%|██| 43/43 [07:51<00:00, 10.96s/it, train_loss=0.7650, train_acc=0.6249, lr=6.59e-5]
开始验证！
Epoch 5/10: 100%|██████████████████| 11/11 [00:34<00:00, 3.11s/it, val_loss=0.7473, val_acc=0.6348]
结束验证！ 验证loss为：0.7549 验证准确率为：0.6308
Epoch 6/10: 100%|██| 43/43 [07:57<00:00, 11.10s/it, train_loss=0.6646, train_acc=0.6772, lr=6.06e-5]
开始验证！
Epoch 6/10: 100%|██████████████████| 11/11 [00:35<00:00, 3.19s/it, val_loss=0.6456, val_acc=0.6870]
结束验证！ 验证loss为：0.6536 验证准确率为：0.6827
Epoch 7/10: 100%|██| 43/43 [08:10<00:00, 11.40s/it, train_loss=0.5803, train_acc=0.7202, lr=5.58e-5]
开始验证！
Epoch 7/10: 100%|██████████████████| 11/11 [00:31<00:00, 2.90s/it, val_loss=0.5656, val_acc=0.7276]
结束验证！ 验证loss为：0.5718 验证准确率为：0.7244
Epoch 8/10: 100%|██| 43/43 [07:53<00:00, 11.01s/it, train_loss=0.5129, train_acc=0.7536, lr=5.13e-5]
开始验证！
Epoch 8/10: 100%|██████████████████| 11/11 [00:32<00:00, 2.97s/it, val_loss=0.5016, val_acc=0.7594]
结束验证！ 验证loss为：0.5065 验证准确率为：0.7569
Epoch 9/10: 100%|██| 43/43 [07:49<00:00, 10.93s/it, train_loss=0.4592, train_acc=0.7802, lr=4.72e-5]
开始验证！
Epoch 9/10: 100%|██████████████████| 11/11 [00:33<00:00, 3.02s/it, val_loss=0.4500, val_acc=0.7847]
结束验证！ 验证loss为：0.4539 验证准确率为：0.7827
Epoch 10/10: 100%|█| 43/43 [07:46<00:00, 10.86s/it, train_loss=0.4162, train_acc=0.8014, lr=4.34e-5]
开始验证！
Epoch 10/10: 100%|█████████████████| 11/11 [00:34<00:00, 3.16s/it, val_loss=0.4094, val_acc=0.8049]
结束验证！ 验证loss为：0.4124 验证准确率为：0.8034
from datetime import datetime
current_time = datetime.now() # 获取当前时间
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.xlabel(current_time) # 打卡请带上时间戳，否则代码截图无效
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")1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 179ms/step 1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 88ms/step 1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 87ms/step 1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 105ms/step 1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 89ms/step 1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 88ms/step 1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 95ms/step 1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 88ms/step
收获：大致了解更新的详细步骤，接下来会继续学习相关代码的运行知识 更加清楚的学习如何进行算法优化与改进
扫一扫
16万+
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
