- 🍨 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
-
本周任务：
1.请根据本文 TensorFlow 代码，编写出相应的 Pytorch 代码
2.了解残差结构
3.是否可以将残差模块融入到C3当中（自由探索）
一、前期工作
我的环境
- 操作系统：CentOS7
- 显卡：RTX3090 两张
- 显卡驱动：550.78
- CUDA版本: 12.4
- 语言环境：Python3.9.19
- 编译器：Jupyter Lab
- 深度学习环境：
- TensorFlow-2.17.0 (GPU版本)
1. 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) #设置GPU显存用量按需使用
tf.config.set_visible_devices([gpus[0]],"GPU")
2. 导入数据
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
import numpy as np
from tensorflow import keras
from tensorflow.keras import layers,models
data_dir = "./data/bird_photos"
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： 565
二、数据处理
1. 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.csdn.net/article/details/117018789
"""
train_ds = tf.keras.preprocessing.image_dataset_from_directory(
data_dir,
validation_split=0.2,
subset="training",
seed=123,
image_size=(img_height, img_width),
batch_size=batch_size)
Found 565 files belonging to 4 classes.
Using 452 files for training.
2024-12-13 12:17:53.399468: I tensorflow/core/common_runtime/gpu/gpu_device.cc:2021] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 22199 MB memory: -> device: 0, name: NVIDIA GeForce RTX 3090, pci bus id: 0000:3b:00.0, compute capability: 8.6
"""
关于image_dataset_from_directory()的详细介绍可以参考文章：https://mtyjkh.blog.csdn.net/article/details/117018789
"""
val_ds = tf.keras.preprocessing.image_dataset_from_directory(
data_dir,
validation_split=0.2,
subset="validation",
seed=123,
image_size=(img_height, img_width),
batch_size=batch_size)
Found 565 files belonging to 4 classes.
Using 113 files for validation.
class_names = train_ds.class_names
print(class_names)
['Bananaquit', 'Black Skimmer', 'Black Throated Bushtiti', 'Cockatoo']
2. 可视化数据
plt.figure(figsize=(10, 5)) # 图形的宽为10高为5
plt.suptitle("Pictures of Birds")
for images, labels in train_ds.take(1):
for i in range(8):
ax = plt.subplot(2, 4, i + 1)
plt.imshow(images[i].numpy().astype("uint8"))
plt.title(class_names[labels[i]])
plt.axis("off")
for image_batch, labels_batch in train_ds:
print(image_batch.shape)
print(labels_batch.shape)
break
(8, 224, 224, 3)
(8,)
AUTOTUNE = tf.data.AUTOTUNE
train_ds = train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE)
val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)
三、构建ResNet-50网络模型
from keras import layers
from keras.layers import Input,Activation,BatchNormalization,Flatten
from keras.layers import Dense,Conv2D,MaxPooling2D,ZeroPadding2D,AveragePooling2D
from keras.models import Model
def identity_block(input_tensor, kernel_size, filters, stage, block):
filters1, filters2, filters3 = filters
name_base = str(stage) + block + '_identity_block_'
x = Conv2D(filters1, (1, 1), name=name_base + 'conv1')(input_tensor)
x = BatchNormalization(name=name_base + 'bn1')(x)
x = Activation('relu', name=name_base + 'relu1')(x)
x = Conv2D(filters2, kernel_size,padding='same', name=name_base + 'conv2')(x)
x = BatchNormalization(name=name_base + 'bn2')(x)
x = Activation('relu', name=name_base + 'relu2')(x)
x = Conv2D(filters3, (1, 1), name=name_base + 'conv3')(x)
x = BatchNormalization(name=name_base + 'bn3')(x)
x = layers.add([x, input_tensor] ,name=name_base + 'add')
x = Activation('relu', name=name_base + 'relu4')(x)
return x
# 在残差网络中，广泛地使用了BN层；但是没有使用MaxPooling以便减小特征图尺寸，
# 作为替代，在每个模块的第一层，都使用了strides = (2, 2)的方式进行特征图尺寸缩减，
# 与使用MaxPooling相比，毫无疑问是减少了卷积的次数，输入图像分辨率较大时比较适合
# 在残差网络的最后一级，先利用layer.add()实现H(x) = x + F(x)
def conv_block(input_tensor, kernel_size, filters, stage, block, strides=(2, 2)):
filters1, filters2, filters3 = filters
res_name_base = str(stage) + block + '_conv_block_res_'
name_base = str(stage) + block + '_conv_block_'
x = Conv2D(filters1, (1, 1), strides=strides, name=name_base + 'conv1')(input_tensor)
x = BatchNormalization(name=name_base + 'bn1')(x)
x = Activation('relu', name=name_base + 'relu1')(x)
x = Conv2D(filters2, kernel_size, padding='same', name=name_base + 'conv2')(x)
x = BatchNormalization(name=name_base + 'bn2')(x)
x = Activation('relu', name=name_base + 'relu2')(x)
x = Conv2D(filters3, (1, 1), name=name_base + 'conv3')(x)
x = BatchNormalization(name=name_base + 'bn3')(x)
shortcut = Conv2D(filters3, (1, 1), strides=strides, name=res_name_base + 'conv')(input_tensor)
shortcut = BatchNormalization(name=res_name_base + 'bn')(shortcut)
x = layers.add([x, shortcut], name=name_base+'add')
x = Activation('relu', name=name_base+'relu4')(x)
return x
def ResNet50(input_shape=[224,224,3],classes=1000):
img_input = Input(shape=input_shape)
x = ZeroPadding2D((3, 3))(img_input)
x = Conv2D(64, (7, 7), strides=(2, 2), name='conv1')(x)
x = BatchNormalization(name='bn_conv1')(x)
x = Activation('relu')(x)
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1))
x = identity_block(x, 3, [64, 64, 256], stage=2, block='b')
x = identity_block(x, 3, [64, 64, 256], stage=2, block='c')
x = conv_block(x, 3, [128, 128, 512], stage=3, block='a')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='b')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='c')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='d')
x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='c')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='d')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='e')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='f')
x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a')
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b')
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c')
x = AveragePooling2D((7, 7), name='avg_pool')(x)
x = Flatten()(x)
x = Dense(classes, activation='softmax', name='fc1000')(x)
model = Model(img_input, x, name='resnet50')
# 加载预训练模型
model.load_weights("./data/resnet50_weights_tf_dim_ordering_tf_kernels.h5")
return model
model = ResNet50()
model.summary()
模型字符太多，省略。
Model: "resnet50"
Total params: 25,636,712 (97.80 MB)
Trainable params: 25,583,592 (97.59 MB)
Non-trainable params: 53,120 (207.50 KB)
在准备对模型进行训练之前，还需要再对其进行一些设置。以下内容是在模型的编译步骤中添加的：
- 损失函数（loss）：用于衡量模型在训练期间的准确率。
- 优化器（optimizer）：决定模型如何根据其看到的数据和自身的损失函数进行更新。
- 指标（metrics）：用于监控训练和测试步骤。以下示例使用了准确率，即被正确分类的图像的比率。
## 模型编译
model.compile(optimizer="adam",
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
四、训练模型
epochs = 50
history = model.fit(
train_ds,
validation_data=val_ds,
epochs=epochs
)
五、模型评估
acc = history.history['accuracy']
val_acc = history.history['val_accuracy']
loss = history.history['loss']
val_loss = history.history['val_loss']
epochs_range = range(epochs)
plt.figure(figsize=(12, 4))
plt.subplot(1, 2, 1)
plt.suptitle("")
plt.plot(epochs_range, acc, label='Training Accuracy')
plt.plot(epochs_range, val_acc, label='Validation Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')
plt.subplot(1, 2, 2)
plt.plot(epochs_range, loss, label='Training Loss')
plt.plot(epochs_range, val_loss, label='Validation Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()
六、预测
# 采用加载的模型（new_model）来看预测结果
plt.figure(figsize=(10, 5)) # 图形的宽为10高为5
plt.suptitle("")
for images, labels in val_ds.take(1):
for i in range(8):
ax = plt.subplot(2, 4, i + 1)
# 显示图片
plt.imshow(images[i].numpy().astype("uint8"))
# 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")
七、总结
- 暂时还不会使用pytorch写出ResNet-50的代码
- 对于ResNet-50的理解不够，需要阅读何凯明的论文
