搞一点用得到的东西

最新推荐文章于 2024-07-16 01:00:13 发布

随机砍狗牙

最新推荐文章于 2024-07-16 01:00:13 发布

阅读量75

点赞数

文章标签：人工智能

本文链接：https://blog.csdn.net/u013569168/article/details/132757742

版权

VGG16是一个经典的深度学习模型，其中包括了13个卷积层和3个全连接层。如果要将其中的全连接层改为回归层，可以按照以下步骤进行操作：

1. 导入VGG16模型

```python
from keras.applications.vgg16 import VGG16

# 指定输入尺寸和预训练权重
model = VGG16(weights='imagenet', include_top=True, input_shape=(224, 224, 3))
```

2. 查看模型结构

```python
model.summary()
```

可以看到模型的结构，其中最后三层为全连接层。

```
Model: "vgg16"
_________________________________________________________________
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, 1000) 4097000
=================================================================
Total params: 138,357,544
Trainable params: 138,357,544
Non-trainable params: 0
_________________________________________________________________
```

3. 删除全连接层

可以通过以下代码删除全连接层。

```python
model.layers.pop() # 删除最后一层全连接层
model.layers.pop() # 删除倒数第二层全连接层
model.layers.pop() # 删除倒数第三层全连接层
```

删除完全连接层后，模型的结构变成了：

```
Model: "vgg16"
_________________________________________________________________
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
=================================================================
Total params: 14,714,688
Trainable params: 14,714,688
Non-trainable params: 0
_________________________________________________________________
```

4. 添加回归层

现在，我们可以为模型添加一个新的回归层。例如，假设我们要预测一个数字：

```python
from keras.layers import Dense

# 添加一个输出大小为1的回归层
model.add(Dense(1, activation='linear'))
```

添加回归层后，模型的结构变为：

随机砍狗牙

关注

0
点赞
踩
0

收藏

觉得还不错? 一键收藏
0
评论
搞一点用得到的东西

VGG16是一个经典的深度学习模型，其中包括了13个卷积层和3个全连接层。现在，我们可以为模型添加一个新的回归层。model.layers.pop() # 删除倒数第二层全连接层。model.layers.pop() # 删除倒数第三层全连接层。model.layers.pop() # 删除最后一层全连接层。可以看到模型的结构，其中最后三层为全连接层。# 添加一个输出大小为1的回归层。可以通过以下代码删除全连接层。# 指定输入尺寸和预训练权重。1. 导入VGG16模型。
复制链接

扫一扫

搞一点用得到的东西

“相关推荐”对你有帮助么？