技术教程 编程教程 pytorch学习笔记（8）--现有模型的使用和修改 正文

pytorch学习笔记（8）--现有模型的使用和修改

2023-03-13,,

官网网址： https://pytorch.org/vision/0.9/models.html#semantic-segmentation

(1)、ImageNet

train_data = torchvision.datasets.ImageNet("../dataset", split='train', transform=torchvision.transforms.ToTensor())

　　ImageNet数据集是一个计算机视觉数据集。 ImageNet数据集一直是评估图像分类算法性能的基准。 ImageNet 数据集是为了促进计算机图像识别技术的发展而设立的一个大型图像数据集。ImageNet详细介绍： https://blog.51cto.com/yunyaniu/5245552

(2) 、神经网络VGG16

weights参数表示是否使用已训练的模型参数。

代码：
# file     : model_pretrained.py

# time     : 2022/8/5 下午4:19

# function : VGG16

import torchvision.datasets

# ImageNet need to be downloaded manually

# train_data = torchvision.datasets.ImageNet("../dataset", split='train', transform=torchvision.transforms.ToTensor())

vgg16_false = torchvision.models.vgg16(weights=False)

vgg16_true = torchvision.models.vgg16(weights=True)

print(vgg16_true)

结果：

VGG(

  (features): Sequential(

    (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (1): ReLU(inplace=True)

    (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (3): ReLU(inplace=True)

    (4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)

    (5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (6): ReLU(inplace=True)

    (7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (8): ReLU(inplace=True)

    (9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)

    (10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (11): ReLU(inplace=True)

    (12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (13): ReLU(inplace=True)

    (14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (15): ReLU(inplace=True)

    (16): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)

    (17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (18): ReLU(inplace=True)

    (19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (20): ReLU(inplace=True)

    (21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (22): ReLU(inplace=True)

    (23): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)

    (24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (25): ReLU(inplace=True)

    (26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (27): ReLU(inplace=True)

    (28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (29): ReLU(inplace=True)

    (30): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)

  )

  (avgpool): AdaptiveAvgPool2d(output_size=(7, 7))

  (classifier): Sequential(

    (0): Linear(in_features=25088, out_features=4096, bias=True)

    (1): ReLU(inplace=True)

    (2): Dropout(p=0.5, inplace=False)

    (3): Linear(in_features=4096, out_features=4096, bias=True)

    (4): ReLU(inplace=True)

    (5): Dropout(p=0.5, inplace=False)

    (6): Linear(in_features=4096, out_features=1000, bias=True)

  )

)

结果显示：VGG16网络是由13层卷积层和3层全连接层组成，最后网络输出一共有1000个分类结果。

（3）、修改现有VGG16模型的结构

    在VGG16模型后增加一个线性层，实现将VGG16的1000个类别输出为CIFAR10的10个类别，代码如下：

# file     : model_pretrained.py

# time     : 2022/8/5 下午4:19

# function :

import torchvision.datasets

from torch import nn

vgg16_false = torchvision.models.vgg16(weights=False)

vgg16_true = torchvision.models.vgg16(weights=True)

print(vgg16_true)

train_data = torchvision.datasets.CIFAR10("../dataset", train=True, transform=torchvision.transforms.ToTensor(), download=False)

vgg16_true.add_module('add_linear', nn.Linear(1000, 10))

print(vgg16_true)

结果:

VGG(

  (features): Sequential(

    (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (1): ReLU(inplace=True)

    (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (3): ReLU(inplace=True)

    (4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)

    (5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (6): ReLU(inplace=True)

    (7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (8): ReLU(inplace=True)

    (9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)

    (10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (11): ReLU(inplace=True)

    (12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (13): ReLU(inplace=True)

    (14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (15): ReLU(inplace=True)

    (16): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)

    (17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (18): ReLU(inplace=True)

    (19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (20): ReLU(inplace=True)

    (21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (22): ReLU(inplace=True)

    (23): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)

    (24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (25): ReLU(inplace=True)

    (26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (27): ReLU(inplace=True)

    (28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (29): ReLU(inplace=True)

    (30): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)

  )

  (avgpool): AdaptiveAvgPool2d(output_size=(7, 7))

  (classifier): Sequential(

    (0): Linear(in_features=25088, out_features=4096, bias=True)

    (1): ReLU(inplace=True)

    (2): Dropout(p=0.5, inplace=False)

    (3): Linear(in_features=4096, out_features=4096, bias=True)

    (4): ReLU(inplace=True)

    (5): Dropout(p=0.5, inplace=False)

    (6): Linear(in_features=4096, out_features=1000, bias=True)

  )

)

VGG(

  (features): Sequential(

    (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (1): ReLU(inplace=True)

    (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (3): ReLU(inplace=True)

    (4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)

    (5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (6): ReLU(inplace=True)

    (7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (8): ReLU(inplace=True)

    (9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)

    (10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (11): ReLU(inplace=True)

    (12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (13): ReLU(inplace=True)

    (14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (15): ReLU(inplace=True)

    (16): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)

    (17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (18): ReLU(inplace=True)

    (19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (20): ReLU(inplace=True)

    (21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (22): ReLU(inplace=True)

    (23): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)

    (24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (25): ReLU(inplace=True)

    (26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (27): ReLU(inplace=True)

    (28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (29): ReLU(inplace=True)

    (30): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)

  )

  (avgpool): AdaptiveAvgPool2d(output_size=(7, 7))

  (classifier): Sequential(

    (0): Linear(in_features=25088, out_features=4096, bias=True)

    (1): ReLU(inplace=True)

    (2): Dropout(p=0.5, inplace=False)

    (3): Linear(in_features=4096, out_features=4096, bias=True)

    (4): ReLU(inplace=True)

    (5): Dropout(p=0.5, inplace=False)

    (6): Linear(in_features=4096, out_features=1000, bias=True)

  )

  (add_linear): Linear(in_features=1000, out_features=10, bias=True)

)

如果想将最后的线性层加在classifier中，则将代码修改如下：

vgg16_true.classifier.add_module('add_linear', nn.Linear(1000, 10))

结果:

VGG(

  (features): Sequential(

    (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (1): ReLU(inplace=True)

    (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (3): ReLU(inplace=True)

    (4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)

    (5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (6): ReLU(inplace=True)

    (7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (8): ReLU(inplace=True)

    (9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)

    (10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (11): ReLU(inplace=True)

    (12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (13): ReLU(inplace=True)

    (14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (15): ReLU(inplace=True)

    (16): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)

    (17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (18): ReLU(inplace=True)

    (19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (20): ReLU(inplace=True)

    (21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (22): ReLU(inplace=True)

    (23): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)

    (24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (25): ReLU(inplace=True)

    (26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (27): ReLU(inplace=True)

    (28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (29): ReLU(inplace=True)

    (30): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)

  )

  (avgpool): AdaptiveAvgPool2d(output_size=(7, 7))

  (classifier): Sequential(

    (0): Linear(in_features=25088, out_features=4096, bias=True)

    (1): ReLU(inplace=True)

    (2): Dropout(p=0.5, inplace=False)

    (3): Linear(in_features=4096, out_features=4096, bias=True)

    (4): ReLU(inplace=True)

    (5): Dropout(p=0.5, inplace=False)

    (6): Linear(in_features=4096, out_features=1000, bias=True)

    (add_linear): Linear(in_features=1000, out_features=10, bias=True)

  )

如果想将在classifier最后一层输出改成10中，则将代码修改如下：

# file     : model_pretrained.py

# time     : 2022/8/5 下午4:19

# function :

import torchvision.datasets

from torch import nn

vgg16_false = torchvision.models.vgg16(weights=False)

print(vgg16_false)

vgg16_false.classifier[6] = nn.Linear(4096, 10)

print(vgg16_false)
VGG(

  (features): Sequential(

    (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (1): ReLU(inplace=True)

    (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (3): ReLU(inplace=True)

    (4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)

    (5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (6): ReLU(inplace=True)

    (7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (8): ReLU(inplace=True)

    (9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)

    (10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (11): ReLU(inplace=True)

    (12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (13): ReLU(inplace=True)

    (14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (15): ReLU(inplace=True)

    (16): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)

    (17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (18): ReLU(inplace=True)

    (19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (20): ReLU(inplace=True)

    (21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (22): ReLU(inplace=True)

    (23): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)

    (24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (25): ReLU(inplace=True)

    (26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (27): ReLU(inplace=True)

    (28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (29): ReLU(inplace=True)

    (30): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)

  )

  (avgpool): AdaptiveAvgPool2d(output_size=(7, 7))

  (classifier): Sequential(

    (0): Linear(in_features=25088, out_features=4096, bias=True)

    (1): ReLU(inplace=True)

    (2): Dropout(p=0.5, inplace=False)

    (3): Linear(in_features=4096, out_features=4096, bias=True)

    (4): ReLU(inplace=True)

    (5): Dropout(p=0.5, inplace=False)

    (6): Linear(in_features=4096, out_features=1000, bias=True)

  )

)

VGG(

  (features): Sequential(

    (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (1): ReLU(inplace=True)

    (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (3): ReLU(inplace=True)

    (4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)

    (5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (6): ReLU(inplace=True)

    (7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (8): ReLU(inplace=True)

    (9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)

    (10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (11): ReLU(inplace=True)

    (12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (13): ReLU(inplace=True)

    (14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (15): ReLU(inplace=True)

    (16): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)

    (17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (18): ReLU(inplace=True)

    (19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (20): ReLU(inplace=True)

    (21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (22): ReLU(inplace=True)

    (23): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)

    (24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (25): ReLU(inplace=True)

    (26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (27): ReLU(inplace=True)

    (28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))

    (29): ReLU(inplace=True)

    (30): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)

  )

  (avgpool): AdaptiveAvgPool2d(output_size=(7, 7))

  (classifier): Sequential(

    (0): Linear(in_features=25088, out_features=4096, bias=True)

    (1): ReLU(inplace=True)

    (2): Dropout(p=0.5, inplace=False)

    (3): Linear(in_features=4096, out_features=4096, bias=True)

    (4): ReLU(inplace=True)

    (5): Dropout(p=0.5, inplace=False)

    (6): Linear(in_features=4096, out_features=10, bias=True)

  )

)

pytorch学习笔记（8）--现有模型的使用和修改的相关教程结束。

《pytorch学习笔记（8）--现有模型的使用和修改.doc》

下载本文的Word格式文档，以方便收藏与打印。

Copyright 2023. 昆居客 - IT编程,互联网信息技术文档大全!