PyTorch的SqueezeNet的迁移训练

flyfish

mobilenet v2完整的迁移训练代码
SqueezeNet有两个版本分别是SqueezeNet 1.0和SqueezeNet 1.1
这里说的是迁移SqueezeNet 1.1
使用预训练模型，将1000类别更改为2类
它的网络结构如下

SqueezeNet((features): Sequential((0): Conv2d(3, 64, kernel_size=(3, 3), stride=(2, 2))(1): ReLU(inplace=True)(2): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=True)(3): Fire((squeeze): Conv2d(64, 16, kernel_size=(1, 1), stride=(1, 1))(squeeze_activation): ReLU(inplace=True)(expand1x1): Conv2d(16, 64, kernel_size=(1, 1), stride=(1, 1))(expand1x1_activation): ReLU(inplace=True)(expand3x3): Conv2d(16, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(expand3x3_activation): ReLU(inplace=True))(4): Fire((squeeze): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1))(squeeze_activation): ReLU(inplace=True)(expand1x1): Conv2d(16, 64, kernel_size=(1, 1), stride=(1, 1))(expand1x1_activation): ReLU(inplace=True)(expand3x3): Conv2d(16, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(expand3x3_activation): ReLU(inplace=True))(5): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=True)(6): Fire((squeeze): Conv2d(128, 32, kernel_size=(1, 1), stride=(1, 1))(squeeze_activation): ReLU(inplace=True)(expand1x1): Conv2d(32, 128, kernel_size=(1, 1), stride=(1, 1))(expand1x1_activation): ReLU(inplace=True)(expand3x3): Conv2d(32, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(expand3x3_activation): ReLU(inplace=True))(7): Fire((squeeze): Conv2d(256, 32, kernel_size=(1, 1), stride=(1, 1))(squeeze_activation): ReLU(inplace=True)(expand1x1): Conv2d(32, 128, kernel_size=(1, 1), stride=(1, 1))(expand1x1_activation): ReLU(inplace=True)(expand3x3): Conv2d(32, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(expand3x3_activation): ReLU(inplace=True))(8): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=True)(9): Fire((squeeze): Conv2d(256, 48, kernel_size=(1, 1), stride=(1, 1))(squeeze_activation): ReLU(inplace=True)(expand1x1): Conv2d(48, 192, kernel_size=(1, 1), stride=(1, 1))(expand1x1_activation): ReLU(inplace=True)(expand3x3): Conv2d(48, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(expand3x3_activation): ReLU(inplace=True))(10): Fire((squeeze): Conv2d(384, 48, kernel_size=(1, 1), stride=(1, 1))(squeeze_activation): ReLU(inplace=True)(expand1x1): Conv2d(48, 192, kernel_size=(1, 1), stride=(1, 1))(expand1x1_activation): ReLU(inplace=True)(expand3x3): Conv2d(48, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(expand3x3_activation): ReLU(inplace=True))(11): Fire((squeeze): Conv2d(384, 64, kernel_size=(1, 1), stride=(1, 1))(squeeze_activation): ReLU(inplace=True)(expand1x1): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1))(expand1x1_activation): ReLU(inplace=True)(expand3x3): Conv2d(64, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(expand3x3_activation): ReLU(inplace=True))(12): Fire((squeeze): Conv2d(512, 64, kernel_size=(1, 1), stride=(1, 1))(squeeze_activation): ReLU(inplace=True)(expand1x1): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1))(expand1x1_activation): ReLU(inplace=True)(expand3x3): Conv2d(64, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(expand3x3_activation): ReLU(inplace=True)))(classifier): Sequential((0): Dropout(p=0.5, inplace=False)(1): Conv2d(512, 1000, kernel_size=(1, 1), stride=(1, 1))(2): ReLU(inplace=True)(3): AdaptiveAvgPool2d(output_size=(1, 1)))
)

我们要改的是

  (classifier): Sequential((0): Dropout(p=0.5, inplace=False)(1): Conv2d(512, 1000, kernel_size=(1, 1), stride=(1, 1))(2): ReLU(inplace=True)(3): AdaptiveAvgPool2d(output_size=(1, 1)))

如果采用孔乙己的茴香豆的茴，使用与之前MobileNet 不同的写法。
将其改成

  (classifier): Sequential((0): Dropout(p=0.5, inplace=False)(1): Conv2d(512, 2, kernel_size=(1, 1), stride=(1, 1))(2): ReLU(inplace=True)(3): AdaptiveAvgPool2d(output_size=(1, 1)))

代码是

model_ft = models.squeezenet1_1(pretrained=True)
model_ft.classifier[1] = nn.Conv2d(in_channels=512, out_channels=2, kernel_size=(1, 1), stride=(1, 1))

PyTorch的SqueezeNet的迁移训练相关推荐

PyTorch实战使用Resnet迁移学习
PyTorch实战使用Resnet迁移学习项目结构项目任务项目代码网络模型测试项目结构数据集存放在flower_data文件夹 cat_to_name.json是makejson文件运行生 ...
pytorch与keras_Keras vs PyTorch：如何通过迁移学习区分外星人与掠食者
pytorch与keras by Patryk Miziuła 通过PatrykMiziuła Keras vs PyTorch:如何通过迁移学习区分外星人与掠食者 (Keras vs PyTorch ...
Pytorch笔记：风格迁移
Pytorch笔记:风格迁移训练模型:风格迁移网络+VGG16网络生成网络:风格迁移网络代码如下(根据陈云<深度学习框架:Pytorch入门与实践>的代码改动) main.py im ...
【深度域自适应】二、利用DANN实现MNIST和MNIST-M数据集迁移训练
前言在前一篇文章[深度域自适应]一.DANN与梯度反转层(GRL)详解中,我们主要讲解了DANN的网络架构与梯度反转层(GRL)的基本原理,接下来这篇文章中我们将主要复现DANN论文Unsuperv ...
8_用opencv调用深度学习框架tenorflow、Pytorch、Torch、caffe训练好的模型（20190212）
用opencv调用深度学习框架tenorflow.Pytorch.Torch.caffe训练好模型(20190212) 文章目录: https://blog.csdn.net/hust_bochu_x ...
PyTorch项目使用TensorboardX进行训练可视化
PyTorch项目使用TensorboardX进行训练可视化什么是TensorboardX 配置TensorboardX 使用 pip 安装从源码安装使用TensorboardX 参考资料什么 ...
PyTorch如何加速数据并行训练？分布式秘籍大揭秘
本文转载自机器之心. 选自arXiv 作者:Shen Li等机器之心编译参与:小舟.杜伟 PyTorch 在学术圈里已经成为最为流行的深度学习框架,如何在使用 PyTorch 时实现高效的并行化? ...
TensorFlow Lite（实战系列一）：TFLite Android 迁移训练构建自己的图像识别APP
摘要人工智能想要从实验室走向大众,一个必不可少的途径就是朝着智能终端.嵌入式产品等边缘设备发展.谷歌基于TFMobile推出了TFLite,我们只需要把训练好的模型按照一定规则转换成拥有.tflit ...
【深度域适配】二、利用DANN实现MNIST和MNIST-M数据集迁移训练
知乎专栏链接:https://zhuanlan.zhihu.com/p/109057360 CSDN链接:https://daipuweiai.blog.csdn.net/article/detail ...

PyTorch的SqueezeNet的迁移训练

PyTorch的SqueezeNet的迁移训练相关推荐

最新文章

热门文章