深度学习图片分类模型总结（附部分代码）

参考视频：2.1 pytorch官方demo(Lenet)_哔哩哔哩_bilibili

LeNet（1998）

pytorch 示例

笔记

1. Pytorch Tensor的通道排序：[batch,channel,height,width]

2. CIFAR10 dataset: It has the classes: ‘airplane’, ‘automobile’, ‘bird’, ‘cat’, ‘deer’, ‘dog’, ‘frog’, ‘horse’, ‘ship’, ‘truck’. The images in CIFAR-10 are of size 3x32x32, i.e. 3-channel color images of 32x32 pixels in size.

3. 为什么每计算一个batch就需要调用一次optimizer.zero_grad()：

   1. PyTorch中在反向传播前为什么要手动将梯度清零？ - 知乎

4. pytorch官网：-docs可查看各个函数的用法，-tutorials可以查看示例

5. data = torch.max(outputs, dim=1), then data will be a tuple containing two tensors.

   1. data[0]: This tensor will contain the maximum values along dimension 1 (the class dimension) of the outputs tensor. It will have a shape of [batch], where batch is the number of validation images in the batch.
   2. data[1]: This tensor will contain the indices of the maximum values along dimension 1 (the class dimension) of the outputs tensor. It will also have a shape of [batch], where each element represents the predicted class label (index) for each validation image in the batch.

6. get the size of a tensor along a specific dimension, you use the method size() or the property shape[].

   import torch
   # Assuming val_label is a tensor with shape [batch_size, ...]
   # Using size() method
   size_along_first_dim = val_label.size(0)
   # Using shape property
   size_along_first_dim = val_label.shape[0]