深度学习与PyTorch入门实战 - 39. Pooling Sampling0 码力 | 13 页 | 749.97 KB | 2 年前3- pytorch 入门笔记-03- 神经网络现在，如果在反向过程中跟随 loss，使用它的 .grad fn 属性，将看到如下所示的计算图。 input -> conv2d -> relu -> maxpool2d -> conv2d -> relu -> maxpool2d -> view -> linear -> relu -> linear -> relu -> linear ->0 码力 | 7 页 | 370.53 KB | 2 年前3
- 动手学深度学习 v2.0Size([1, 96, 54, 54]) MaxPool2d output shape: torch.Size([1, 96, 26, 26]) Conv2d output shape: torch.Size([1, 256, 26, 26]) ReLU output shape: torch.Size([1, 256, 26, 26]) MaxPool2d output shape: torch.Size([1 Conv2d output shape: torch.Size([1, 384, 12, 12]) ReLU output shape: torch.Size([1, 256, 12, 12]) MaxPool2d output shape: torch.Size([1, 256, 5, 5]) Flatten output shape: torch.Size([1, 6400]) Linear output output shape: torch.Size([1, 96, 54, 54]) MaxPool2d output shape: torch.Size([1, 96, 26, 26]) Sequential output shape: torch.Size([1, 256, 26, 26]) MaxPool2d output shape: torch.Size([1, 256, 12, 12])0 码力 | 797 页 | 29.45 MB | 2 年前3
共 3 条
- 1