正确设置 CNN 输入尺寸（Pytorch）

Question

我不断收到此错误：

Traceback (most recent call last):
  File "/Users/robbymoseley/Desktop/IOP/IOP-ML/Model/IOP_model.py", line 201, in <module>
    logps = model(images)
  File "/Applications/Python Virtual Environment/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/Users/robbymoseley/Desktop/IOP/IOP-ML/Model/IOP_model.py", line 95, in forward
    x = self.pool(F.relu(self.conv1(x)))
  File "/Applications/Python Virtual Environment/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/Applications/Python Virtual Environment/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 399, in forward
    return self._conv_forward(input, self.weight, self.bias)
  File "/Applications/Python Virtual Environment/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 396, in _conv_forward
    self.padding, self.dilation, self.groups)
RuntimeError: Expected 4-dimensional input for 4-dimensional weight [6, 1, 5, 5], but got 2-dimensional input of size [10, 307200] instead

这是我正在尝试使用的模型：

class Net(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(1, 6, 5)
        # we use the maxpool multiple times, but define it once
        self.pool = nn.MaxPool2d(2, 2)
        # in_channels = 6 because self.conv1 output 6 channel
        self.conv2 = nn.Conv2d(6, 16, 5)
        # 5*5 comes from the dimension of the last convnet layer
        self.fc1 = nn.Linear(input_size, hidden_sizes[0])
        self.fc2 = nn.Linear(hidden_sizes[0], hidden_sizes[1])
        self.fc3 = nn.Linear(hidden_sizes[1], output_size)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 16 * 5 * 5)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)  # no activation on final layer
        return x

输入图像为 640x480。

这也是我的主要功能：

if __name__ == __main__:

    if torch.cuda.is_available():
        device = torch.device("cuda:0")
    else:
        device = torch.device("cpu")

    model = Net().to(device)

    criterion = nn.NLLLoss()
    images, labels = next(iter(train_loader))
    # images = images.view(images.shape[0], -1)
    print(images.shape)
    images = images.view(images.shape[0], -1)
    logps = model(images)
    loss = criterion(logps, labels)  # calculate the NLL loss

    # training process
    optimizer = optim.SGD(model.parameters(), lr=0.003, momentum=0.9)

    loss_fn = nn.NLLLoss()

    # train the model
    train_model(num_epochs, model)

    # validate the model
    validate_model(model)

    print("Execution has finished")

如何调整预期的输入尺寸或权重？或者我可以更改输入的尺寸以正确反映模型的结构吗？如果是这样，我该怎么做？

Answer 1

基于卷积部分，我确实注意到了问题，您的最终池化层输出通道计算不正确

以下是根据您提到的输入大小 640x480x1 的代码应该如何工作

import torch
import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(1, 6, 5)
        # we use the maxpool multiple times, but define it once
        self.pool = nn.MaxPool2d(2, 2)
        # in_channels = 6 because self.conv1 output 6 channel
        self.conv2 = nn.Conv2d(6, 16, 5)
        # 5*5 comes from the dimension of the last convnet layer
        self.fc1 = nn.Linear(16 * 157 * 117, 256) # You didnt provide the numbers here but i did calculate the in channels based off the prev layer
        self.fc2 = nn.Linear(256, 10)
        self.fc3 = nn.Linear(10, 2)

    def forward(self, x):
        x = self.conv1(x)
        print('Conv1 Shape: {}'.format(x.shape))
        x = self.pool(F.relu(x))
        print('Pool1 Shape: {}'.format(x.shape))
        x = self.conv2(x)
        print('Conv2 Shape: {}'.format(x.shape))
        x = self.pool(F.relu(x))
        print('Pool2 Shape: {}'.format(x.shape))
        x = x.view(-1, 16 * 157 * 117)
        print('Flatten Shape: {}'.format(x.shape))
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)  # no activation on final layer
        return x
    
model = Model()

model(torch.randn(1, 1, 640, 480)) # 1 Channel since your first conv layer input inchannel is 1

每一层的输出形状

model(torch.randn(1, 1, 640, 480))
Conv1 Shape: torch.Size([1, 6, 636, 476])
Pool1 Shape: torch.Size([1, 6, 318, 238])
Conv2 Shape: torch.Size([1, 16, 314, 234])
Pool2 Shape: torch.Size([1, 16, 157, 117])
Flatten Shape: torch.Size([1, 293904])