[PyTorch] Tutorial: torch.nn.Conv2d

Conv2d

CLASS torch.nn.Conv2d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True, padding_mode='zeros', device=None, dtype=None)

2D convolution

$$out(N_i,C_{ou{t}_j})=bias(C_{ou{t}_j})+\sum _{k=0}^{C_{in}-1}Weight(C_{ou{t}_j},k)\ast input(N_i,k)$$

$N$ : batch size
$C$ : Number of channels
$H$ : input high
$W$ : input width

• weight ([ Tensor ]) – module learnable weights, of shape ( $\text{out\_chanels}$, $\frac{\text{in\_channels}}{\text{groups}}$, $\text{kernel\_size[0]}$, $\text{kernel\_size[1]}$ ). 从$\mathcal{U}(-\sqrt{k},\sqrt{k})$ , where$k=\frac{groups}{C_{\text{in}}\ast {\prod }_{i=0}^1\text{kernel\_size}[i]}$
• bias ([ Tensor ] ) – module learnable weights, of shape (out_channels). If biasis True, from $\mathcal{U}(-\sqrt{k},\sqrt{k})$ 采样，其中$k=\frac{groups}{C_{\text{in}}\ast {\prod }_{i=0}^1\text{kernel\_size}\left[i\right]}$

• parameter
• in_channels ([ int ]) – number of channels of the input image
• out_channels ([ int ]) - number of output channels
• kernel_size ([ int ] or *[ tuple ]) - kernel size
• stride ([ int ] or [ tuple ], optional ) - stride, default is 1
• padding ([ int ] [ tuple ] or [ str ] optional ) - padding, default is 0
• padding_mode ([ str ] optional ) - zeros, reflect, replicate, default is zeros.
• dilation ([ int ] [ tuple ] optional ) - dilation kernel, defaults to 1
• groups ([ int ] optional ) - grouping, default 1
• bias ([ bool ] optional ) - if set to true, add the learned bias

import torch
import torch.nn as nn 

# With square kernels and equal stride
m1 = nn.Conv2d(16, 33, 3, stride=2)
# non-square kernels and unequal stride and with padding
m2 = nn.Conv2d(16, 33, (3, 5), stride=(2, 1), padding=(4, 2))
# non-square kernels and unequal stride and with padding and dilation
m3 = nn.Conv2d(16, 33, (3, 5), stride=(2, 1), padding=(4, 2), dilation=(3, 1))

input = torch.randn(20, 16, 50, 100)

output1 = m1(input)  # torch.Size([20, 33, 24, 49])
output2 = m2(input)  # torch.Size([20, 33, 28, 100])
output3 = m3(input)  # torch.Size([20, 33, 26, 100])

【reference】

Conv2d — PyTorch 1.13 documentation