PyTorch torch.nn.Conv3d Function

PyTorch torch.nn 参考手册PyTorch torch.nn Reference Manual


torch.nn.Conv3dIs a 3D convolution module in PyTorch.

It processes 3D inputs, such as videos or medical images (depth x height x width).

Function Definition

torch.nn.Conv3d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True)

Input Shape

(batch, channels, depth, height, width)

Usage Examples

Example 1: Basic Usage

Example

import torch
import torch.nn as nn

# 3D convolution
conv3d = nn.Conv3d(in_channels=3, out_channels=32, kernel_size=3, padding=1)

# Input: batch=2, channels=3, depth=16, height=32, width=32
x = torch.randn(2, 3, 16, 32, 32)
output = conv3d(x)

print("Input shape:", x.shape)
print("Output shape:", output.shape)

Example 2: Video Classification

Example

import torch
import torch.nn as nn

class VideoCNN(nn.Module):
    def __init__(self, num_classes=10):
        super(VideoCNN, self).__init__()
        self.conv1 = nn.Conv3d(3, 32, kernel_size=3, padding=1)
        self.pool = nn.MaxPool3d(2)
        self.conv2 = nn.Conv3d(32, 64, kernel_size=3, padding=1)
        self.gap = nn.AdaptiveAvgPool3d(1)
        self.fc = nn.Linear(64, num_classes)

    def forward(self, x):
        x = torch.relu(self.conv1(x))
        x = self.pool(x)
        x = torch.relu(self.conv2(x))
        x = self.gap(x)
        x = x.view(x.size(0), -1)
        return self.fc(x)

model = VideoCNN()
x = torch.randn(4, 3, 16, 112, 112)  # 16-frame video
output = model(x)

print("Video:", x.shape, "-> Class:", output.shape)

Example 3: Parameter Calculation

Example

import torch
import torch.nn as nn

conv = nn.Conv3d(64, 128, kernel_size=3, padding=1)

# Parameter count calculation: out_ch * in_ch * k_d * k_h * k_w + bias
params = 128 * 64 * 3 * 3 * 3
print("Number of parameters:", params)
print("Weight shape:", conv.weight.shape)

Use Cases

  • Video processing: action recognition
  • Medical imaging: CT、MRI
  • 3D segmentation: voxel data

Note: 3D convolution requires a large amount of computation and needs more GPU memory.


PyTorch torch.nn 参考手册PyTorch torch.nn Reference Manual

Other Extensions