ConvReLU3d — PyTorch 2.7 documentation (original) (raw)

• Docs >
• Quantization >
• Quantization API Reference >
• ConvReLU3d
• 

Shortcuts

class torch.ao.nn.intrinsic.qat.ConvReLU3d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True, padding_mode='zeros', qconfig=None)[source][source]¶

A ConvReLU3d module is a fused module of Conv3d and ReLU, attached with FakeQuantize modules for weight for quantization aware training.

We combined the interface of Conv3d andBatchNorm3d.

Variables

weight_fake_quant – fake quant module for weight

• ConvReLU3d
  • ConvReLU3d