# torch.nn.intrinsic¶

This module implements the combined (fused) modules conv + relu which can be then quantized.

## ConvBn1d¶

class torch.nn.intrinsic.ConvBn1d(conv, bn)[source]

This is a sequential container which calls the Conv 1d and Batch Norm 1d modules. During quantization this will be replaced with the corresponding fused module.

## ConvBn2d¶

class torch.nn.intrinsic.ConvBn2d(conv, bn)[source]

This is a sequential container which calls the Conv 2d and Batch Norm 2d modules. During quantization this will be replaced with the corresponding fused module.

## ConvBn3d¶

class torch.nn.intrinsic.ConvBn3d(conv, bn)[source]

This is a sequential container which calls the Conv 3d and Batch Norm 3d modules. During quantization this will be replaced with the corresponding fused module.

## ConvBnReLU1d¶

class torch.nn.intrinsic.ConvBnReLU1d(conv, bn, relu)[source]

This is a sequential container which calls the Conv 1d, Batch Norm 1d, and ReLU modules. During quantization this will be replaced with the corresponding fused module.

## ConvBnReLU2d¶

class torch.nn.intrinsic.ConvBnReLU2d(conv, bn, relu)[source]

This is a sequential container which calls the Conv 2d, Batch Norm 2d, and ReLU modules. During quantization this will be replaced with the corresponding fused module.

## ConvBnReLU3d¶

class torch.nn.intrinsic.ConvBnReLU3d(conv, bn, relu)[source]

This is a sequential container which calls the Conv 3d, Batch Norm 3d, and ReLU modules. During quantization this will be replaced with the corresponding fused module.

## ConvReLU1d¶

class torch.nn.intrinsic.ConvReLU1d(conv, relu)[source]

This is a sequential container which calls the Conv1d and ReLU modules. During quantization this will be replaced with the corresponding fused module.

## ConvReLU2d¶

class torch.nn.intrinsic.ConvReLU2d(conv, relu)[source]

This is a sequential container which calls the Conv2d and ReLU modules. During quantization this will be replaced with the corresponding fused module.

## ConvReLU3d¶

class torch.nn.intrinsic.ConvReLU3d(conv, relu)[source]

This is a sequential container which calls the Conv3d and ReLU modules. During quantization this will be replaced with the corresponding fused module.