Shortcuts

ConvBn2d

class torch.nn.intrinsic.qat.ConvBn2d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=None, padding_mode='zeros', eps=1e-05, momentum=0.1, freeze_bn=False, qconfig=None)[source]

A ConvBn2d module is a module fused from Conv2d and BatchNorm2d, attached with FakeQuantize modules for weight, used in quantization aware training.

We combined the interface of torch.nn.Conv2d and torch.nn.BatchNorm2d.

Similar to torch.nn.Conv2d, with FakeQuantize modules initialized to default.

Variables:
  • freeze_bn

  • weight_fake_quant – fake quant module for weight

Docs

Access comprehensive developer documentation for PyTorch

View Docs

Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials

Resources

Find development resources and get your questions answered

View Resources