Conv3d
-
class
torch.nn.qat.
Conv3d
(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True, padding_mode='zeros', qconfig=None, device=None, dtype=None)[source] A Conv3d module attached with FakeQuantize modules for weight, used for quantization aware training.
We adopt the same interface as torch.nn.Conv3d, please see https://pytorch.org/docs/stable/nn.html?highlight=conv3d#torch.nn.Conv3d for documentation.
Similar to torch.nn.Conv3d, with FakeQuantize modules initialized to default.
- Variables
~Conv3d.weight_fake_quant – fake quant module for weight
-
classmethod
from_float
(mod)[source] Create a qat module from a float module or qparams_dict
Args: mod a float module, either produced by torch.ao.quantization utilities or directly from user