mirror of https://github.com/hpcaitech/ColossalAI
65 lines
1.7 KiB
Python
65 lines
1.7 KiB
Python
#!/usr/bin/env python
|
|
# -*- encoding: utf-8 -*-
|
|
|
|
from typing import Optional, Callable
|
|
|
|
import torch.nn as nn
|
|
from torch import Tensor
|
|
|
|
from colossalai.registry import LAYERS
|
|
from .conv import conv3x3
|
|
|
|
|
|
@LAYERS.register_module
|
|
class ResNetBasicBlock(nn.Module):
|
|
"""Basic ResNet block
|
|
"""
|
|
expansion: int = 1
|
|
|
|
def __init__(
|
|
self,
|
|
inplanes: int,
|
|
planes: int,
|
|
stride: int = 1,
|
|
downsample: Optional[nn.Module] = None,
|
|
groups: int = 1,
|
|
base_width: int = 64,
|
|
dilation: int = 1,
|
|
norm_layer: Optional[Callable[..., nn.Module]] = None
|
|
) -> None:
|
|
super().__init__()
|
|
if norm_layer is None:
|
|
norm_layer = nn.BatchNorm2d
|
|
if groups != 1 or base_width != 64:
|
|
raise ValueError(
|
|
'BasicBlock only supports groups=1 and base_width=64')
|
|
if dilation > 1:
|
|
raise NotImplementedError(
|
|
"Dilation > 1 not supported in BasicBlock")
|
|
# Both self.conv1 and self.downsample layers downsample the input when stride != 1
|
|
self.conv1 = conv3x3(inplanes, planes, stride)
|
|
self.bn1 = norm_layer(planes)
|
|
self.relu = nn.ReLU(inplace=True)
|
|
self.conv2 = conv3x3(planes, planes)
|
|
self.bn2 = norm_layer(planes)
|
|
self.downsample = downsample
|
|
self.stride = stride
|
|
|
|
def forward(self, x: Tensor) -> Tensor:
|
|
identity = x
|
|
|
|
out = self.conv1(x)
|
|
out = self.bn1(out)
|
|
out = self.relu(out)
|
|
|
|
out = self.conv2(out)
|
|
out = self.bn2(out)
|
|
|
|
if self.downsample is not None:
|
|
identity = self.downsample(x)
|
|
|
|
out += identity
|
|
out = self.relu(out)
|
|
|
|
return out
|