-- coding: utf-8 --
‘’‘ResNet in PyTorch.
For Pre-activation ResNet, see ‘preact_resnet.py’.
Reference:
[1] Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun
Deep Residual Learning for Image Recognition. arXiv:1512.03385
‘’’
import torch
import torch.nn as nn
import torch.nn.functional as F
class BasicBlock(nn.Module):
expansion = 1
def __init__(self, in_planes, planes, stride=1):
super(BasicBlock, self).__init__()
self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
self.bn1 = nn.BatchNorm2d(planes)
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=1, padding=1, bias=False)
self.bn2 = nn.BatchNorm2d(planes)
self.shortcut = nn.Sequential()
if stride != 1 or in_planes != self.expansion*planes:
self.shortcut = nn.Sequential(
nn.Conv2d(in_planes, self.expansion*planes, kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(self.expansion*planes)
)
def forward(self, x):
out = F.relu(self.bn1(self.conv1(x)))
out = self.bn2(self.conv2(out))
out += self.shortcut(x)
out = F.relu(out)
return out
class Bottleneck(nn.Module):
expansion = 4
def __init__(self, in_planes, planes, stride=1):
super(Bottleneck, self).__init__()
self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=1, bias=False)
self.bn1 = nn.BatchNorm2d(planes)
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
self.bn2 = nn.BatchNorm2d(planes)
self.conv3 = nn.Conv2d(planes, self.expansion*planes, kernel_size=1, bias=False)
self.bn3 = nn.BatchNorm2d(self.expansion*planes)
self.shortcut = nn.Sequential()
if stride != 1 or in_planes != self.expansion*planes:
self.shortcut = nn.Sequential(
nn.Conv2d(in_planes, self.expansion*planes, kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(self.expansion*planes)
)
def forward(self, x):
out = F.relu(self.bn1(self.conv1(x)))
out = F.relu(self.bn2(self.conv2(out)))
out = self.bn3(self.conv3(out))
out += self.shortcut(x)
out = F.relu(out)
return out
class ResNet(nn.Module):
def init(self, block, num_blocks, num_classes=15):
super(ResNet, self).init()
self.in_planes = 64
self.conv1 = nn.Conv2d(3, 64, kernel_size=5, stride=2, padding=2, bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.MaxPool2d = nn.MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
self.layer1 = self._make_layer(block, 64, num_blocks[0], stride=1)
self.layer2 = self._make_layer(block, 128, num_blocks[1], stride=2)
self.layer3 = self._make_layer(block, 256, num_blocks[2], stride=2)
self.layer4 = self._make_layer(block, 512, num_blocks[3], stride=2)
self.linear = nn.Linear(512*block.expansion, num_classes)
def _make_layer(self, block, planes, num_blocks, stride):
strides = [stride] + [1]*(num_blocks-1)
layers = []
for stride in strides:
layers.append(block(self.in_planes, planes, stride))
self.in_planes = planes * block.expansion
return nn.Sequential(*layers)
def forward(self, x):
out = F.relu(self.bn1(self.conv1(x)))#32x32
out = self.MaxPool2d(out)#16x16
out = self.layer1(out)
out = self.layer2(out)
out = self.layer3(out)
out = self.layer4(out)
out = F.avg_pool2d(out, 8)
out = self.linear(out)
return out
in train_model(model, criterion, optimizer, optimizer_name, learning_rate, num_epochs)
33 with torch.set_grad_enabled(True):
34 # print(input1.dtype, input2.dtype)
—> 35 outputs = model(input1, input2)
36 # dummy_img = outputs
37 _, preds = torch.max(outputs, 1)
~/anaconda3/envs/pytorch1/lib/python3.6/site-packages/torch/nn/modules/module.py in call(self, *input, **kwargs)
475 result = self._slow_forward(*input, **kwargs)
476 else:
–> 477 result = self.forward(*input, **kwargs)
478 for hook in self._forward_hooks.values():
479 hook_result = hook(self, input, result)
in forward(self, x1, x2)
27 def forward(self,x1,x2):
28 print(x1.shape, x2.shape)
—> 29 feat1 = self.pretrain_place.forward(x1)
30 # print(‘feat1’, feat1.shape)
31 x2 = self.branch1(x2)
~/Research/128size_modelpy/ResNet64.py in forward(self, x)
95 out = self.layer4(out)
96 out = F.avg_pool2d(out, 8)
—> 97 out = self.linear(out)
98 return out
99
TypeError: avg_pool2d(): argument ‘input’ (position 1) must be Tensor, not MaxPool2d