pytorch resnet实现

官方github上已经有了pytorch基础模型的实现，链接

但是其中一些模型，尤其是resnet，都是用函数生成的各个层，自己看起来是真的难受！

所以自己按照caffe的样子，写一个pytorch的resnet18模型，当然和1000分类模型不同，模型做了一些修改，输入48*48的3通道图片，输出7类。

 

import torch.nn as nn
import torch.nn.functional as F

class ResNet18Model(nn.Module):
	def __init__(self):
		super().__init__()

		self.bn64_0 = nn.BatchNorm2d(64)
		self.bn64_1 = nn.BatchNorm2d(64)
		self.bn64_2 = nn.BatchNorm2d(64)
		self.bn64_3 = nn.BatchNorm2d(64)
		self.bn64_4 = nn.BatchNorm2d(64)


		self.bn128_0 = nn.BatchNorm2d(128)
		self.bn128_1 = nn.BatchNorm2d(128)
		self.bn128_2 = nn.BatchNorm2d(128)
		self.bn128_3 = nn.BatchNorm2d(128)

		self.bn256_0 = nn.BatchNorm2d(256)
		self.bn256_1 = nn.BatchNorm2d(256)
		self.bn256_2 = nn.BatchNorm2d(256)
		self.bn256_3 = nn.BatchNorm2d(256)

		self.bn512_0 = nn.BatchNorm2d(512)
		self.bn512_1 = nn.BatchNorm2d(512)
		self.bn512_2 = nn.BatchNorm2d(512)
		self.bn512_3 = nn.BatchNorm2d(512)


		self.shortcut_straight_0 = nn.Sequential()
		self.shortcut_straight_1 = nn.Sequential()
		self.shortcut_straight_2 = nn.Sequential()
		self.shortcut_straight_3 = nn.Sequential()
		self.shortcut_straight_4 = nn.Sequential()


		self.shortcut_conv_bn_64_128_0 = nn.Sequential(nn.Conv2d(64, 128, kernel_size=1, stride=2, bias=False),nn.BatchNorm2d(128))

		self.shortcut_conv_bn_128_256_0 = nn.Sequential(nn.Conv2d(128, 256, kernel_size=1, stride=2, bias=False),nn.BatchNorm2d(256))

		self.shortcut_conv_bn_256_512_0 = nn.Sequential(nn.Conv2d(256, 512, kernel_size=1, stride=2, bias=False),nn.BatchNorm2d(512))


		self.conv_w3_h3_in3_out64_s1_p1_0 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False)

		self.conv_w3_h3_in64_out64_s1_p1_0 = nn.Conv2d(64, 64, kernel_size=3, stride=1, padding=1, bias=False)
		self.conv_w3_h3_in64_out64_s1_p1_1 = nn.Conv2d(64, 64, kernel_size=3, stride=1, padding=1, bias=False)
		self.conv_w3_h3_in64_out64_s1_p1_2 = nn.Conv2d(64, 64, kernel_size=3, stride=1, padding=1, bias=False)
		self.conv_w3_h3_in64_out64_s1_p1_3 = nn.Conv2d(64, 64, kernel_size=3, stride=1, padding=1, bias=False)


		self.conv_w3_h3_in64_out128_s2_p1_0 = nn.Conv2d(64, 128, kernel_size=3, stride=2, padding=1, bias=False)

		self.conv_w3_h3_in128_out128_s1_p1_0 = nn.Conv2d(128, 128, kernel_size=3, stride=1, padding=1, bias=False)
		self.conv_w3_h3_in128_out128_s1_p1_1 = nn.Conv2d(128, 128, kernel_size=3, stride=1, padding=1, bias=False)
		self.conv_w3_h3_in128_out128_s1_p1_2 = nn.Conv2d(128, 128, kernel_size=3, stride=1, padding=1, bias=False)


		self.conv_w3_h3_in128_out256_s2_p1_0 = nn.Conv2d(128, 256, kernel_size=3, stride=2, padding=1, bias=False)

		self.conv_w3_h3_in256_out256_s1_p1_0 = nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1, bias=False)
		self.conv_w3_h3_in256_out256_s1_p1_1 = nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1, bias=False)
		self.conv_w3_h3_in256_out256_s1_p1_2 = nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1, bias=False)


		self.conv_w3_h3_in256_out512_s2_p1_0 = nn.Conv2d(256, 512, kernel_size=3, stride=2, padding=1, bias=False)

		self.conv_w3_h3_in512_out512_s1_p1_0 = nn.Conv2d(512, 512, kernel_size=3, stride=1, padding=1, bias=False)
		self.conv_w3_h3_in512_out512_s1_p1_1 = nn.Conv2d(512, 512, kernel_size=3, stride=1, padding=1, bias=False)
		self.conv_w3_h3_in512_out512_s1_p1_2 = nn.Conv2d(512, 512, kernel_size=3, stride=1, padding=1, bias=False)


		self.avg_pool_0 = nn.AdaptiveAvgPool2d((1, 1))
		self.fc_512_7_0 = nn.Linear(512, 7)
		self.dropout_0 = nn.Dropout(p=0.5)




	def forward(self, x):

		# 48*48*3
		t = self.conv_w3_h3_in3_out64_s1_p1_0(x) #48*48*64
		t = self.bn64_0(t)
		y1 = F.relu(t)


		t = self.conv_w3_h3_in64_out64_s1_p1_0(y1) #48*48*64
		t = self.bn64_1(t) 
		y2 = F.relu(t)

		t = self.conv_w3_h3_in64_out64_s1_p1_1(y2) #48*48*64
		t = self.bn64_2(t)
		t += self.shortcut_straight_0(y1)
		y3 = F.relu(t)


		t = self.conv_w3_h3_in64_out64_s1_p1_2(y3) #48*48*64
		t = self.bn64_3(t)
		y4 = F.relu(t)

		t = self.conv_w3_h3_in64_out64_s1_p1_3(y4) #48*48*64
		t = self.bn64_4(t)
		t += self.shortcut_straight_1(y3)
		y5 = F.relu(t)


		t = self.conv_w3_h3_in64_out128_s2_p1_0(y5) #24*24*128
		t = self.bn128_0(t)
		y6 = F.relu(t)

		t = self.conv_w3_h3_in128_out128_s1_p1_0(y6) #24*24*128
		t = self.bn128_1(t)
		t += self.shortcut_conv_bn_64_128_0(y5)
		y7 = F.relu(t)


		t = self.conv_w3_h3_in128_out128_s1_p1_1(y7) #24*24*128
		t = self.bn128_2(t)
		y8 = F.relu(t)

		t = self.conv_w3_h3_in128_out128_s1_p1_2(y8) #24*24*128
		t = self.bn128_3(t)
		t += self.shortcut_straight_2(y7)
		y9 = F.relu(t)


		t = self.conv_w3_h3_in128_out256_s2_p1_0(y9) #12*12*256
		t = self.bn256_0(t)
		y10 = F.relu(t)

		t = self.conv_w3_h3_in256_out256_s1_p1_0(y10) #12*12*256
		t = self.bn256_1(t)
		t += self.shortcut_conv_bn_128_256_0(y9)
		y11 = F.relu(t)


		t = self.conv_w3_h3_in256_out256_s1_p1_1(y11) #12*12*256
		t = self.bn256_2(t)
		y12 = F.relu(t)

		t = self.conv_w3_h3_in256_out256_s1_p1_2(y12) #12*12*256
		t = self.bn256_3(t)
		t += self.shortcut_straight_3(y11)
		y13 = F.relu(t)


		t = self.conv_w3_h3_in256_out512_s2_p1_0(y13) #6*6*512
		t = self.bn512_0(t)
		y14 = F.relu(t)

		t = self.conv_w3_h3_in512_out512_s1_p1_0(y14) #6*6*512
		t = self.bn512_1(t)
		t += self.shortcut_conv_bn_256_512_0(y13)
		y15 = F.relu(t)


		t = self.conv_w3_h3_in512_out512_s1_p1_1(y15) #6*6*512
		t = self.bn512_2(t)
		y16 = F.relu(t)

		t = self.conv_w3_h3_in512_out512_s1_p1_2(y16) #6*6*512
		t = self.bn512_3(t)
		t += self.shortcut_straight_4(y15)
		y17 = F.relu(t)


		out = self.avg_pool_0(y17) #1*1*512		
		out = out.view(out.size(0), -1)
		out = self.dropout_0(out)
		out = self.fc_512_7_0(out)

		return out



if __name__ == '__main__':
	net = ResNet18Model()
	# print(net)

	import torch
	net_in = torch.rand(1, 3, 48, 48)
	net_out = net(net_in)
	print(net_out)
	print(net_out.size())