# -*- coding: utf-8 -*-
"""
Created on Tue Sep 4 21:17:05 2018
@author: www
"""
import sys
sys.path.append("...")
import numpy as np
import torch
from torch import nn
import torch.nn.functional as F
from torch.autograd import Variable
from torchvision.datasets import CIFAR10
def conv3x3(in_channel, out_channel, stride=1):
return nn.Conv2d(in_channel, out_channel, 3, stride=stride, padding=1, bias=False)
class residual_block(nn.Module):
def __init__(self, in_channel, out_channel, same_shape=True):
super(residual_block, self).__init__()
self.same_shape = same_shape
stride = 1 if self.same_shape else 2
self.conv1 = conv3x3(in_channel, out_channel, stride=stride)
self.bn1 = nn.BatchNorm2d(out_channel)
self.conv2 = conv3x3(out_channel, out_channel)
self.bn2 = nn.BatchNorm2d(out_channel)
if not self.same_shape:
self.conv3 = nn.Conv2d(in_channel, out_channel, 1, stride=stride)
def forward(self, x):
out = self.conv1(x)
out = F.relu(self.bn1(out), True)
out = self.conv2(out)
out = F.relu(self.bn2(out), True)
if not self.same_shape:
x = self.conv3(x)
return F.relu(x+out, True)
#我们测试一下一个 residual block 的输入和输出
# 输入输出形状相同
test_net = residual_block(32, 32)
test_x = Variable(torch.zeros(1, 32, 96, 96))
print('input:{}'.format(test_x.shape))
test_y = test_net(test_x)
print('output:{}'.format(test_y.shape))
## 输入输出形状不同
test_net = residual_block(32, 32, False)
test_x = Variable(torch.zeros(1, 32, 96, 96))
print('input: {}'.format(test_x.shape))
test_y = test_net(test_x)
print('output: {}'.format(test_y.shape))
#下面我们尝试实现一个 ResNet，它就是 residual block 模块的堆叠
class resnet(nn.Module):
def __init__(self, in_channel, num_classes, verbose = False):
super(resnet, self).__init__()
self.verbose = verbose
self.block1 = nn.Conv2d(in_channel, 64, 7, 2)
self.block2 = nn.Sequential(
nn.MaxPool2d(3, 2),
residual_block(64, 64),
residual_block(64, 64)
)
self.block3 = nn.Sequential(
residual_block(64, 128, False),
residual_block(128, 128)
)
self.block4 = nn.Sequential(
residual_block(128, 256, False),
residual_block(256, 256)
)
self.block5 = nn.Sequential(
residual_block(256, 512, False),
residual_block(512, 512),
nn.AvgPool2d(3)
)
self.classifier = nn.Linear(512, num_classes)
def forward(self, x):
x = self.block1(x)
if self.verbose:
print('block 1 output: {}'.format(x.shape))
x = self.block2(x)
if self.verbose:
print('block 2 output: {}'.format(x.shape))
x = self.block3(x)
if self.verbose:
print('block 3 output: {}'.format(x.shape))
x = self.block4(x)
if self.verbose:
print('block 4 output: {}'.format(x.shape))
x = self.block5(x)
if self.verbose:
print('block 5 output: {}'.format(x.shape))
x = x.view(x.shape[0], -1)
x = self.classifier(x)
return x
#输出一下每个 block 之后的大小
test_net = resnet(3, 10, True)
test_x = Variable(torch.zeros(1, 3, 96, 96))
test_y = test_net(test_x)
print('output: {}'.format(test_y.shape))
def data_tf(x):
x = x.resize((96, 96), 2) # 将图片放大到 96 x 96
x = np.array(x, dtype='float32') / 255
x = (x - 0.5) / 0.5 # 标准化，这个技巧之后会讲到
x = x.transpose((2, 0, 1)) # 将 channel 放到第一维，只是 pytorch 要求的输入方式
x = torch.from_numpy(x)
return x
train_set = CIFAR10('./data', train=True, transform=data_tf)
train_data = torch.utils.data.DataLoader(train_set, batch_size=64, shuffle=True)
test_set = CIFAR10('./data', train=False, transform=data_tf)
test_data = torch.utils.data.DataLoader(test_set, batch_size=128, shuffle=False)
net = resnet(3, 10)
optimizer = torch.optim.SGD(net.parameters(), lr=0.01)
criterion = nn.CrossEntropyLoss()
from datetime import datetime
def get_acc(output, label):
total = output.shape[0]
_, pred_label = output.max(1)
num_correct = (pred_label == label).sum().data[0]
return num_correct / total
def train(net, train_data, valid_data, num_epochs, optimizer, criterion):
if torch.cuda.is_available():
net = net.cuda()
prev_time = datetime.now()
for epoch in range(num_epochs):
train_loss = 0
train_acc = 0
net = net.train()
for im, label in train_data:
if torch.cuda.is_available():
im = Variable(im.cuda())
label = Variable(label.cuda())
else:
im = Variable(im)
label = Variable(label)
#forward
output = net(im)
loss = criterion(output, label)
#forward
optimizer.zero_grad()
loss.backward()
optimizer.step()
train_loss += loss.data[0]
train_acc += get_acc(output, label)
cur_time = datetime.now()
h, remainder = divmod((cur_time-prev_time).seconds, 3600)
m, s = divmod(remainder, 60)
time_str = "Time %02d:%02d:%02d" % (h, m, s)
if valid_data is not None:
valid_loss = 0
valid_acc = 0
net = net.eval()
for im, label in valid_data:
if torch.cuda.is_available():
im = Variable(im.cuda(), volatile=True)
label = Variable(label.cuda(), volatile=True)
else:
im = Variable(im, volatile=True)
label = Variable(label, volatile=True)
output = net(im)
loss = criterion(output, label)
valid_loss += loss.item()
valid_acc += get_acc(output, label)
epoch_str = (
"Epoch %d. Train Loss: %f, Train Acc: %f, Valid Loss: %f, Valid Acc: %f, "
% (epoch, train_loss / len(train_data),
train_acc / len(train_data), valid_loss / len(valid_data),
valid_acc / len(valid_data)))
else:
epoch_str = ("Epoch %d. Train Loss: %f, Train Acc: %f, " %
(epoch, train_loss / len(train_data),
train_acc / len(train_data)))
prev_time = cur_time
print(epoch_str + time_str)
train(net, train_data, test_data, 20, optimizer, criterion)
#ResNet 使用跨层通道使得训练非常深的卷积神经网络成为可能。同样它使用很简单的卷积层配置，使得其拓展更加简单。
