# coding:utf8
import torch
from torch import nn, optim# nn 神經(jīng)網(wǎng)絡(luò)模塊 optim優(yōu)化函數(shù)模塊
from torch.utils.data import DataLoader
from torch.autograd import Variable
from torchvision import transforms, datasets
from visdom import Visdom  # 可視化處理模塊
import time
import numpy as np
# 可視化app
viz = Visdom()
# 超參數(shù)
BATCH_SIZE = 40
LR = 1e-3
EPOCH = 2
# 判斷是否使用gpu
USE_GPU = True
if USE_GPU:
 gpu_status = torch.cuda.is_available()
else:
 gpu_status = False
transform=transforms.Compose([transforms.ToTensor(),transforms.Normalize((0.1307,), (0.3081,))])
# 數(shù)據(jù)引入
train_dataset = datasets.MNIST('../data', True, transform, download=False)
test_dataset = datasets.MNIST('../data', False, transform)
train_loader = DataLoader(train_dataset, BATCH_SIZE, True)
# 為加快測試，把測試數(shù)據(jù)從10000縮小到2000
test_data = torch.unsqueeze(test_dataset.test_data, 1)[:1500]
test_label = test_dataset.test_labels[:1500]
# visdom可視化部分?jǐn)?shù)據(jù)
viz.images(test_data[:100], nrow=10)
#viz.images(test_data[:100], nrow=10)
# 為防止可視化視窗重疊現(xiàn)象，停頓0.5秒
time.sleep(0.5)
if gpu_status:
 test_data = test_data.cuda()
test_data = Variable(test_data, volatile=True).float()
# 創(chuàng)建線圖可視化窗口
line = viz.line(np.arange(10))
# 創(chuàng)建cnn神經(jīng)網(wǎng)絡(luò)
class CNN(nn.Module):
 def __init__(self, in_dim, n_class):
  super(CNN, self).__init__()
  self.conv = nn.Sequential(
# channel 為信息高度 padding為圖片留白 kernel_size 掃描模塊size（5x5）
nn.Conv2d(in_channels=in_dim, out_channels=16,kernel_size=5,stride=1, padding=2),
nn.ReLU(),
# 平面縮減 28x28 >> 14*14
nn.MaxPool2d(kernel_size=2),
nn.Conv2d(16, 32, 3, 1, 1),
nn.ReLU(),
# 14x14 >> 7x7
nn.MaxPool2d(2)
  )
  self.fc = nn.Sequential(
nn.Linear(32*7*7, 120),
nn.Linear(120, n_class)
  )
 def forward(self, x):
  out = self.conv(x)
  out = out.view(out.size(0), -1)
  out = self.fc(out)
  return out
net = CNN(1,10)
if gpu_status :
 net = net.cuda()
 #print("#"*26, "使用gpu", "#"*26)
else:
 #print("#" * 26, "使用cpu", "#" * 26)
 pass
# loss、optimizer 函數(shù)設(shè)置
loss_f = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=LR)
# 起始時間設(shè)置
start_time = time.time()
# 可視化所需數(shù)據(jù)點(diǎn)
time_p, tr_acc, ts_acc, loss_p = [], [], [], []
# 創(chuàng)建可視化數(shù)據(jù)視窗
text = viz.text("<h1>convolution Nueral Network</h1>")
for epoch in range(EPOCH):
 # 由于分批次學(xué)習(xí)，輸出loss為一批平均，需要累積or平均每個batch的loss，acc
 sum_loss, sum_acc, sum_step = 0., 0., 0.
 for i, (tx, ty) in enumerate(train_loader, 1):
  if gpu_status:
tx, ty = tx.cuda(), ty.cuda()
  tx = Variable(tx)
  ty = Variable(ty)
  out = net(tx)
  loss = loss_f(out, ty)
  #print(tx.size())
  #print(ty.size())
  #print(out.size())
  sum_loss += loss.item()*len(ty)
  #print(sum_loss)
  pred_tr = torch.max(out,1)[1]
  sum_acc += sum(pred_tr==ty).item()
  sum_step += ty.size(0)
  # 學(xué)習(xí)反饋
  optimizer.zero_grad()
  loss.backward()
  optimizer.step()
  # 每40個batch可視化一下數(shù)據(jù)
  if i % 40 == 0:
if gpu_status:
 test_data = test_data.cuda()
test_out = net(test_data)
print(test_out.size())
# 如果用gpu運(yùn)行out數(shù)據(jù)為cuda格式需要.cpu（）轉(zhuǎn)化為cpu數(shù)據(jù) 在進(jìn)行比較
pred_ts = torch.max(test_out, 1)[1].cpu().data.squeeze()
print(pred_ts.size())
rightnum = pred_ts.eq(test_label.view_as(pred_ts)).sum().item()
#rightnum =sum(pred_tr==ty).item()
#  sum_acc += sum(pred_tr==ty).item()
acc =  rightnum/float(test_label.size(0))
print("epoch: [{}/{}] | Loss: {:.4f} | TR_acc: {:.4f} | TS_acc: {:.4f} | Time: {:.1f}".format(epoch+1, EPOCH,
  sum_loss/(sum_step), sum_acc/(sum_step), acc, time.time()-start_time))
# 可視化部分
time_p.append(time.time()-start_time)
tr_acc.append(sum_acc/sum_step)
ts_acc.append(acc)
loss_p.append(sum_loss/sum_step)
viz.line(X=np.column_stack((np.array(time_p), np.array(time_p), np.array(time_p))),
Y=np.column_stack((np.array(loss_p), np.array(tr_acc), np.array(ts_acc))),
win=line,
opts=dict(legend=["Loss", "TRAIN_acc", "TEST_acc"]))
# visdom text 支持html語句
viz.text("<p style='color:red'>epoch:{}</p><br><p style='color:blue'>Loss:{:.4f}</p><br>"
"<p style='color:BlueViolet'>TRAIN_acc:{:.4f}</p><br><p style='color:orange'>TEST_acc:{:.4f}</p><br>"
"<p style='color:green'>Time:{:.2f}</p>".format(epoch, sum_loss/sum_step, sum_acc/sum_step, acc,
time.time()-start_time),
win=text)
sum_loss, sum_acc, sum_step = 0., 0., 0.