pytorch中网络和损失函数可视化的示例分析

小编给大家分享一下pytorch中网络和损失函数可视化的示例分析，相信大部分人都还不怎么了解，因此分享这篇文章给大家参考一下，希望大家阅读完这篇文章后大有收获，下面让我们一起去了解一下吧！

1.效果

2.环境

1.pytorch
2.visdom
3.python3.5

3.用到的代码

# coding:utf8import torchfrom torch import nn, optim   # nn 神经网络模块 optim优化函数模块from torch.utils.data import DataLoaderfrom torch.autograd import Variablefrom torchvision import transforms, datasetsfrom visdom import Visdom  # 可视化处理模块import timeimport numpy as np# 可视化appviz = Visdom()# 超参数BATCH_SIZE = 40LR = 1e-3EPOCH = 2# 判断是否使用gpuUSE_GPU = Trueif USE_GPU:    gpu_status = torch.cuda.is_available()else:    gpu_status = Falsetransform=transforms.Compose([transforms.ToTensor(),transforms.Normalize((0.1307,), (0.3081,))])# 数据引入train_dataset = datasets.MNIST('../data', True, transform, download=False)test_dataset = datasets.MNIST('../data', False, transform)train_loader = DataLoader(train_dataset, BATCH_SIZE, True)# 为加快测试，把测试数据从10000缩小到2000test_data = torch.unsqueeze(test_dataset.test_data, 1)[:1500]test_label = test_dataset.test_labels[:1500]# visdom可视化部分数据viz.images(test_data[:100], nrow=10)#viz.images(test_data[:100], nrow=10)# 为防止可视化视窗重叠现象，停顿0.5秒time.sleep(0.5)if gpu_status:    test_data = test_data.cuda()test_data = Variable(test_data, volatile=True).float()# 创建线图可视化窗口line = viz.line(np.arange(10))# 创建cnn神经网络class CNN(nn.Module):    def __init__(self, in_dim, n_class):        super(CNN, self).__init__()        self.conv = nn.Sequential(            # channel 为信息高度 padding为图片留白 kernel_size 扫描模块size（5x5）            nn.Conv2d(in_channels=in_dim, out_channels=16,kernel_size=5,stride=1, padding=2),            nn.ReLU(),            # 平面缩减 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 outnet = 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 函数设置loss_f = nn.CrossEntropyLoss()optimizer = optim.Adam(net.parameters(), lr=LR)# 起始时间设置start_time = time.time()# 可视化所需数据点time_p, tr_acc, ts_acc, loss_p = [], [], [], []# 创建可视化数据视窗text = viz.text("
convolution Nueral Network
")for epoch in range(EPOCH):    # 由于分批次学习，输出loss为一批平均，需要累积or平均每个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)        # 学习反馈        optimizer.zero_grad()        loss.backward()        optimizer.step()        # 每40个batch可视化一下数据        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运行out数据为cuda格式需要.cpu（）转化为cpu数据 在进行比较            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))            # 可视化部分            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语句            viz.text("
epoch:{}

Loss:{:.4f}

"                     "
TRAIN_acc:{:.4f}

TEST_acc:{:.4f}

"                     "
Time:{:.2f}
".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.

以上是"pytorch中网络和损失函数可视化的示例分析"这篇文章的所有内容，感谢各位的阅读！相信大家都有了一定的了解，希望分享的内容对大家有所帮助，如果还想学习更多知识，欢迎关注行业资讯频道！