pytorch学习(十九) |
您所在的位置：网站首页 › tensorflow训练过程 › pytorch学习(十九) |
|
前言
在训练CNN网络时候，如何实时显示训练过程的数据，比如Loss, Accuracy等， 将这些数据可视化显示有助于我们进行模型调参，模型改进优化。本章节内容将基于visdom可视化工具绘制训练过程的Loss, Acc曲线。 关于visdom的基本用法，请参考之前系列的文章。 开发/测试环境 Ubuntu 18.04 Anaconda3 pycharm visdom pytorch 目的 使用MNIST手写体数据集训练LeNet-5网络 使用visdom实时可视化训练的Loss,Accuracy曲线 过程 定义CNN网络直接使用pytorch官网的例子(做一次代码搬运工) 网络输入： N x 1 x 32 x 32 （N表示min_batch size） 网络输出： N x 1 x 10 (10个类别) 代码 net.py import torch import torch.nn as nn import torch.nn.functional as F class Net(nn.Module): def __init__(self): super(Net, self).__init__() # 1 input image channel, 6 output channels, 5x5 square convolution # kernel self.conv1 = nn.Conv2d(1, 6, 5) self.conv2 = nn.Conv2d(6, 16, 5) # an affine operation: y = Wx + b self.fc1 = nn.Linear(16 * 5 * 5, 120) self.fc2 = nn.Linear(120, 84) self.fc3 = nn.Linear(84, 10) def forward(self, x): # Max pooling over a (2, 2) window x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2)) # If the size is a square you can only specify a single number x = F.max_pool2d(F.relu(self.conv2(x)), 2) x = x.view(-1, self.num_flat_features(x)) x = F.relu(self.fc1(x)) x = F.relu(self.fc2(x)) x = self.fc3(x) return x def num_flat_features(self, x): size = x.size()[1:] # all dimensions except the batch dimension num_features = 1 for s in size: num_features *= s return num_features 准备数据集 训练集 验证集 使用torchvision提供的MNIST数据集，不用提前下载。 注意地方： MNIST数据的图像为28 x 28 x1, 但是定义的网络输入的N x 1 x 32 x 32, 因此对数据进行了Resize((32, 32)) mport torch import torchvision import numpy as np import matplotlib.pyplot as plt import visdom import torch.nn as nn import torch.optim as optim import torchvision.transforms as transforms from torch.utils.data import DataLoader import net import utils dataset_dir = '/media/weipenghui/Extra/MNIST' transform = transforms.Compose([transforms.Resize((32, 32)), transforms.ToTensor()]) batch_size = 64 train_dataset = torchvision.datasets.MNIST(root=dataset_dir, train=True, transform=transform) val_dataset = torchvision.datasets.MNIST(root=dataset_dir, train=False, transform=transform) print('train dataset: {} \nval dataset: {}'.format(len(train_dataset), len(val_dataset))) train_dataloader = DataLoader(dataset=train_dataset, batch_size=batch_size, shuffle=True, num_workers=4) val_dataloader = DataLoader(dataset=val_dataset, batch_size=batch_size, shuffle=False, num_workers=4) # 显示一个batch viz = visdom.Visdom(env='train-mnist') viz.image(torchvision.utils.make_grid(next(iter(train_dataloader))[0], nrow=8), win='train-image') plt.figure() utils.imshow(next(iter(train_dataloader))) plt.show()matplotlib显示效果： image.pngvisdom显示效果： image.png 训练网络，可视化Loss,AccuracyLoss, Accuracy的统计： batch_size设置为64， 迭代一次即跑完64张图像。本人设置每迭代200次统计一次Train Loss, 并且进行一次完整的测试，分别统计Train Acc, Val Acc， 然后将数据发送给visdom服务端，实时显示。 # ------------------模型，优化方法------------------------------ device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu') net = net.Net() net.to(device) optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9) scheduler = optim.lr_scheduler.StepLR(optimizer, step_size=10, gamma=0.5) loss_fc = nn.CrossEntropyLoss() # -----------------训练--------------------------------------- loss_win = viz.line(np.arange(10)) acc_win = viz.line(X=np.column_stack((np.array(0), np.array(0))), Y=np.column_stack((np.array(0), np.array(0)))) iter_count = 0 for epoch in range(20): running_loss = 0.0 tr_loss = 0.0 tr_acc = 0.0 ts_acc = 0.0 tr_total = 0 tr_correct = 0 ts_total = 0 ts_correct = 0 scheduler.step() for i, sample_batch in enumerate(train_dataloader): inputs = sample_batch[0].to(device) labels = sample_batch[1].to(device) net.train() optimizer.zero_grad() outputs = net(inputs) loss = loss_fc(outputs, labels) loss.backward() optimizer.step() running_loss += loss.item() tr_total += labels.size(0) tr_correct += (torch.max(outputs, 1)[1] == labels).sum().item() if i % 200 == 199: # test for sample_batch in val_dataloader: inputs = sample_batch[0].to(device) labels = sample_batch[1].to(device) net.eval() outputs = net(inputs) _, prediction = torch.max(outputs, 1) ts_correct += (prediction == labels).sum().item() ts_total += labels.size(0) tr_loss = running_loss / 200 tr_acc = tr_correct / tr_total ts_acc = ts_correct / ts_total iter_count += 200 if iter_count == 200: viz.line(Y=np.array([tr_loss]), X=np.array([iter_count]), update='replace', win=loss_win) viz.line(Y=np.column_stack((np.array([tr_acc]), np.array([ts_acc]))), X=np.column_stack((np.array([iter_count]), np.array([iter_count]))), win=acc_win, update='replace', opts=dict(legned=['Train_acc', 'Val_acc'])) else: viz.line(Y=np.array([tr_loss]), X=np.array([iter_count]), update='append', win=loss_win) viz.line(Y=np.column_stack((np.array([tr_acc]), np.array([ts_acc]))), X=np.column_stack((np.array([iter_count]), np.array([iter_count]))), win=acc_win, update='append') running_loss = 0 tr_total = 0 tr_correct = 0 ts_total = 0 ts_correct = 0 print('Train finish!') torch.save(net.state_dict(), './model/model_10_2_epoch.pth') 训练输出Train loss Train acc Val acc mini_batch图像 image.png Train Loss Train Val accuracy最终，验证集的Accuracy达到98%以上。 完整工程 train.py import torch import torchvision import numpy as np import matplotlib.pyplot as plt import visdom import torch.nn as nn import torch.optim as optim import torchvision.transforms as transforms from torch.utils.data import DataLoader import net import utils dataset_dir = '/media/weipenghui/Extra/MNIST' transform = transforms.Compose([transforms.Resize((32, 32)), transforms.ToTensor()]) batch_size = 64 train_dataset = torchvision.datasets.MNIST(root=dataset_dir, train=True, transform=transform) val_dataset = torchvision.datasets.MNIST(root=dataset_dir, train=False, transform=transform) print('train dataset: {} \nval dataset: {}'.format(len(train_dataset), len(val_dataset))) train_dataloader = DataLoader(dataset=train_dataset, batch_size=batch_size, shuffle=True, num_workers=4) val_dataloader = DataLoader(dataset=val_dataset, batch_size=batch_size, shuffle=False, num_workers=4) # 显示一个batch viz = visdom.Visdom(env='train-mnist') viz.image(torchvision.utils.make_grid(next(iter(train_dataloader))[0], nrow=8), win='train-image') # plt.figure() # utils.imshow(next(iter(train_dataloader))) # plt.show() # ------------------模型，优化方法------------------------------ device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu') net = net.Net() net.to(device) optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9) scheduler = optim.lr_scheduler.StepLR(optimizer, step_size=10, gamma=0.5) loss_fc = nn.CrossEntropyLoss() # -----------------训练--------------------------------------- loss_win = viz.line(np.arange(10)) acc_win = viz.line(X=np.column_stack((np.array(0), np.array(0))), Y=np.column_stack((np.array(0), np.array(0)))) iter_count = 0 for epoch in range(20): running_loss = 0.0 tr_loss = 0.0 tr_acc = 0.0 ts_acc = 0.0 tr_total = 0 tr_correct = 0 ts_total = 0 ts_correct = 0 scheduler.step() for i, sample_batch in enumerate(train_dataloader): inputs = sample_batch[0].to(device) labels = sample_batch[1].to(device) net.train() optimizer.zero_grad() outputs = net(inputs) loss = loss_fc(outputs, labels) loss.backward() optimizer.step() running_loss += loss.item() tr_total += labels.size(0) tr_correct += (torch.max(outputs, 1)[1] == labels).sum().item() if i % 200 == 199: # test for sample_batch in val_dataloader: inputs = sample_batch[0].to(device) labels = sample_batch[1].to(device) net.eval() outputs = net(inputs) _, prediction = torch.max(outputs, 1) ts_correct += (prediction == labels).sum().item() ts_total += labels.size(0) tr_loss = running_loss / 200 tr_acc = tr_correct / tr_total ts_acc = ts_correct / ts_total iter_count += 200 if iter_count == 200: viz.line(Y=np.array([tr_loss]), X=np.array([iter_count]), update='replace', win=loss_win) viz.line(Y=np.column_stack((np.array([tr_acc]), np.array([ts_acc]))), X=np.column_stack((np.array([iter_count]), np.array([iter_count]))), win=acc_win, update='replace', opts=dict(legned=['Train_acc', 'Val_acc'])) else: viz.line(Y=np.array([tr_loss]), X=np.array([iter_count]), update='append', win=loss_win) viz.line(Y=np.column_stack((np.array([tr_acc]), np.array([ts_acc]))), X=np.column_stack((np.array([iter_count]), np.array([iter_count]))), win=acc_win, update='append') running_loss = 0 tr_total = 0 tr_correct = 0 ts_total = 0 ts_correct = 0 print('Train finish!') torch.save(net.state_dict(), './model/model_10_2_epoch.pth') net.py import torch import torch.nn as nn import torch.nn.functional as F class Net(nn.Module): def __init__(self): super(Net, self).__init__() # 1 input image channel, 6 output channels, 5x5 square convolution # kernel self.conv1 = nn.Conv2d(1, 6, 5) self.conv2 = nn.Conv2d(6, 16, 5) # an affine operation: y = Wx + b self.fc1 = nn.Linear(16 * 5 * 5, 120) self.fc2 = nn.Linear(120, 84) self.fc3 = nn.Linear(84, 10) def forward(self, x): # Max pooling over a (2, 2) window x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2)) # If the size is a square you can only specify a single number x = F.max_pool2d(F.relu(self.conv2(x)), 2) x = x.view(-1, self.num_flat_features(x)) x = F.relu(self.fc1(x)) x = F.relu(self.fc2(x)) x = self.fc3(x) return x def num_flat_features(self, x): size = x.size()[1:] # all dimensions except the batch dimension num_features = 1 for s in size: num_features *= s return num_features utils.py import numpy as np import torch from torchvision.utils import make_grid import matplotlib.pyplot as plt def imshow(sample_batch): inputs, labels = sample_batch images_transformed = make_grid(inputs, nrow=4, pad_value=255) images_transformed = np.transpose(images_transformed.numpy(), (1, 2, 0)) plt.imshow(images_transformed) |
| CopyRight 2018-2019 办公设备维修网 版权所有 豫ICP备15022753号-3 |