Last active
March 4, 2023 19:45
-
-
Save xmfbit/b27cdbff68870418bdb8cefa86a2d558 to your computer and use it in GitHub Desktop.
Revisions
-
xmfbit revised this gist
May 12, 2018 . 1 changed file with 11 additions and 8 deletions.There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode charactersOriginal file line number Diff line number Diff line change @@ -1,3 +1,4 @@ import os import torch import torch.nn as nn from torch.autograd import Variable @@ -9,11 +10,13 @@ use_cuda = torch.cuda.is_available() root = './data' if not os.path.exists(root): os.mkdir(root) trans = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (1.0,))]) # if not exist, download mnist dataset train_set = dset.MNIST(root=root, train=True, transform=trans, download=True) test_set = dset.MNIST(root=root, train=False, transform=trans, download=True) batch_size = 100 @@ -75,7 +78,7 @@ def name(self): optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.9) criterion = nn.CrossEntropyLoss() for epoch in xrange(10): # trainning @@ -86,7 +89,7 @@ def name(self): x, target = x.cuda(), target.cuda() x, target = Variable(x), Variable(target) out = model(x) loss = criterion(out, target) ave_loss = ave_loss * 0.9 + loss.data[0] * 0.1 loss.backward() optimizer.step() @@ -98,10 +101,10 @@ def name(self): total_cnt = 0 for batch_idx, (x, target) in enumerate(test_loader): if use_cuda: x, target = x.cuda(), target.cuda() x, target = Variable(x, volatile=True), Variable(target, volatile=True) out = model(x) loss = criterion(out, target) _, pred_label = torch.max(out.data, 1) total_cnt += x.data.size()[0] correct_cnt += (pred_label == target.data).sum() -
Jan 27, 2018 . 1 changed file with 54 additions and 33 deletions.There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode charactersOriginal file line number Diff line number Diff line change @@ -6,22 +6,25 @@ import torch.nn.functional as F import torch.optim as optim ## load mnist dataset use_cuda = torch.cuda.is_available() root = './data' download = False # download MNIST dataset or not trans = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (1.0,))]) train_set = dset.MNIST(root=root, train=True, transform=trans, download=download) test_set = dset.MNIST(root=root, train=False, transform=trans) batch_size = 100 train_loader = torch.utils.data.DataLoader( dataset=train_set, batch_size=batch_size, shuffle=True) test_loader = torch.utils.data.DataLoader( dataset=test_set, batch_size=batch_size, shuffle=False) print '==>>> total trainning batch number: {}'.format(len(train_loader)) print '==>>> total testing batch number: {}'.format(len(test_loader)) @@ -33,16 +36,15 @@ def __init__(self): self.fc1 = nn.Linear(28*28, 500) self.fc2 = nn.Linear(500, 256) self.fc3 = nn.Linear(256, 10) def forward(self, x): x = x.view(-1, 28*28) x = F.relu(self.fc1(x)) x = F.relu(self.fc2(x)) x = self.fc3(x) return x def name(self): return "MLP" class LeNet(nn.Module): def __init__(self): @@ -51,45 +53,64 @@ def __init__(self): self.conv2 = nn.Conv2d(20, 50, 5, 1) self.fc1 = nn.Linear(4*4*50, 500) self.fc2 = nn.Linear(500, 10) def forward(self, x): x = F.relu(self.conv1(x)) x = F.max_pool2d(x, 2, 2) x = F.relu(self.conv2(x)) x = F.max_pool2d(x, 2, 2) x = x.view(-1, 4*4*50) x = F.relu(self.fc1(x)) x = self.fc2(x) return x def name(self): return "LeNet" ## training model = LeNet() if use_cuda: model = model.cuda() optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.9) ceriation = nn.CrossEntropyLoss() for epoch in xrange(10): # trainning ave_loss = 0 for batch_idx, (x, target) in enumerate(train_loader): optimizer.zero_grad() if use_cuda: x, target = x.cuda(), target.cuda() x, target = Variable(x), Variable(target) out = model(x) loss = ceriation(out, target) ave_loss = ave_loss * 0.9 + loss.data[0] * 0.1 loss.backward() optimizer.step() if (batch_idx+1) % 100 == 0 or (batch_idx+1) == len(train_loader): print '==>>> epoch: {}, batch index: {}, train loss: {:.6f}'.format( epoch, batch_idx+1, ave_loss) # testing correct_cnt, ave_loss = 0, 0 total_cnt = 0 for batch_idx, (x, target) in enumerate(test_loader): if use_cuda: x, targe = x.cuda(), target.cuda() x, target = Variable(x, volatile=True), Variable(target, volatile=True) out = model(x) loss = ceriation(out, target) _, pred_label = torch.max(out.data, 1) total_cnt += x.data.size()[0] correct_cnt += (pred_label == target.data).sum() # smooth average ave_loss = ave_loss * 0.9 + loss.data[0] * 0.1 if(batch_idx+1) % 100 == 0 or (batch_idx+1) == len(test_loader): print '==>>> epoch: {}, batch index: {}, test loss: {:.6f}, acc: {:.3f}'.format( epoch, batch_idx+1, ave_loss, correct_cnt * 1.0 / total_cnt) torch.save(model.state_dict(), model.name()) -
Mar 4, 2017 .There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode charactersOriginal file line number Diff line number Diff line change @@ -0,0 +1,95 @@ import torch import torch.nn as nn from torch.autograd import Variable import torchvision.datasets as dset import torchvision.transforms as transforms import torch.nn.functional as F import torch.optim as optim ## load mnist dataset root = './data' download = False trans = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (1.0,))]) train_set = dset.MNIST(root=root, train=True, transform=trans, download=download) test_set = dset.MNIST(root=root, train=False, transform=trans) batch_size = 128 kwargs = {'num_workers': 1, 'pin_memory': True} train_loader = torch.utils.data.DataLoader( dataset=train_set, batch_size=batch_size, shuffle=True, **kwargs) test_loader = torch.utils.data.DataLoader( dataset=test_set, batch_size=batch_size, shuffle=False, **kwargs) print '==>>> total trainning batch number: {}'.format(len(train_loader)) print '==>>> total testing batch number: {}'.format(len(test_loader)) ## network class MLPNet(nn.Module): def __init__(self): super(MLPNet, self).__init__() self.fc1 = nn.Linear(28*28, 500) self.fc2 = nn.Linear(500, 256) self.fc3 = nn.Linear(256, 10) self.ceriation = nn.CrossEntropyLoss() def forward(self, x, target): x = x.view(-1, 28*28) x = F.relu(self.fc1(x)) x = F.relu(self.fc2(x)) x = F.relu(self.fc3(x)) loss = self.ceriation(x, target) return x, loss def name(self): return 'mlpnet' class LeNet(nn.Module): def __init__(self): super(LeNet, self).__init__() self.conv1 = nn.Conv2d(1, 20, 5, 1) self.conv2 = nn.Conv2d(20, 50, 5, 1) self.fc1 = nn.Linear(4*4*50, 500) self.fc2 = nn.Linear(500, 10) self.ceriation = nn.CrossEntropyLoss() def forward(self, x, target): x = self.conv1(x) x = F.max_pool2d(x, 2, 2) x = F.relu(x) x = self.conv2(x) x = F.max_pool2d(x, 2, 2) x = F.relu(x) x = x.view(-1, 4*4*50) x = self.fc1(x) x = self.fc2(x) loss = self.ceriation(x, target) return x, loss def name(self): return 'lenet' ## training model = MLPNet().cuda() optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.9) for epoch in xrange(10): # trainning for batch_idx, (x, target) in enumerate(train_loader): optimizer.zero_grad() x, target = Variable(x.cuda()), Variable(target.cuda()) _, loss = model(x, target) loss.backward() optimizer.step() if batch_idx % 100 == 0: print '==>>> epoch: {}, batch index: {}, train loss: {:.6f}'.format(epoch, batch_idx, loss.data[0]) # testing correct_cnt, ave_loss = 0, 0 for batch_idx, (x, target) in enumerate(test_loader): x, target = Variable(x.cuda(), volatile=True), Variable(target.cuda(), volatile=True) score, loss = model(x, target) _, pred_label = torch.max(score.data, 1) correct_cnt += (pred_label == target.data).sum() ave_loss += loss.data[0] accuracy = correct_cnt*1.0/len(test_loader)/batch_size ave_loss /= len(test_loader) print '==>>> epoch: {}, test loss: {:.6f}, accuracy: {:.4f}'.format(epoch, ave_loss, accuracy) torch.save(model.state_dict(), model.name())