if opt.model != '':
classifier.load_state_dict(torch.load(opt.model))
optimizer = optim.SGD(classifier.parameters(), lr=0.01, momentum=0.9)
classifier.cuda()
num_batch = len(dataset)/opt.batchSize
for epoch in range(opt.nepoch):
for i, data in enumerate(dataloader, 0):
points, target = data
points, target = Variable(points), Variable(target)
points = points.transpose(2,1)
points, target = points.cuda(), target.cuda()
optimizer.zero_grad()
classifier = classifier.train()
pred, _ = classifier(points)
pred = pred.view(-1, num_classes)
target = target.view(-1,1)[:,0] - 1
#print(pred.size(), target.size())
loss = F.nll_loss(pred, target)
loss.backward()
optimizer.step()
pred_choice = pred.data.max(1)[1]
correct = pred_choice.eq(target.data).cpu().sum()
print('[%d: %d/%d] train loss: %f accuracy: %f' %(epoch, i, num_batch, loss.item(), correct.item()/float(opt.batchSize * 2500)))
if i % 10 == 0:
j, data = next(enumerate(testdataloader, 0))
points, target = data
points, target = Variable(points), Variable(target)
optimizer = optim.SGD(classifier.parameters(),
lr=opt.lr,
momentum=opt.momentum)
classifier.cuda()
num_batch = len(dataset) / opt.batchSize
miou_list = list()
for epoch in range(opt.nepoch):
for i, data in enumerate(dataloader, 0):
points, target = data
points, target = Variable(points), Variable(target)
points = points.transpose(2, 1)
points, target = points.cuda(), target.cuda()
optimizer.zero_grad()
classifier = classifier.train()
pred, _ = classifier(points)
pred = pred.view(-1, num_classes)
target = target.view(-1, 1)[:, 0] - 1
#print(pred.size(), target.size())
loss = F.nll_loss(pred, target)
loss.backward()
optimizer.step()
pred_choice = pred.data.max(1)[1]
correct = pred_choice.eq(target.data).cpu().sum()
print('[%d: %d/%d] train loss: %f accuracy: %f' %
(epoch, i, num_batch, loss.item(),
correct.item() / float(opt.batchSize * opt.num_points)))
if i % 100 == 0:
test_loss = []
plots_dir = os.path.join(model_dir, 'plots')
if not os.path.exists(model_dir):
os.makedirs(model_dir)
if not os.path.exists(plots_dir):
os.makedirs(plots_dir)
for epoch in range(opt.nepoch):
train_batch_num = 0
test_batch_num = 0
total_train_correct = 0
total_train_loss = 0
classifier.train()
for i, data in enumerate(dataloader, 0):
optimizer.zero_grad()
train_batch_num += 1
points, target = data
points, target = points.to(device, non_blocking=True), target.to(device, non_blocking=True)
points = points.transpose(2,1)
pred, _ = classifier(points)
pred = pred.view(-1, num_classes)
target = target.view(-1,1)[:,0] - 1
loss = F.nll_loss(pred, target.long())
loss.backward()
optimizer.step()
pred_choice = pred.data.max(1)[1]
correct = pred_choice.eq(target.long().data).cpu().sum()
total_train_correct += correct.item()
