j, data = next(enumerate(testdataloader, 0))
points, target = data
points = points.transpose(2, 1)
points, target = points.cuda(), target.cuda()
classifier = classifier.eval()
pred, _, _ = classifier(points)
pred = pred.view(-1, num_classes)
target = target.view(-1, 1)[:, 0] - 1
loss = F.nll_loss(pred, target)
pred_choice = pred.data.max(1)[1]
correct = pred_choice.eq(target.data).cpu().sum()
print('[%d: %d/%d] %s loss: %f accuracy: %f' %
(epoch, i, num_batch, blue('test'), loss.item(),
correct.item() / float(opt.batchSize * 2500)))
torch.save(classifier.state_dict(),
'%s/seg_model_%s_%d.pth' % (opt.outf, opt.class_choice, epoch))
## benchmark mIOU
shape_ious = []
for i, data in tqdm(enumerate(testdataloader, 0)):
points, target = data
points = points.transpose(2, 1)
points, target = points.cuda(), target.cuda()
classifier = classifier.eval()
pred, _, _ = classifier(points)
pred_choice = pred.data.max(2)[1]
pred_np = pred_choice.cpu().data.numpy()
target_np = target.cpu().data.numpy() - 1
points, target = data
points = points.transpose(2, 1)
points, target = points.cuda(), target.cuda()
classifier = classifier.eval()
pred, _, _ = classifier(points)
pred = pred.view(-1, num_classes)
target = target.view(-1, 1)[:, 0] - 1
loss = F.nll_loss(pred, target)
pred_choice = pred.data.max(1)[1]
correct = pred_choice.eq(target.data).cpu().sum()
print('[%d: %d/%d] %s loss: %f accuracy: %f' %
(epoch, i, num_batch, blue('test'), loss.item(),
correct.item() / float(opt.batchSize * 2500)))
torch.save(
classifier.state_dict(), '%s/seg_model_%s_%d.pth' %
(opt.outf, opt.class_choice, epoch)) #保存在seg/seg_model_Chair_1.pth
## benchmark mIOU #mIOU = TP/(FP+FN+TP)
shape_ious = [] #测试
for i, data in tqdm(enumerate(testdataloader, 0)): #tqdm进度条
points, target = data
points = points.transpose(2, 1)
points, target = points.cuda(), target.cuda()
classifier = classifier.eval()
pred, _, _ = classifier(points)
pred_choice = pred.data.max(2)[1]
pred_np = pred_choice.cpu().data.numpy()
target_np = target.cpu().data.numpy() - 1
points, target = data
points = points.transpose(2, 1)
points, target = points.cuda(), target.cuda()
classifier = classifier.eval()
pred, _, _ = classifier(points)
pred = pred.view(-1, num_classes)
target = target.view(-1, 1)[:, 0] - 1
loss = F.nll_loss(pred, target)
pred_choice = pred.data.max(1)[1]
correct = pred_choice.eq(target.data).cpu().sum()
print('[%d: %d/%d] %s loss: %f accuracy: %f' %
(epoch, i, num_batch, blue('test'), loss.item(),
correct.item() / float(opt.batchSize * 2500)))
torch.save(
classifier.state_dict(),
'%s/seg_model_%s_%d.pth' % (opt.outf, opt.class_choice, epoch))
## benchmark mIOU
shape_ious = []
for i, data in tqdm(enumerate(testdataloader, 0)):
points, target = data
points = points.transpose(2, 1)
points, target = points.cuda(), target.cuda()
classifier = classifier.eval()
pred, _, _ = classifier(points)
pred_choice = pred.data.max(2)[1]
pred_np = pred_choice.cpu().data.numpy()
target_np = target.cpu().data.numpy() - 1
writer.add_scalar('validation errG_global', errG_g_eval.item(),
27 * epoch + n)
writer.add_scalar('validation errG_local', errG_l_eval.item(),
27 * epoch + n)
writer.add_scalar('validation chamfer_loss',
chamferloss_eval.item(), 27 * epoch + n)
writer.add_scalar('validation errG_loss', loss_eval.item(),
27 * epoch + n)
#for name, param in globalD.named_parameters():
# writer.add_histogram(name, param.clone().cpu().data.numpy(), 27 * epoch + n)
#for name, param in localD.named_parameters():
# writer.add_histogram(name, param.clone().cpu().data.numpy(), 27 * epoch + n)
#for name, param in netG.named_parameters():
# writer.add_histogram(name, param.clone().cpu().data.numpy(), 27 * epoch + n)
schedulerG.step()
schedulerD.step()
if loss.item() < best_loss:
best_loss = loss.item()
torch.save(netG.state_dict(),
'%s/com_model_G_%f_%d.pth' % (opt.outf, loss.item(), epoch))
torch.save(
localD.state_dict(),
'%s/com_model_localD_%f_%d.pth' % (opt.outf, errD.item(), epoch))
torch.save(
globalD.state_dict(),
'%s/com_model_globalD_%f_%d.pth' % (opt.outf, errD.item(), epoch))
loss = F.nll_loss(pred, target)
loss_buf.append(loss.detach().cpu().numpy())
if opt.feature_transform:
loss += feature_transform_reguliarzer(trans_feat) * 0.001
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)))
# finish one epoch
print('Epoch %d: Train loss: %.2f, Time: %.2f s' % (epoch, np.mean(loss_buf), time.time() - epoch_start_time))
# every ten epoch: save model & evaluate
if (epoch + 1) % 10 == 0:
torch.save(classifier.state_dict(), '%s/seg_model_%s_%d.pth' % (opt.outf, opt.class_choice, epoch + 1))
# evaluate on test set
loss_buf = []
correct_buf = []
iou_buf = []
for i, data in enumerate(testdataloader, 0):
points, target = data
points, target = Variable(points), Variable(target)
points = points.transpose(2, 1)
points, target = points.cuda(), target.cuda()
pred, _, _ = classifier(points)
pred = pred.view(-1, num_classes)
target = target.view(-1, 1)[:, 0] - 1
loss = F.nll_loss(pred, target)
pred_choice = pred.data.max(1)[1]
correct = pred_choice.eq(target.data).cpu().sum()