Cleanup

natanielruiz

2017-08-12 fdf1fedb0d3b4beb672464a438c22b94b9cb7d0f

 code/train.py

File was renamed from code/train_resnet_bins_comb.py
@@ -113,11 +113,10 @@
                                               num_workers=2)

    model.cuda(gpu)
    criterion = nn.CrossEntropyLoss()
    reg_criterion = nn.MSELoss()
    criterion = nn.CrossEntropyLoss().cuda()
    reg_criterion = nn.MSELoss().cuda()
    # Regression loss coefficient
    alpha = 0.1
    lsm = nn.Softmax()
    alpha = 0.01

    idx_tensor = [idx for idx in xrange(66)]
    idx_tensor = torch.FloatTensor(idx_tensor).cuda(gpu)
@@ -125,33 +124,25 @@
    optimizer = torch.optim.Adam([{'params': get_ignored_params(model), 'lr': args.lr},
                                  {'params': get_non_ignored_params(model), 'lr': args.lr * 10}],
                                  lr = args.lr)
    # optimizer = torch.optim.SGD([{'params': get_ignored_params(model), 'lr': args.lr},
    #                              {'params': get_non_ignored_params(model), 'lr': args.lr}],
    #                               lr = args.lr, momentum=0.9, weight_decay=5e-4)
    # optimizer = torch.optim.RMSprop([{'params': get_ignored_params(model), 'lr': args.lr},
    #                               {'params': get_non_ignored_params(model), 'lr': args.lr * 10}],
    #                               lr = args.lr)

    print 'Ready to train network.'

    for epoch in range(num_epochs):
        for i, (images, labels, name) in enumerate(train_loader):
            images = Variable(images).cuda(gpu)
            label_yaw = Variable(labels[:,0]).cuda(gpu)
            label_pitch = Variable(labels[:,1]).cuda(gpu)
            label_roll = Variable(labels[:,2]).cuda(gpu)
            images = Variable(images.cuda(gpu))
            label_yaw = Variable(labels[:,0].cuda(gpu))
            label_pitch = Variable(labels[:,1].cuda(gpu))
            label_roll = Variable(labels[:,2].cuda(gpu))

            optimizer.zero_grad()
            model.zero_grad()

            yaw, pitch, roll = model(images)

            # Cross entropy loss
            loss_yaw = criterion(yaw, label_yaw)
            loss_pitch = criterion(pitch, label_pitch)
            loss_roll = criterion(roll, label_roll)

            # loss_seq = [loss_yaw, loss_pitch, loss_roll]
            # grad_seq = [torch.Tensor(1).cuda(gpu) for _ in range(len(loss_seq))]
            # torch.autograd.backward(loss_seq, grad_seq)
            # optimizer.step()

            # MSE loss
            yaw_predicted = F.softmax(yaw)
@@ -166,15 +157,13 @@
            loss_reg_pitch = reg_criterion(pitch_predicted, label_pitch.float())
            loss_reg_roll = reg_criterion(roll_predicted, label_roll.float())

            # print yaw_predicted[0], label_yaw.data[0]

            # Total loss
            loss_yaw += alpha * loss_reg_yaw
            loss_pitch += alpha * loss_reg_pitch
            loss_roll += alpha * loss_reg_roll

            loss_seq = [loss_yaw, loss_pitch, loss_roll]
            grad_seq = [torch.Tensor(1).cuda(gpu) for _ in range(len(loss_seq))]
            model.zero_grad()
            torch.autograd.backward(loss_seq, grad_seq)
            optimizer.step()

@@ -195,4 +184,4 @@
            'output/snapshots/resnet50_epoch_'+ str(epoch+1) + '.pkl')

    # Save the final Trained Model
    torch.save(model.state_dict(), 'output/snapshots/resnet50_epoch_' + str(epoch+1) + '.pkl')
    torch.save(model.state_dict(), 'output/snapshots/resnet50_epoch' + str(epoch+1) + '.pkl')