Omg

natanielruiz

2017-09-07 6dd2ff502947ec809d420e2baefa023d821a8bb1

 code/train.py

@@ -102,8 +102,13 @@

    print 'Loading data.'

    transformations = transforms.Compose([transforms.Scale(224),transforms.RandomCrop(224),
                                          transforms.ToTensor()])
    # transformations = transforms.Compose([transforms.Scale(224),
    #                                       transforms.RandomCrop(224),
    #                                       transforms.ToTensor()])

    transformations = transforms.Compose([transforms.Scale(250),
    transforms.RandomCrop(224), transforms.ToTensor(),
    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])])

    pose_dataset = datasets.Pose_300W_LP(args.data_dir, args.filename_list,
                                transformations)
@@ -124,6 +129,10 @@
    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=0.01)

    print 'Ready to train network.'

@@ -173,15 +182,15 @@
            if (i+1) % 100 == 0:
                print ('Epoch [%d/%d], Iter [%d/%d] Losses: Yaw %.4f, Pitch %.4f, Roll %.4f'
                       %(epoch+1, num_epochs, i+1, len(pose_dataset)//batch_size, loss_yaw.data[0], loss_pitch.data[0], loss_roll.data[0]))
                if epoch == 0:
                    torch.save(model.state_dict(),
                    'output/snapshots/resnet50_iter_'+ str(i+1) + '.pkl')
                # if epoch == 0:
                #     torch.save(model.state_dict(),
                #     'output/snapshots/resnet50_lbatch_iter_'+ str(i+1) + '.pkl')

        # Save models at numbered epochs.
        if epoch % 1 == 0 and epoch < num_epochs - 1:
            print 'Taking snapshot...'
            torch.save(model.state_dict(),
            'output/snapshots/resnet50_epoch_'+ str(epoch+1) + '.pkl')
            'output/snapshots/resnet50_norm_norot_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_norm_norot_epoch_' + str(epoch+1) + '.pkl')