Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

表情迁移只保存log文件,没有视频 #867

Open
wj73 opened this issue Jan 4, 2025 · 1 comment
Open

表情迁移只保存log文件,没有视频 #867

wj73 opened this issue Jan 4, 2025 · 1 comment
Assignees

Comments

@wj73
Copy link

wj73 commented Jan 4, 2025

请问为什么我在训练自己的表情迁移模型时,只有log文件,没有视频,用的是fashion数据集
训练十几秒就完成了,这是日志文件
[12/31 14:26:19] ppgan INFO: Configs: {'epochs': 150, 'output_dir': 'output_dir\firstorder_fashion-2024-12-31-14-26', 'model': {'name': 'FirstOrderModel', 'common_params': {'num_kp': 10, 'num_channels': 3, 'estimate_jacobian': True}, 'generator': {'name': 'FirstOrderGenerator', 'kp_detector_cfg': {'temperature': 0.1, 'block_expansion': 32, 'max_features': 1024, 'scale_factor': 0.25, 'num_blocks': 5}, 'generator_cfg': {'block_expansion': 64, 'max_features': 512, 'num_down_blocks': 2, 'num_bottleneck_blocks': 6, 'estimate_occlusion_map': True, 'dense_motion_params': {'block_expansion': 64, 'max_features': 1024, 'num_blocks': 5, 'scale_factor': 0.25}}}, 'discriminator': {'name': 'FirstOrderDiscriminator', 'discriminator_cfg': {'scales': [1], 'block_expansion': 32, 'max_features': 512, 'num_blocks': 4, 'sn': True}}, 'train_params': {'scales': [1, 0.5, 0.25, 0.125], 'transform_params': {'sigma_affine': 0.05, 'sigma_tps': 0.005, 'points_tps': 5}, 'loss_weights': {'generator_gan': 1, 'discriminator_gan': 1, 'feature_matching': [10, 10, 10, 10], 'perceptual': [10, 10, 10, 10, 10], 'equivariance_value': 10, 'equivariance_jacobian': 10}}}, 'optimizer': {'name': 'Adam'}, 'lr_scheduler': {'epoch_milestones': [187500, 281250], 'lr_generator': 0.0002, 'lr_discriminator': 0.0002, 'lr_kp_detector': 0.0002}, 'dataset': {'train': {'name': 'FirstOrderDataset', 'phase': 'train', 'dataroot': 'data/first_order/fashion/', 'num_repeats': 50, 'time_flip': True, 'batch_size': 8, 'id_sampling': False, 'frame_shape': [256, 256, 3], 'process_time': False, 'create_frames_folder': False, 'num_workers': 0, 'max_dataset_size': 'inf', 'direction': 'BtoA', 'input_nc': 3, 'output_nc': 3, 'transforms': [{'name': 'PairedRandomHorizontalFlip', 'prob': 0.5, 'keys': ['image', 'image']}, {'name': 'PairedColorJitter', 'brightness': 0.1, 'contrast': 0.1, 'saturation': 0.1, 'hue': 0.1, 'keys': ['image', 'image']}]}, 'test': {'name': 'FirstOrderDataset', 'dataroot': 'data/first_order/fashion/', 'phase': 'test', 'batch_size': 1, 'num_workers': 0, 'time_flip': False, 'id_sampling': False, 'create_frames_folder': False, 'frame_shape': [256, 256, 3]}}, 'log_config': {'interval': 10, 'visiual_interval': 10}, 'snapshot_config': {'interval': 10}, 'validate': {'interval': 31250}, 'is_train': True, 'profiler_options': None, 'timestamp': '-2024-12-31-14-26'}
[12/31 14:26:21] ppgan INFO: Found C:\Users\X.cache\ppgan\vgg19.pdparams

@wj73
Copy link
Author

wj73 commented Jan 4, 2025

图片1

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants