Closed sgbaird closed 2 years ago
https://github.com/Janspiry/Palette-Image-to-Image-Diffusion-Models/issues/5 talks about the same error Model [Palette() form models.model] not recognized
train.log
22-06-09 22:55:24.592 - INFO: Create the log file in directory experiments/debug_inpainting_celebahq_220609_225523.
22-06-09 22:55:24.684 - INFO: Dataset [InpaintDataset() form data.dataset] is created.
22-06-09 22:55:24.684 - INFO: Dataset for train have 48 samples.
22-06-09 22:55:24.685 - INFO: Dataset for val have 2 samples.
22-06-09 22:55:25.194 - INFO: Network [Network() form models.network] is created.
22-06-09 22:55:25.195 - INFO: Network [Network] weights initialize using [kaiming] method.
22-06-09 22:55:25.692 - WARNING: Config is a str, converts to a dict {'name': 'mae'}
22-06-09 22:55:26.060 - INFO: Metric [mae() form models.metric] is created.
22-06-09 22:55:26.060 - WARNING: Config is a str, converts to a dict {'name': 'mse_loss'}
22-06-09 22:55:26.068 - INFO: Loss [mse_loss() form models.loss] is created.
22-06-09 22:55:26.257 - INFO: Beign loading pretrained model [Network] ...
22-06-09 22:55:26.257 - WARNING: Pretrained model in [experiments/train_inpainting_celebahq_220426_233652/checkpoint/190_Network.pth] is not existed, Skip it
22-06-09 22:55:26.257 - INFO: Beign loading pretrained model [Network_ema] ...
22-06-09 22:55:26.258 - WARNING: Pretrained model in [experiments/train_inpainting_celebahq_220426_233652/checkpoint/190_Network_ema.pth] is not existed, Skip it
22-06-09 22:55:26.281 - INFO: Beign loading training states
22-06-09 22:55:26.282 - WARNING: Training state in [experiments/train_inpainting_celebahq_220426_233652/checkpoint/190.state] is not existed, Skip it
I'm having the same issue with the current status of "master" branch. Commit "https://github.com/Janspiry/Palette-Image-to-Image-Diffusion-Models/tree/d1b9b010edeee177aaa15850002766e370a8307b" is working fine for me. A bug was probably introduced in commit "ed29b1ce9ff2ae41791d52642004385886f0680f"
I'm having the same issue with the current status of "master" branch. Commit "https://github.com/Janspiry/Palette-Image-to-Image-Diffusion-Models/tree/d1b9b010edeee177aaa15850002766e370a8307b" is working fine for me. A bug was probably introduced in commit "ed29b1ce9ff2ae41791d52642004385886f0680f"
Hi, could you show me the log and configure file? Since the lastest code have changed the configure file structure.
Feel free to reopen the issue if there is any question.
I have the same problem when I train from scratch on my own dataset, but I don't know how to solve it. Here is my log: 23-04-22 20:28:58.357 - INFO: Create the log file in directory experiments/debug_colorization_mirflickr25k_230422_202856.
23-04-22 20:28:58.409 - INFO: Dataset [ColorizationDataset() form data.dataset] is created. 23-04-22 20:28:58.409 - INFO: Dataset for train have 48 samples. 23-04-22 20:28:58.409 - INFO: Dataset for val have 2 samples. 23-04-22 20:28:58.910 - INFO: Network [Network() form models.network] is created. 23-04-22 20:28:58.910 - INFO: Network [Network] weights initialize using [kaiming] method. 23-04-22 20:28:59.314 - INFO: Config is a str, converts to a dict {'name': 'mae'} 23-04-22 20:28:59.865 - INFO: Metric [mae() form models.metric] is created. 23-04-22 20:28:59.865 - INFO: Config is a str, converts to a dict {'name': 'mse_loss'} 23-04-22 20:28:59.897 - INFO: Loss [mse_loss() form models.loss] is created. 23-04-22 20:28:59.900 - INFO: Optimizer [Adam() form default file] is created. 23-04-22 20:28:59.900 - INFO: Scheduler [LinearLR() form default file] is created.
setup
Running on Windows Subsystem for Linux 2 (WSL2).
conda
installation per #20command
inpainting_celebahq_dummy.json
Directory Structure
Error