search

ellisdg / 3DUnetCNN

Pytorch 3D U-Net Convolution Neural Network (CNN) designed for medical image segmentation
MIT License
1.9k stars 653 forks source link

TypeError: __init__() missing 1 required positional argument: 'dtype' #301

Closed Ron-carry closed 2 years ago

Ron-carry commented 2 years ago

Hi , when I train 10 datasets , it's OK ! But when I train 100 datasets , it's wrong ! I need help ! Here is the error message :

Config: ./brats_config.json Model: ./output_model/brats_unet3d_baseline.h5 Log: brats_baseline_training_log.csv Setting window size to 160 x 192 x 128 Setting batch size to 1 Writing new configuration file: ./brats_config_auto.json Encoder 0: 4 32 Encoder 1: 32 64 Encoder 2: 64 128 Encoder 3: 128 256 Encoder 4: 256 512 Decoder 4: 512 256 Decoder 3: 512 128 Decoder 2: 256 64 Decoder 1: 128 32 Decoder 0: 64 32 save_last_n_models 10 n gpus: 1 Traceback (most recent call last): File "../../unet3d/scripts/train.py", line 254, in main() File "../../unet3d/scripts/train.py", line 247, in main *system_config) File "D:\ProgramData\hff\AISegment\3DUnetCNN-20211205\unet3d\train\train.py", line 17, in run_training_with_package return run_training(args, kwargs) File "D:\ProgramData\hff\AISegment\3DUnetCNN-20211205\unet3d\train\pytorch.py", line 168, in run_pytorch_training amp=amp) File "D:\ProgramData\hff\AISegment\3DUnetCNN-20211205\unet3d\train\pytorch.py", line 219, in train regularized=regularized, vae=vae, scaler=scaler) File "D:\ProgramData\hff\AISegment\3DUnetCNN-20211205\unet3d\train\pytorch_training_utils.py", line 36, in epoch_training for i, (images, target) in enumerate(train_loader): File "D:\ProgramFiles\Anaconda3\envs\pytorchgpu-1.5\lib\site-packages\torch\utils\data\dataloader.py", line 345, in next data = self._next_data() File "D:\ProgramFiles\Anaconda3\envs\pytorchgpu-1.5\lib\site-packages\torch\utils\data\dataloader.py", line 856, in _next_data return self._process_data(data) File "D:\ProgramFiles\Anaconda3\envs\pytorchgpu-1.5\lib\site-packages\torch\utils\data\dataloader.py", line 881, in _process_data data.reraise() File "D:\ProgramFiles\Anaconda3\envs\pytorchgpu-1.5\lib\site-packages\torch_utils.py", line 395, in reraise raise self.exc_type(msg) TypeError: init() missing 1 required positional argument: 'dtype'**

stale[bot] commented 2 years ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions. If you are still wanting followup to this issue, please ping the thread by leaving a comment. You may also contact david.ellis@unmc.edu with questions.