setp2

[06Liz]

parser = argparse.ArgumentParser(description="DeepLabV3") parser.add_argument("--trainset_dir", type=str, default='/Data2/KI_data_train_scale_aug_patch')

parser.add_argument("--valset_dir", type=str, default=img + '/data_list.csv')
parser.add_argument("--output_dir", type=str, default=output_folder)

parser.add_argument("--snapshot_dir", type=str, default='snapshots_2D/fold1_with_white_UNet2D_ns_normalwhole_1106')
parser.add_argument("--reload_path", type=str,
                    default='snapshots_2D/fold1_with_white_Omni-Seg_normalwhole_1201/MOTS_DynConv_fold1_with_white_scale_psuedo_allMatching_withsemi_0.1_0.1_normalwhole_0217_e81.pth')
parser.add_argument("--best_epoch", type=int, default=100)

# parser.add_argument("--validsetname", type=str, default='scale')
parser.add_argument("--validsetname", type=str, default='normal')
# parser.add_argument("--valset_dir", type=str, default='/Data2/Demo_KI_data_train_patch_with_white')
parser.add_argument("--train_list", type=str, default='list/MOTS/MOTS_train.txt')
parser.add_argument("--val_list", type=str, default='list/MOTS/xx.txt')

where are these files? @ddrrnn123

[06Liz]

Traceback (most recent call last): File "Random_Step2_Testing_OmniSeg_label_overlap_64_padding.py", line 1055, in main(now_case, output_dir, case_name) File "Random_Step2_Testing_OmniSeg_label_overlap_64_padding.py", line 899, in main for iter, batch in enumerate(valloader): File "/root/miniconda3/envs/omni_seg/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 628, in next data = self._next_data() File "/root/miniconda3/envs/omni_seg/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1313, in _next_data return self._process_data(data) File "/root/miniconda3/envs/omni_seg/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1359, in _process_data data.reraise() File "/root/miniconda3/envs/omni_seg/lib/python3.7/site-packages/torch/_utils.py", line 543, in reraise raise exception ValueError: Caught ValueError in DataLoader worker process 0. Original Traceback (most recent call last): File "/root/miniconda3/envs/omni_seg/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 302, in _worker_loop data = fetcher.fetch(index) File "/root/miniconda3/envs/omni_seg/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 58, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/root/miniconda3/envs/omni_seg/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 58, in data = [self.dataset[idx] for idx in possibly_batched_index] File "/root/autodl-tmp/Omni-Seg/Omni_seg_pipeline_gpu/MOTSDataset_2D_Patch_joint_csv_PTC.py", line 208, in getitem image = np.load(datafiles["image_path"]) File "/root/miniconda3/envs/omni_seg/lib/python3.7/site-packages/numpy/lib/npyio.py", line 444, in load raise ValueError("Cannot load file containing pickled data " ValueError: Cannot load file containing pickled data when allow_pickle=False Why I use example doesn't give an error, but after processing it step by step with my own svs image, I will get an error when I run python Random_Step2_Testing_OmniSeg_label_overlap_64_padding.py step2？ @Haoju-Leng @ddrrnn123

[ddrrnn123]

Hi friends,

I think you need to define your own dataset and set the path to your local folder in the script. I recommend downloading our WSI example to check whether the entire pipeline runs successfully, then switch to your own dataset.

Please let me know if you have any questions!

Best, Ruining