SynDiff icon indicating copy to clipboard operation
SynDiff copied to clipboard

OSError: Unable to synchronously open file (file signature not found)

Open x0204 opened this issue 1 year ago • 1 comments

I am enthusiastic about the opportunity to contribute to the team, particularly in the aspect of utilizing the diffusion model for unsupervised medical image translation, as outlined in the provided documentation.

Upon reviewing the mentioned paper, I encountered an error during the training process. The error code is as follows:

"(SynDiff) chang@chang-System-Product-Name:~/Downloads/SynDiff$ python train.py --image_size 256 --exp exp_syndiff --num_channels 2 --num_channels_dae 64 --ch_mult 1 1 2 2 4 4 --num_timesteps 4 --num_res_blocks 2 --batch_size 1 --contrast1 T1 --contrast2 T2 --num_epoch 1000 --ngf 64 --embedding_type positional --use_ema --ema_decay 0.999 --r1_gamma 1. --z_emb_dim 256 --lr_d 1e-4 --lr_g 1.6e-4 --lazy_reg 10 --num_process_per_node 1 --save_content --local_rank 0 --input_path /home/chang/Downloads/SynDiff/Input_files --output_path /home/chang/Downloads/SynDiff/output_files module_path = /home/chang/Downloads/SynDiff/utils/op Traceback (most recent call last): File "/home/chang/Downloads/SynDiff/train.py", line 861, in init_processes(0, size, train_syndiff, args) File "/home/chang/Downloads/SynDiff/train.py", line 724, in init_processes fn(rank, gpu, args) File "/home/chang/Downloads/SynDiff/train.py", line 209, in train_syndiff dataset = CreateDatasetSynthesis(phase = "train", input_path = args.input_path, contrast1 = args.contrast1, contrast2 = args.contrast2) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/chang/Downloads/SynDiff/dataset.py", line 9, in CreateDatasetSynthesis data_fs_s1=LoadDataSet(target_file) ^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/chang/Downloads/SynDiff/dataset.py", line 21, in LoadDataSet f = h5py.File(load_dir,'r') ^^^^^^^^^^^^^^^^^^^^^^^ File "/home/chang/fsl/lib/python3.11/site-packages/h5py/_hl/files.py", line 562, in init fid = make_fid(name, mode, userblock_size, fapl, fcpl, swmr=swmr) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/chang/fsl/lib/python3.11/site-packages/h5py/_hl/files.py", line 235, in make_fid fid = h5f.open(name, flags, fapl=fapl) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper File "h5py/h5f.pyx", line 102, in h5py.h5f.open OSError: Unable to synchronously open file (file signature not found)

Subject: Inquiry Regarding Error in Training Process and Dataset Details

Dear [Recipient's Name],

I trust this message finds you well. I am enthusiastic about the opportunity to contribute to the team, particularly in the aspect of utilizing the diffusion model for unsupervised medical image translation, as outlined in the provided documentation.

Upon reviewing the mentioned paper, I have encountered an error during the training process. The error code is as follows:

bash Copy code "(SynDiff) chang@chang-System-Product-Name:~/Downloads/SynDiff$ python train.py --image_size 256 --exp exp_syndiff --num_channels 2 --num_channels_dae 64 --ch_mult 1 1 2 2 4 4 --num_timesteps 4 --num_res_blocks 2 --batch_size 1 --contrast1 T1 --contrast2 T2 --num_epoch 1000 --ngf 64 --embedding_type positional --use_ema --ema_decay 0.999 --r1_gamma 1. --z_emb_dim 256 --lr_d 1e-4 --lr_g 1.6e-4 --lazy_reg 10 --num_process_per_node 1 --save_content --local_rank 0 --input_path /home/chang/Downloads/SynDiff/Input_files --output_path /home/chang/Downloads/SynDiff/output_files module_path = /home/chang/Downloads/SynDiff/utils/op Traceback (most recent call last): File "/home/chang/Downloads/SynDiff/train.py", line 861, in init_processes(0, size, train_syndiff, args) File "/home/chang/Downloads/SynDiff/train.py", line 724, in init_processes fn(rank, gpu, args) File "/home/chang/Downloads/SynDiff/train.py", line 209, in train_syndiff dataset = CreateDatasetSynthesis(phase = "train", input_path = args.input_path, contrast1 = args.contrast1, contrast2 = args.contrast2) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/chang/Downloads/SynDiff/dataset.py", line 9, in CreateDatasetSynthesis data_fs_s1=LoadDataSet(target_file) ^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/chang/Downloads/SynDiff/dataset.py", line 21, in LoadDataSet f = h5py.File(load_dir,'r') ^^^^^^^^^^^^^^^^^^^^^^^ File "/home/chang/fsl/lib/python3.11/site-packages/h5py/_hl/files.py", line 562, in init fid = make_fid(name, mode, userblock_size, fapl, fcpl, swmr=swmr) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/chang/fsl/lib/python3.11/site-packages/h5py/_hl/files.py", line 235, in make_fid fid = h5f.open(name, flags, fapl=fapl) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper File "h5py/h5f.pyx", line 102, in h5py.h5f.open OSError: Unable to synchronously open file (file signature not found)"

I would appreciate your insights and guidance on resolving this issue. Additionally, I seek further clarification on the details of the BRATS and IXI datasets utilized for training, as these specifics were not entirely clear in the documentation.

Thank you for your time and assistance. I am eager to address and overcome these challenges collaboratively.

x0204 avatar Jan 29 '24 13:01 x0204

I have the same problem. How did you solve it in the end?

zfw-cv avatar Jun 14 '24 10:06 zfw-cv