search

hellopipu / PromptMR

Fill the K-Space and Refine the Image: Prompting for Dynamic and Multi-Contrast MRI Reconstruction, STACOM2023
https://link.springer.com/chapter/10.1007/978-3-031-52448-6_25
MIT License
27 stars 4 forks source link

hello!I have encountered this problem #8

Open zky0701 opened 2 weeks ago

zky0701 commented 2 weeks ago

When I run the pretrained file, an error occurs: Traceback (most recent call last): File "run_pretrained_promptmr_fastmri_knee_inference.py", line 182, in torch.device(args.device), File "run_pretrained_promptmr_fastmri_knee_inference.py", line 121, in run_inference model.load_state_dict(torch.load(state_dict_file)) File "/home/zhengkaiyi/anaconda3/envs/zky/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1672, in load_state_dict self.class.name, "\n\t".join(error_msgs))) RuntimeError: Error(s) in loading state_dict for PromptMR: Is it because I ran the files in the wrong order, or is there another reason? Could you help me solve it?

hellopipu commented 1 week ago

Did you download the pretrained model? If so, could you show the full error message?

RuntimeError: Error(s) in loading state_dict for PromptMR:

zky0701 commented 1 week ago

Did you download the pretrained model? If so, could you show the full error message?

RuntimeError: Error(s) in loading state_dict for PromptMR:Hello, thank you for your response. I am currently facing two issues. The first issue is that when I tried to load the pre trained model, I had already downloaded the file Knee_leaderboardsteate_dict.pt. However, when I tried to run it, I encountered an error message that was very long. The error messages were two separate ones. The first one is: Missing key (s) in stateudict: "sens_net. norm_unet. unet. feat_extract. weight", "sens_net. norm_unet. unet. enc_level1. encoder. 0. body. 0. weight", "sens_net. norm_unet. unet. weight" errors such as "t. enc_level1. encoder. 0. body. 1. weight" and so on. The second one is: Unexpected key (s) in state_dict: "sens_net. form_unet. unet. downsample_layers. 0. layers. 0. weight", "sens_net. form_unet. unet. downsample_layers. 0. layers. 4. weight", "sens_net. form_unet. unet. downsample_layers. 1. layers. 0. weight", and so on. May I ask what caused this error. The second question is that when I load the training model, the system cannot find the path to the dataset to be trained. Where should I modify my path? (The dataset I downloaded is the FastMRI dataset from New York University, using the file kne_multicoil_train_batch_1.) Is the dataset I used correct?