fastMRI icon indicating copy to clipboard operation
fastMRI copied to clipboard

A large-scale dataset of both raw MRI measurements and clinical MRI images.

Results 25 fastMRI issues
Sort by recently updated
recently updated
newest added

This PR will implement code for reproducing results in the following paper: Radmanesh, A., Muckley, M. J., Murrell, T., Lindsey, E., Sriram, A., Knoll, F., ... & Lui, Y. W....

CLA Signed

Hello, I've been updating the code in line with the changes introduced in PyTorch Lightning v2's documentation. I'm working to ensure that all modifications align correctly and the code functions...

bug

As documented in Discussion #287, the `tar.gz` file for the brain DICOM data seems to be corrupted. I have downloaded a couple of times, observing an SHA256 hash of `68e19447b428ab723d62bcd09a2b859a06eac52f4d5751d5b66570de0f7064db`...

bug

Please: - [x] Check for duplicate requests. - [x] Describe your goal, and if possible provide a code snippet with a motivating example. Hi fastmri developers, what about building `fastmri`...

enhancement

Hello all! Since PyTorch and PytorchLightning is upgraded to 2.0 and above, the `fastmri_examples` code such as `unet` is now deprecated. I am wondering that whether there is a plan...

enhancement

While working with the knee dataset on a VarNet from Pytorch-lighting's library and using the ```FastMriDataModule``` data-loaders, I observed that the training is unstable and crashes fairly often. I tried...

bug

Although the [fastMRI 2.0 release](https://github.com/facebookresearch/fastMRI/discussions/284) reduced data storage requirements by batching the fastMRI dataset, in some cases even the fastMRI 2.0 batches can be too small to work with (e.g.,...

enhancement

Please:When the number of my GPUs is set to greater than 1, the following error will occur. How can I fix this BUG? Traceback (most recent call last): File "/home/23-panjiawei/MRI_code/unet_knee_sc_leaderboard.py",...

bug

Here is the minimal code that reproduces the error. ```python from fastmri.data.subsample import create_mask_for_mask_type from fastmri.data.transforms import apply_mask, to_tensor, center_crop import numpy as np mask_func =create_mask_for_mask_type( mask_type_str="magic_fraction", center_fractions=[0.37], accelerations=[4] )...

bug

Added a new folder in fastmri_examples which includes the new modules for feature varent and ablations. Added a new model file (feature_varnet) in fastmri/models which includes the new models. Updated...

CLA Signed