Followed HF model card suggestions

README.md

@@ -1,9 +1,49 @@
 # XPDNet-brain-af4
+---
+tags:
+- TensorFlow
+- MRI reconstruction
+datasets:
+- fastMRI
+---
 
 This model was used to achieve the 2nd highest submission in terms of PSNR on the fastMRI dataset (see https://fastmri.org/leaderboards/).
 It is a base model for acceleration factor 4.
 The model uses 25 iterations and a medium MWCNN.
 
+## Model description
 For more details, see https://arxiv.org/abs/2010.07290.
+This section is WIP.
+
+## Intended uses and limitations
+This model can be used to reconstruct brain data from Siemens scanner at acceleration factor 4.
+It was shown [here](https://arxiv.org/abs/2106.00753), that it can generalize well, although further tests are required.
+
+## How to use
+This model can be loaded using the following repo: https://github.com/zaccharieramzi/fastmri-reproducible-benchmark
+The framework is TensorFlow.
+Example notebooks and detailed use guides are WIP.
+
+## Limitations and bias
+The limitations and bias of this model have not been properly investigated.
+
+## Training data
+This model was trained using the [fastMRI dataset](https://fastmri.org/dataset/).
+
+## Training procedure
+The training procedure is described in https://arxiv.org/abs/2010.07290.
+This section is WIP.
+
+## Evaluation results
+On the fastMRI validation dataset
+
+| Contrast | T1     | T2     | FLAIR  | T1-POST |
+|----------|--------|--------|--------|---------|
+| PSNR     | 41.56  | 40.68  | 39.60  | 42.53   |
+| SSIM     | 0.9506 | 0.9554 | 0.9321 | 0.9683  |
+
+Further results can be seen on the fastMRI leaderboards for the test and challenge dataset: https://fastmri.org/leaderboards/
+
+
+
 
-Please cite the work above if you use this model.