Update README.md

README.md

@@ -1,3 +1,52 @@
 ---
 license: mit
 ---
+# Model Card for pre-trained EEGNet models on mental imagery datasets
+
+Collection of 12 neural networks trained for motor imagery decoding.
+
+## Model Details
+
+- **Architecture:** [EEGNetv4](https://braindecode.org/stable/generated/braindecode.models.EEGNetv4.html) by  [Lawhern et. al (2018)](https://doi.org/10.1088/1741-2552/aace8c).
+
+
+## How to Get Started with the Model
+
+- **Download and load in memory:**
+```python
+import pickle
+
+# download the model from the hub:
+path_kwargs = hf_hub_download(
+    repo_id='PierreGtch/EEGNetv4',
+    filename='EEGNetv4_Lee2019_MI/kwargs.pkl',
+)
+path_params = hf_hub_download(
+    repo_id='PierreGtch/EEGNetv4',
+    filename='EEGNetv4_Lee2019_MI/model-params.pkl',
+)
+with open(path_kwargs, 'rb') as f:
+    kwargs = pickle.load(f)
+module_cls = kwargs['module_cls']
+module_kwargs = kwargs['module_kwargs']
+
+# load the model with pre-trained weights:
+torch_module = module_cls(**module_kwargs)
+```
+- **Details:** more details and potential use-case scenarios can be found in the notebook [here](https://neurotechlab.socsci.ru.nl/resources/pretrained_imagery_models/)
+
+
+## Training Details
+
+- **Training dataset:** Each model was trained on the dataset with corresponding name in the MOABB library (see [datasets list](https://neurotechx.github.io/moabb/dataset_summary.html#motor-imagery)).
+- **Details:** For details on the training procedure, please refer to the poster [here](https://neurotechlab.socsci.ru.nl/resources/pretrained_imagery_models/).
+
+## Evaluation
+
+- **Cross-dataset transfer:** The transfer abilities of the models was tested on the same datasets as for training.
+- **Details:** The results can be found on the poster [here](https://neurotechlab.socsci.ru.nl/resources/pretrained_imagery_models/).
+
+## Model Card Authors
+
+- **Modedels training and results by:** Pierre Guetschel
+