To receive notifications about scheduled maintenance, please subscribe to the mailing-list gitlab-operations@sympa.ethz.ch. You can subscribe to the mailing-list at https://sympa.ethz.ch

Commit bd6c9bfb authored by zpgeng's avatar zpgeng
Browse files

Update README

parent e83dfdeb
# DL-Project
Predicting eye gaze with DL
Predicting eye gaze direction with DL
Models that we try: CNN, InceptionTime, EEGNet, Xception, DeepEye, and DeepEyeRNN.
## Datasets
You can download the datasets from this link: https://polybox.ethz.ch/index.php/s/GLe287LxHq3QysW
- 125Hz data: noweEEG.mat
- 500Hz data: all_EEGprocuesan.mat
- labels (0 for left, 1 for right): all_trialinfoprosan.mat
## Model Configuration
Please configure the config.py file correctly before running the main.py file:
......@@ -43,8 +51,8 @@ For [ETH Leonhard](https://scicomp.ethz.ch/wiki/Python_on_Leonhard) users, you c
3. Use the following command to run the model: `bsub -n 10 -W 4:00 -o experiment_[your_model] -R "rusage[mem=5000, ngpus_excl_p=1]" python ../main.py`
__Note:__ If you want to run the model locally, you should ensure to have Pytorch, Tensorflow==2.x installed.
__Note:__ If you want to run the model locally, you should ensure to have Pytorch, Tensorflow==2.x installed.
## Reading the Results
......@@ -53,18 +61,3 @@ A summary of the model is printed in the `experiment_[your_model]` file generate
After each run, a directory with the name `'number'_config['model']` is created under the run directory, where 'number' refers to the time stamp of the training (different for each run of main.py). It contains the weights of the model, a .csv file with the fiting history, the best validation score and an accuracy and loss plot of the training.
## DeepEye3 Tuning (deprecated)
nb_filter: [32, 64]
depth: [9, 12, 20]
kernel_size:[40, 20]
residual_jump: [3, 4]
Large depth causes overfitting, same for the number of filters. Kernel size seems to have tiny affect on validation. Residual jump for 4 (i.e. `depth % (res_jump) == (res_jump - 1)`) is not so good in our task, but I think it would be useful for future tasks.
The best setting is **nb_filter == 32, depth == 9, kernel_size == 40, res_jump == 3**
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment