Baseline model and source code
The baseline is implemented using Feature pyramid network (FPN) architecture with different ResNet backbones. The baseline model can be downloaded from SARAS-ESAD-baseline repository at GitHub. You can use this code to reproduce the results. Details on the implementation and baseline results are provided in README.md.
Features of the baseline code:
1. Data organising instructions and helping scripts.
2. Pytorch dataloader for the provided dataset.
3. Pytorch code for training a baseline model.
4. Evaluating the trained model on the validation dataset.
5. Generation of submission file given set of input images
We hope this will help kick start more team to get up to speed and allow time for more innovative solutions.