Rewrite a simple CNN classifier with tensorflow 2.0 alpha, apply iWild dataset on Kaggle.
This is an FGVCx competition as part of the FGVC6 workshop at CVPR 2019, and is sponsored by Microsoft AI for Earth. There is a github page for the competition here. Please open an issue if you have questions or problems with the dataset.
Model | GFlop | Kaggle Score |
---|---|---|
Custom Molde | - | - |
ResnetV2 | - | - |
- Evaluate classification benchmark with classic model like Inception.
- Arrange new coding style on Tensorflow 2.0.
- Design a custom model to kickoff iwild dataset.
- Add model summary tool to assess model efficiency.
- Imporve data pipeline of dataset api on Tensorflow 2.0.