- Improve internal batching logic for predicting from image paths.
0.12.0
- Improve support for using the APIs in a loop, in particular, reduce the memory usage due to re-creating the model object.
0.11.0
- Switch from `tf.keras` to `keras_core` - Include test run for JAX backend - Update README - Other minor fixes
0.10.2
- Fixed model inference usage to avoid potential TF [mem-leak](https://github.com/tensorflow/tensorflow/issues/44711#issuecomment-724439274)
0.10.1
- Remove `grad_cam_height` and `grad_cam_width` settings, the output grad-cam image will always be the same size as the input image - Default `alpha` is 0.8
0.9.2
- Add progress bar for predicting video frames. - Set all default batch sizes to 8.