Rishabh Agrahari

ALE Plot dimension mismatch

2

I'm trying to run `plot_ale` like this: ``` proba_ale = ale_analysis(model, train_dataframe, features_list) plot_ale(proba_ale, n_cols=2, fig_kw={'figwidth': 12, 'figheight': 15}, sharey=None); ``` Here, `model` is my trained model, `train_dataframe` is the...

Hey, We have three levels of box visibility: ``` """Enumerates the various level of box visibility in an image.""" ALL = 0 # Requires all corners are inside the image....

render_annotation fixed

1

Fixed #33 Changes: 1. Little modification with a code comment. (L1065). 2. Removed a redundant line (L1066). 3. Removed for loop, as there will be only one box for a...

A small issue in render_annotation function

2

Hey, In `render_annotation` function you don't need a for loop ([here](https://github.com/lyft/nuscenes-devkit/blob/master/lyft_dataset_sdk/lyftdataset.py#L1083)) as there will always be one box in `boxes` (we are doing assertion checks for the same). And you...

Running render_scene in Jupyter notebook throws error

2

Hey, I've found an issue related to render_scene function, running it in Jupyter notebook throws following error: ``` --------------------------------------------------------------------------- error Traceback (most recent call last) in ----> 1 level5data.render_scene(my_scene['token']) /opt/conda/lib/python3.6/site-packages/lyft_dataset_sdk/lyftdataset.py...

Update keras code

2

Hi, I'm going through your code, I see some code which has been deprecated in due course of time. like [here](https://github.com/orobix/retina-unet/blob/master/src/retinaNN_training.py#L19) `visualize_util` has been changed to `vis_utils` and `plot` to...

Training when images may not have any ground truth bboxes

6

Hi, I've a dataset which has images which may or may not have ground truth boxes. I've tweaked the dataloader and MultiboxLoss accordingly. In cases where the image doesn't have...