Farhan Hai Khan

Hmm, can you provide a reproducible example?

Labels that are there officially? ```python LABELS = [ "person", "bicycle", "car", "motorbike", "aeroplane", "bus", "train", "truck", "boat", "traffic light", "fire hydrant", "stop sign", "parking meter", "bench", "bird", "cat", "dog",...

Labels that I got from Pixellib/PointRend! ```python NEW_POINTREND_CLASSNAMES_MAPPING = [ "person", "bicycle", "car", "motorcycle", "airplane", "bus", "train", "truck", "boat", "traffic light", "fire hydrant", "stop sign", "parking meter", "bench", "bird", "cat",...

Differences ```python NEW_POINTREND_CLASSNAMES_MAPPING = { "motorcycle": "motorbike", "airplane": "aeroplane", "sofa" : "couch", "pottedplant" : "potted plant", "diningtable": "dining table", "tvmonitor": "tv", "hair drier" : "hair dryer", } ```

@ayoolaolafenwa look into this once!

Please fix all merge conflicts. Also, provide documentation for the same.

Thanks for the response @arunmp2004! How to train from a single JSON file from VGG Image Annotator Tool? @ayoolaolafenwa ??

@qubvel Can you review and merge this?

> @JordanMakesMaps read it somewhere stating that in newer tensorflow or keras require the return batch as tuple rather than list > > ``` > def __getitem__(self, i): > >...

Try this dataloder and dataset classes: ``` MAIN_SIZE_X = 512 MAIN_SIZE_Y = 512 # helper function for data visualization def visualize(**images): """PLot images in one row.""" n = len(images) plt.figure(figsize=(20,...