ayoolaolafenwa

I export using ` python3 export_onnx.py --config-file configs/coco/sparseinst/sparse_inst_r50vd_giam_aug.yaml --input "cycle.jpg" MODEL.WEIGHTS sparse_inst_r50vd_giam_aug_8bc5b3.pth MODEL.DEVICE cpu` I got this error message `TracerWarning: Iterating over a tensor might cause the trace to be...

> @ayoolaolafenwa please try it again, it should supported now. Thank you! I will test it!

@khanfarhan10 I am planning on releasing the version for custom training with PointRend. I will let you know when it is released.

Thank you @VZed. I am presently busy and I will reach back to you later on it.

@thebigboss84 this is caused by an empty array. Check the json files generated for your dataset and check if any is empty.

@thebigboss84 can you share the dataset and the annotated json files with me?

Thank you @arunmp2004. I am presently busy with some commitments and when I have the time I will work on it.

> Thanks for the response @arunmp2004! How to train from a single JSON file from VGG Image Annotator Tool? @ayoolaolafenwa ?? PixelLib does not support VGG Image Annotator. Annotate your...

> Hi mam, How we can draw loss vs epoch and mAP vs epoch using with pixel lib custom training instance segmentation model. @kavi0786 I have not provided that feature...