fatih akyon
fatih akyon
I am having a similar issue on a custom dataset of only 1 class. It may be not related to the imbalance.
@LinB203 is there any video predict code in the repo to test it on a mp4 file? Or a preprocessing script showing how to sample the frames from a video?
@mkolomeychenko release v5.0 is not stable there are lots of bug fixes after release 5.0 (@glenn-jocher can you confirm it?), are you going to synronize with the ultralytiucs/yolov5 repos current...
@mkolomeychenko @glenn-jocher are you going to update the outdated supervisely yolov5 app to yolov5 v7.0?
It's in utils.general in the latest versions: https://github.com/ultralytics/yolov5/blob/fde77584687041aa62795bb2c27e895cf73686bf/utils/general.py#L242 But icevision should be used with `yolov5-icevision` package I believe: https://github.com/airctic/icevision/blob/b6b70ad5fe5fa168d4d44d122b433ad1aaf1959c/setup.cfg#L38
@Carlson-J thanks for the fix. It would be better to pin min sahi version to `0.11.1` since there have been many bug fixes and performance improvements since `sahi==0.8.*` I have...
I have also opened a PR adding support to latest sahi version: https://github.com/airctic/icevision/pull/1156
Hello @wangzhaoyang-508, why did you delete the original readme file?
Hey @sergiev, thanks for your fantastic contribution! Do you plan to add some tests for your case into test_shapelyutils.py?
what do you think about this implementation @sergiev? It fixes the same problem in a different way. https://github.com/obss/sahi/pull/1047/files