Jim Bohnslav
Jim Bohnslav
I have the exact same issue. Are the frames freed after they are used, or something? Here's my example: ```python import resource import time import decord video_list = ['video1.mp4', 'video2.mp4',...
what's the codec on the video file you're reading? I've found that decord does not match imageio for MJPG videos-- seems the JPG decoder is not identical
I have the same issue on one of my videos-- CPU only. I then tried `vr.next()` and got a more specific error message: ``` /github/workspace/src/video/ffmpeg/threaded_decoder.cc:292: [12:57:23] /github/workspace/src/video/ffmpeg /threaded_decoder.cc:218: Check failed:...
I can confirm both that this bug still exists in 0.5.0, and that setting `perspective_correct=False` removes the issue. I ran my code with torch anomaly detection on, not sure if...
When I first started DeepEthogram all the datasets available to me were multi-label (1+ at a time) rather than multiclass (1 at a time). We don't describe this in the...
You do definitely need to re-train if you use the softmax activation.
On the list!
can you try to `pip install --upgrade deepethogram` and see if it's fixed?
Hi there, what OS are you working on? If you're comfortable with trying Docker, I just pushed some docker images. That should give a 100% reproducible environment, which should fix...
Hey Sean, I haven't done that exact comparison, but if you wanted to do the comparison and compare to opencv, feel free to submit a pull request! Best, Jim On...