Anuar
Anuar
FYI, when I tried `torch2trt()` on my 2080 Ti it didn't give any keypoint output. However on Jetson it worked.
Pytorch 1.3.0, TensorRT 6.0.1.5, Torchvision 0.4.1, CUDA 10.0, 2080 Ti. I tried it quickly, I can try it again on Monday. I had different versions on Xavier (Pytorch 1.1, TensorRT...
Is there any chance this PR gets accepted? I was actually facing the exact problem this PR is trying to fix.
Sorry I realized what I was talking about is called smoothing, specifically what I am looking for is "fixed-lag smoother" and "RTS smoother" in the literature.
Great, thanks for a thorough reply! Yeah I agree that starting with a pre-trained detector and only fine-tuning the tracker would make sense. I am not 100% from the code...
I will let you how my development goes, if anything I could submit a PR.
So I first wanted to train a detector KerasYOLO.py. I think I changed all the right things (anchors, labels, etc...) but I get non-sense low-confidence predictions after training, even though...
@tomanick @qichenghan666 @HorusMaster Did you guys try to validate this model on datasets from the paper (Kinetics, Charades or anything else)? Does the accuracy look representative of the paper?
@ariel415el thank you! So as far as I understood you first converted your TF model to ONNX and then used TensorRT to deploy it in C++? Would be great if...
Is there any solution to this? I can't see print statements either