clover978

did you solve it? I met the same problem.

I did similar experments. The conclusion is consistent. I use onnxruntime to profile exported two onnx files on rtx3090. Inference code is exactly the same except for the onnx files...

> so why lite-hrnet cost more time than hrnet? then why we need lite-hrnet? @clover978 Maybe lite-hrnet result in better efficiency on specific hardware (e.g. CPU, FPGA)，since it does have...

I met exactlly the same problem. Have you figure out is this situation normal or unnormal?

Hi, @alexandrepdumont To my understanding, for the dataset downloaded from original [repo ](https://nol.cs.nctu.edu.tw:234/open-source/TrackNetv2), the code is correct. `heat_map = genHeatMap(WIDTH, HEIGHT, int(label[2]/ratio), int(label[3]/ratio), sigma, mag)` For dataset generated by [`imgLabel.py`](https://github.com/Chang-Chia-Chi/TrackNet-Badminton-Tracking-tensorflow2/blob/main/imgLabel.py),...

The training is still in progress. But I don't think the eleluation result is quiet normal. The accuracy become 0.74 in the very beginning and start to zigzag. ``` ==========Epoch...

> Yes you are quite right, I took out the ratio on subsequent training, as all it did as far as I saw was expand the images into 2.5x the...