Goddaman

Results 5 comments of Goddaman

How to get validation loss/mAP during VarifocalNet training?

I met the same problem. Have you found how to solve it?

The parameters and computation decreased, but FPS was worse than the baseline model

> I had only tested it on Nvidia GPUs before. After seeing your reply, I tested it on CPU, and the FPS was increased on CPU. Maybe some performance issues...

DETR VAL mAP 0.0000

same issue, did u fix it?

Training the model causes the issue.

i meet the same problem, did you solve it?

yolov8剪枝前后权重大小没变，推理速度也没变

权重大小没变是因为target-prune-rate设置的不够大，设置成0.5，权重就变小了。 但是在gpu上的推理速度仍然没有改变，在cpu上剪枝后的推理速度是推理前的1.59倍。 我想问一下，为什么在gpu上的推理速度没有变快啊？