FSCE
FSCE copied to clipboard
I can not get the same results in split 1 and shot 10? I just have one gpu 3090.
I just have one gpu 3090. And I do not change config, like lr and batchsize, how can I get the same result with paper? My nAP50 = 60.8 (paper = 63.4) final model (http://dl.yf.io/fs-det/model/) datasets (http://dl.yf.io/fs-det/datasets/vocsplit/*.txt)
Hello, how did you compile the code on the 3090 using cuda 11.0.
Hello, how did you compile the code on the 3090 using cuda 11.0.
I can not compile the code on the 3090, but you can run it with detectron2.
Hello, how did you compile the code on the 3090 using cuda 11.0.
I can not compile the code on the 3090, but you can run it with detectron2.
I have reproduced the same results, I think there are several reasons:
- the best model is not the final results, you can try some other checkpoints saved by different steps.
- try 2 GPUs or more, I have tried, and the results with a single GPU are pretty lower than multi GPUs (61 -> 64).
I use the official compilation, not the detectron2
provided by the author.
收到,谢谢!