Closed xiaoliqiangxxqzz closed 2 years ago
@thomasehuang @xinw1012 I'm sorry to bother you, but could you give me some advice?
Which model/config are you running? That is very similar to the results reported, at least for the FRCN+ft-full model:
name | nAP |
---|---|
FRCN+ft-full | 5.5 |
TFA w/ fc | 9.1 |
TFA w/ cos | 9.1 |
Which model/config are you running? That is very similar to the results reported, at least for the FRCN+ft-full model:
name AP FRCN+ft-full 5.5 TFA w/ fc 9.1 TFA w/ cos 9.1
I use the model with cos classifier of 10 shot, and the models and data used are all provided by them.
Hi, thanks for your interest in our work. Just to confirm, did you try to download the models from the model zoo directly? https://github.com/ucbdrive/few-shot-object-detection/blob/master/docs/MODEL_ZOO.md#10-shot-3? Can you verify the evaluation setups? We also released the training/eval logs in metrics
so you may use it as an indicator for any discrepancy. There should not be a difference if you were using the pre-trained models. You can keep updating us if you have additional information on your experiment setups.
Thanks!
When I used the 10shot model you trained on the Coco, I found that the AP was only 5.002![1620733393(1)](https://user-images.githubusercontent.com/20881108/117810023-7782e080-b291-11eb-9360-68bbb5ca00f1.png)
Is there anything I should pay attention to?