Songyang Zhang
Songyang Zhang
@dsp6414 We plan to support MobileOne in the future, and contributions are also welcomed. If you have any questions about the contributing, feel free to raise the question and we...
Please provide more information about the running command, which version, what dataset, and environment information to help the discussion. Thanks
Same problem, while I get a 47.5 mAP with the example in the readme. ``` AP for bird = 0.415 AP for bus = 0.480 AP for cow = 0.033...
If the randomness matters a lot, it's difficult to verify the effectiveness of the method.
@yanxp Would you like to share the sampled data split(.pkl) list to make the experiments reproducible?
@Hxx2048 Thanks for your efforts. From my perspective, I think the author need to verify their methods with the bug-fixed `filter_class_roidb`, report the numerical results and provide the data split...
@xiaolonw Would you like to release the torch version of code for ASTN? Thanks a lot.
@PkuRainBow Hi, could you share your training configuration? I try to train PSP on CIityScapes, but get 68 mIOU. I use crop instead of resizing the image and the crop...
meshlab is ok for obj
Hi, logit_scale and logit_bias are class-wise magnitudes and margin(scalar for each class), respectively, as described in the original paper.