Vidit comments

Results 26 comments of


                                            Vidit

Why the summary of dAps and bbox ap is not 100%?

section 2.3 and appendix A.1 of the paper highlight this oddity of the mAP score.

reproducibility and domain classifier loss

Thank you for your answer. The above reported numbers are after da+ca training, but I initialise the second stage training with the weights at 20k iterations. I will try to...

reproducibility and domain classifier loss

Thanks for this update. Yes, I see that for the second stage that all the adversarial losses don't go to zero(p7-p5). Could you please tell me how to run the...

reproducibility and domain classifier loss

Thanks for the pointers. Another question that I have is how do you decide to which iteration's weight to take to initialize for the second stage's training. Do you use...

reproducibility and domain classifier loss

@chengchunhsu for sim10k->cityscapes without DA, for how many iterations do you train your network? Simply, setting `DA_ON` as `False`, did not work for me. I set `USE_DIS_GLOBAL` as `False`, also...

reproducibility and domain classifier loss

thanks, @andgitchang for your clarifications but I still don't get how the original FCOS repo will get me source only result as it was not trained on Sim10k.

reproducibility and domain classifier loss

@andgitchang I also need to know what is the learning rate used and for how many iterations the network is trained for.

reproducibility and domain classifier loss

> In most of our experiments, the pretrained iteration was set as 5k or 10k, except we set 2k for the KITTI dataset since it requires less training iterations. >...

reproducibility and domain classifier loss

Hi Cheng-Chun, I trained the source only model for 24k iteration and lr 0.005. I could get 39.9 for sim10k-->cityscapes. Previously, I had trained for 80k iteration following the example...

reproducibility and domain classifier loss

Thanks Cheng-Chu for the clarifications.