Open ssssholmes opened 3 years ago
I tried it and the perfermance at the beginning is pretty pool.
Hi @ssssholmes,
@Jeff-sjtu , Thanks for your reply! One more question, Do you use normalization in the linear layers for the output of sigma in mask rcnn?
@Jeff-sjtu , Thanks for your reply! One more question, Do you use normalization in the linear layers for the output of sigma in mask rcnn?
We don't use normalization in the linear layer for sigma. We just used the sigmoid function after the linear layer.
Hi @ssssholmes,
- We use the original optimizer (sgd) and learning rate in Mask R-CNN, with 180000 iters. And the. Mask R-CNN model is pre-trained with heatmap.
- Yes, the flow model is the same.
- We regress the relative coordinates.
thanks for your great work. i prepare to site your paper. but i meat the mask rcnn's setting issue. in your paper, you said mask rcnn is trained without heatmap pretrain and the trainin schedule is 3X (27000iter). but this is different from the setting you just mentioned above. so can you please provide the excat setting of the mask rcnn you used in you paper? thanks a lot!
Hi @maowayne123,
In Table. 2 in the paper, both the default Mask RCNN and Mask RCNN + RLE are trained with 270,000(3x) iterations. After submission, we retrain Mask RCNN + RLE with the 2x schedule (to see if we can save some time), we found the performance basically the same as the 3x schedule (still 66.7 mAP).
great! thank you!
Hi, I want to train mask rcnn with rle loss!