-
Hi, I'm wondering have you changed a two-stage net like faster-rcnn or FPN to a one-stage net like the paper said? Do I just need to change the softmax loss layer to your focal loss layer for classifi…
-
https://github.com/open-mmlab/mmdetection/blob/f78af7785ada87f1ced75a2313746e4ba3149760/mmdet/models/task_modules/assigners/match_cost.py#L252C1-L269C38
When the input is not binary, why in line 26…
-
Hi, I am using your implementation of focal loss, and sometimes the value calculated is nan. I realized that it is due to the normalization in terms of positive samples in the batch since I am working…
-
Hi,
is it possible to modify this function to focal loss ? if so , please add this loss.
-
Hi,
I noticed that you removed the weight that balances the losses of different positions, which is a part of the focal frequency loss.
I wonder why that is. Did you observe a performance degra…
-
https://github.com/fundamentalvision/Deformable-DETR/blob/11169a60c33333af00a4849f1808023eba96a931/models/segmentation.py#L221
The focal loss is computed on all object queries (i.e. suppose `num_qu…
-
Thanks for your released code.
When conducting experiments on the Horse scene, Francis scene and Church scene of the Tanks dataset using the default.yaml file, I found that the results were much wo…
-
Hi, I think there is probably a mistake in here:
https://github.com/qubvel/segmentation_models/blob/a6fbf2d5ea21081929df634d095d389211e649ef/segmentation_models/base/functional.py#L281.
The values i…
-
Hi,thank you for sharing the code, I use you provided fockl loss to replace the the softmaxloss used in the fast-rcnn phase of faster-rcnn. But he training accuracy is only 65%. Is there any trainin…
LXWDL updated
6 years ago
-
Thank you for your great work! I have a problem when I tried to run your model on my single computer. The quality focal loss is so big up to value 2000-3000. Do you have any idea to solve this problem…