-
Notifications
You must be signed in to change notification settings - Fork 5.5k
Can not find the source code of Retinanet loss function. #257
Comments
The source code is in caffe2: https://github.com/caffe2/caffe2/blob/master/modules/detectron/select_smooth_l1_loss_op.h |
@ppwwyyxx Thank you. I have read that source code. And I have an other question. The actual parampeters for function 'SelectSmoothL1Loss' are 'retnet_bbox_pred_' + suffix, 'retnet_roi_bbox_targets_' + suffix, 'retnet_roi_fg_bbox_locs_' + suffix and 'retnet_fg_num'. I know that the 'retnet_bbox_pred_' + suffix are calculate by the model, but where do the other three actual parameters 'retnet_roi_bbox_targets_' + suffix, 'retnet_roi_fg_bbox_locs_' + suffix and 'retnet_fg_num' come from? And where can I find the source code that is used to produce the three actual parameters? |
Hi @zhouhao94, the blobs you mention are computed by the functions in this file. |
Updated Link to loss function: https://github.com/pytorch/pytorch/blob/master/modules/detectron/select_smooth_l1_loss_op.h |
Incidentally, here is TF implementation: https://www.tensorflow.org/addons/api_docs/python/tfa/losses/SigmoidFocalCrossEntropy |
I am trying to understand the source code of Retinanet. While I can't find the source code of Retinanet's loss function.
def add_fpn_retinanet_losses(model):
For example, I can't find the source code of 'SelectSmoothL1Loss()' in 'bbox_loss = model.net.SelectSmoothL1Loss()', where the 'model' is an defined detectron model.
Any help? Thanks
The text was updated successfully, but these errors were encountered: