You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I followed these instructions to serve a Mask R-CNN model via pytorch serve. Inference on an example image works fine, however returns only bounding boxes, class labels and score. Segmentation masks are missing.
Reproduction
I looked into the mmdet_handler.py and it seems to me that in the postprocess method the segm_result is not properly included in the returned output.
I tried to include segm_result into the output list, however got errors like
Describe the bug
I followed these instructions to serve a Mask R-CNN model via pytorch serve. Inference on an example image works fine, however returns only bounding boxes, class labels and score. Segmentation masks are missing.
Reproduction
I looked into the mmdet_handler.py and it seems to me that in the
postprocess
method thesegm_result
is not properly included in the returned output.I tried to include
segm_result
into the output list, however got errors likeand
I guess, some other parts of the code need to be altered. However, I am not familiar enough with the code base to make these changes.
Environment
python mmdet/utils/collect_env.py
to collect necessary environment information and paste it here.The text was updated successfully, but these errors were encountered: