Upon trying to use the Mask R-CNN ECANet-50 weights with MMDetection for simple inference, we (@iyaja) faced several issues which are listed below:
Kernel Size discrepancy in the backbone ECANet-50 which we solved by having k_size to be 3 for the first two blocks and 7 for the last two in the backbone.
For the mask head, the ECANet uses 81 classes instead of 80 which is used as default in MMDetection configs where the +1 class is accounted for the background class.
For the Regression head, because of the 81 classes the input layer in the Linear layer now changed to 324 instead of 320 as in the default MMDetection config.
Because MMDetection was updated with the bbox_head and mask_head keys being shifted to roi_head super keys, there is a key mismatch between the state_dict of the weights provided in this repository and the config in MMDetection.
Even after fixing the above issues, we were not able to obtain valid results, example:
Expected result:
We would like the authors to share which commit hash of MMDetection they used to obtain the results. Additionally, it would be very beneficial if the authors could add a dedicated folder providing the code to run both training and inference for all the object detection and segmentation models presented in the paper.
Upon trying to use the Mask R-CNN ECANet-50 weights with MMDetection for simple inference, we (@iyaja) faced several issues which are listed below:
Even after fixing the above issues, we were not able to obtain valid results, example:
Expected result:
We would like the authors to share which commit hash of MMDetection they used to obtain the results. Additionally, it would be very beneficial if the authors could add a dedicated folder providing the code to run both training and inference for all the object detection and segmentation models presented in the paper.