I am training mask rcnn using detectron framework and getting below warnings:
WARNING:fvcore.common.checkpoint:Skip loading parameter 'roi_heads.box_predictor.cls_score.weight' to the model due to incompatible shapes: (81, 1024) in the checkpoint but (46, 1024) in the model! You might want to double check if this is expected.
WARNING:fvcore.common.checkpoint:Skip loading parameter 'roi_heads.box_predictor.cls_score.bias' to the model due to incompatible shapes: (81,) in the checkpoint but (46,) in the model! You might want to double check if this is expected.
WARNING:fvcore.common.checkpoint:Skip loading parameter 'roi_heads.box_predictor.bbox_pred.weight' to the model due to incompatible shapes: (320, 1024) in the checkpoint but (180, 1024) in the model! You might want to double check if this is expected.
WARNING:fvcore.common.checkpoint:Skip loading parameter 'roi_heads.box_predictor.bbox_pred.bias' to the model due to incompatible shapes: (320,) in the checkpoint but (180,) in the model! You might want to double check if this is expected.
WARNING:fvcore.common.checkpoint:Skip loading parameter 'roi_heads.mask_head.predictor.weight' to the model due to incompatible shapes: (80, 256, 1, 1) in the checkpoint but (45, 256, 1, 1) in the model! You might want to double check if this is expected.
WARNING:fvcore.common.checkpoint:Skip loading parameter 'roi_heads.mask_head.predictor.bias' to the model due to incompatible shapes: (80,) in the checkpoint but (45,) in the model! You might want to double check if this is expected.
WARNING:fvcore.common.checkpoint:Some model parameters or buffers are not found in the checkpoint:
Also, when I am running this using AMLS pipelines the 70_driverlog log file is not being created. Any help would be appreciated. if this warning needs to be taken care of. what is the meaning of these warnings.
