It needs val_json_file=${PATH_GCS_MASKRCNN:?}/instances_val2017.json as input. However, the annotations already exist in tf record files and should not be duplicated as another input.
By the way, a lot of coco stuff messed up with the whole mask rcnn pipeline, for example, coco_utils.py and coco_metric.py, which should be removed and otherwise the whole model sounds like to make coco training work but not for general datasets.
In the tutorial https://cloud.google.com/tpu/docs/tutorials/mask-rcnn
It needs
val_json_file=${PATH_GCS_MASKRCNN:?}/instances_val2017.json
as input. However, the annotations already exist in tf record files and should not be duplicated as another input.By the way, a lot of
coco
stuff messed up with the whole mask rcnn pipeline, for example,coco_utils.py
andcoco_metric.py
, which should be removed and otherwise the whole model sounds like to make coco training work but not for general datasets.