Closed mattroos closed 1 year ago
It is specified in mmdet's default dataset config. The current configs inherit the default dataset config: https://github.com/open-mmlab/mmdetection/blob/master/configs/_base_/datasets/coco_instance.py
I see. So neither train nor test ann_file
and img_prefix
need to be specified in configs/focalnet/cascade_mask_rcnn_focalnet_tiny_patch4_mstrain_480-800_adamw_3x_coco_srf.py
if they are correctly specified in the mmdet's default config, to my understanding.
If someone wanted to alter the paths for the training set would it look something list this train=dict(pipeline=train_pipeline, ann_file=path/to/json.json, img_prefix=path/to/prefix/)
in configs/focalnet/cascade_mask_rcnn_focalnet_tiny_patch4_mstrain_480-800_adamw_3x_coco_srf.py
?
Hi, @mattroos , yes, you are correct.
In the example config file
configs/focalnet/cascade_mask_rcnn_focalnet_tiny_patch4_mstrain_480-800_adamw_3x_coco_srf.py
we see:
Why are
ann_file
andimg_prefix
defined in thetest
dict but not in thetrain
dict? Where should the paths be specified for the training set?