Open yd8534976 opened 4 years ago
To support this feature, we have to modify blueoil/networks/base.py
, blueoil/cmd/train.py
, blueoil/datasets/dataset_iterator.py
. But if we modify theses files directly, we would also have to change hundreds of files like #618 . If so, the PR will be too large to be reviewed. So we could add new files like blueoil/networks/base_multi.py
, blueoil/cmd/train_multi.py
, blueoil/datasets/dataset_iterator_multi.py
instead of modifying them directly. If so, lines of code can be controlled and the PRs will be reviewable.
blueoil/datasets/dataset_iterator_multi.py
blueoil/datasets/widerface_multi.py
blueoil/networks/base_multi.py
blueoil/networks/object_detection/yolo_utils.py
blueoil/networks/object_detection/yolo_v2_multi.py
blueoil/cmd/train_multi.py
blueoil/configs/core/object_detection/yolo_v2_multi_widerface.py
Currently, we can only use
(images, labels)
pair to feed a model. It is not flexible for a complicated model. Sometimes, we may face cases like(images, labels_1, labels_2..)
. We have to take it into account.