detectron2 train with own datasets

最新推荐文章于 2024-11-13 10:16:50 发布

原创最新推荐文章于 2024-11-13 10:16:50 发布 · 372 阅读

1 ·

CC 4.0 BY-SA版权

文章标签：

#深度学习

pytorch 专栏收录该内容

6 篇文章

订阅专栏

本文详细介绍了如何使用Detectron2框架进行自定义数据集的注册、配置及模型训练过程。从数据集路径设定到YAML配置文件修改，再到训练模型的最终运行，全面覆盖了自定义数据集在Detectron2中的应用流程。

1. detecton2/data/datasets/builtin.py

#appoint self datasets path

self_datasets_root = 'datasets'

2. coco_self_train coco_self_val

#appoint self datasets path
self_datasets_root = 'datasets'
_PREDEFINED_SPLITS_COCO = {}
_PREDEFINED_SPLITS_COCO["coco"] = {
    "coco_2014_train": ("coco/train2014", "coco/annotations/instances_train2014.json"),
    "coco_2014_val": ("coco/val2014", "coco/annotations/instances_val2014.json"),
    "coco_2014_minival": ("coco/val2014", "coco/annotations/instances_minival2014.json"),
    "coco_2014_minival_100": ("coco/val2014", "coco/annotations/instances_minival2014_100.json"),
    "coco_2014_valminusminival": (
        "coco/val2014",
        "coco/annotations/instances_valminusminival2014.json",
    ),
    "coco_2017_train": ("coco/train2017", "coco/annotations/instances_train2017.json"),
    "coco_2017_val": ("coco/val2017", "coco/annotations/instances_val2017.json"),
    "coco_2017_test": ("coco/test2017", "coco/annotations/image_info_test2017.json"),
    "coco_2017_test-dev": ("coco/test2017", "coco/annotations/image_info_test-dev2017.json"),
    "coco_2017_val_100": ("coco/val2017", "coco/annotations/instances_val2017_100.json"),
    "coco_self_train":("metal/train", "metal/annotations/instances_train.json"),
    "coco_self_val":("metal/val","metal/annotations/instances_val.json"),
}

#def register_all_coco(root="datasets"):
def register_all_coco(root=self_datasets_root):
    for dataset_name, splits_per_dataset in _PREDEFINED_SPLITS_COCO.items():
        for key, (image_root, json_file) in splits_per_dataset.items():
            # Assume pre-defined datasets live in `./datasets`.
            register_coco_instances(
                key,
                _get_builtin_metadata(dataset_name),
                os.path.join(root, json_file) if "://" not in json_file else json_file,
                os.path.join(root, image_root),
            )

    for (
        prefix,
        (panoptic_root, panoptic_json, semantic_root),
    ) in _PREDEFINED_SPLITS_COCO_PANOPTIC.items():
        prefix_instances = prefix[: -len("_panoptic")]
        instances_meta = MetadataCatalog.get(prefix_instances)
        image_root, instances_json = instances_meta.image_root, instances_meta.json_file
        register_coco_panoptic_separated(
            prefix,
            _get_builtin_metadata("coco_panoptic_separated"),
            image_root,
            os.path.join(root, panoptic_root),
            os.path.join(root, panoptic_json),
            os.path.join(root, semantic_root),
            instances_json,
        )

4: modify the yaml configure file in configs: for example: configs/Base-RCNN-FPN.yaml

MODEL:
  META_ARCHITECTURE: "GeneralizedRCNN"
  BACKBONE:
    NAME: "build_resnet_fpn_backbone"
  RESNETS:
    OUT_FEATURES: ["res2", "res3", "res4", "res5"]
  FPN:
    IN_FEATURES: ["res2", "res3", "res4", "res5"]
  ANCHOR_GENERATOR:
    SIZES: [[32], [64], [128], [256], [512]]  # One size for each in feature map
    ASPECT_RATIOS: [[0.5, 1.0, 2.0]]  # Three aspect ratios (same for all in feature maps)
  RPN:
    IN_FEATURES: ["p2", "p3", "p4", "p5", "p6"]
    PRE_NMS_TOPK_TRAIN: 2000  # Per FPN level
    PRE_NMS_TOPK_TEST: 1000  # Per FPN level
    # Detectron1 uses 2000 proposals per-batch,
    # (See "modeling/rpn/rpn_outputs.py" for details of this legacy issue)
    # which is approximately 1000 proposals per-image since the default batch size for FPN is 2.
    POST_NMS_TOPK_TRAIN: 1000
    POST_NMS_TOPK_TEST: 1000
  ROI_HEADS:
    NAME: "StandardROIHeads"
    IN_FEATURES: ["p2", "p3", "p4", "p5"]
  ROI_BOX_HEAD:
    NAME: "FastRCNNConvFCHead"
    NUM_FC: 2
    POOLER_RESOLUTION: 7
  ROI_MASK_HEAD:
    NAME: "MaskRCNNConvUpsampleHead"
    NUM_CONV: 4
    POOLER_RESOLUTION: 14
DATASETS:
  TRAIN: ("coco_self_train",)  #("coco_2017_train",)
  TEST: ("coco_self_val",)  #("coco_2017_val",)
SOLVER:
  IMS_PER_BATCH: 16
  BASE_LR: 0.02
  STEPS: (60000, 80000)
  MAX_ITER: 90000
INPUT:
  MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
VERSION: 2

5: change the catalog.py ./detectron/data/transforms/catalog.py

# def __setattr__(self, key, val):
#     if key in self._RENAMED:
#         log_first_n(
#             logging.WARNING,
#             "Metadata '{}' was renamed to '{}'!".format(key, self._RENAMED[key]),
#             n=10,
#         )
#         setattr(self, self._RENAMED[key], val)
#
#     # Ensure that metadata of the same name stays consistent
#     try:
#         oldval = getattr(self, key)
#         assert oldval == val, (
#             "Attribute '{}' in the metadata of '{}' cannot be set "
#             "to a different value!\n{} != {}".format(key, self.name, oldval, val)
#         )
#     except AttributeError:
#         super().__setattr__(key, val)

finaly, run the train model:

python tools/train_net.py --config-file configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml SOLVERS.IMS_PER_BATCH 2 SOLVER.BASE_LR 0.0025