please help!AssertionError: Attribute 'thing_classes' in the metadata of 'coco_2017_train_edge' cannot be set to a different value!

[zhenghan408]

when i training my own dataset ,have the problem about: AssertionError: Attribute 'thing_classes' in the metadata of 'coco_2017_train_edge' cannot be set to a different value!

['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light', 'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow', 'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee', 'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard', 'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch', 'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', 'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear', 'hair drier', 'toothbrush'] != ['building']

please give a suggestion~

[lkevinzc]

Hi @zhenghan408 , thanks for attention! Seems that you are training on a dataset for building. I think you need to prepare your dataset following the COCO format, and then register it, afterwards specifying the dataset in your training config .yaml file.

[zhenghan408]

Hi @zhenghan408 , thanks for attention! Seems that you are training on a dataset for building. I think you need to prepare your dataset following the COCO format, and then register it, afterwards specifying the dataset in your training config .yaml file.

hi,thanks very much!however ,i face another question: ERROR [07/10 16:13:04 d2.engine.train_loop]: Exception during training: Traceback (most recent call last): File "/media/dxy/EE36CE0236CDCBB1/zh/detectron2/detectron2/engine/train_loop.py", line 132, in train self.run_step() File "/media/dxy/EE36CE0236CDCBB1/zh/detectron2/detectron2/engine/train_loop.py", line 214, in run_step loss_dict = self.model(data) File "/home/dxy/anaconda3/envs/dance/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in call result = self.forward(*input, *kwargs) File "/media/dxy/EE36CE0236CDCBB1/zh/dance-master/core/modeling/edge_snake/dance.py", line 140, in forward features, proposals, (gt_sem_seg, [gt_instances, images.image_sizes]) File "/home/dxy/anaconda3/envs/dance/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in call result = self.forward(input, kwargs) File "/media/dxy/EE36CE0236CDCBB1/zh/dance-master/core/modeling/edge_snake/edge_det.py", line 273, in forward edge_loss = self.loss(pred_edge_full, edge_target) self.loss_weight File "/home/dxy/anaconda3/envs/dance/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in call result = self.forward(input, kwargs) File "/media/dxy/EE36CE0236CDCBB1/zh/dance-master/core/layers/losses.py", line 121, in forward if len(target.size()) == 3: AttributeError: 'NoneType' object has no attribute 'size' [07/10 16:13:04 d2.engine.hooks]: Total training time: 0:00:02 (0:00:00 on hooks)

can you give some suggestions?beg you~

[lkevinzc]

Seems that you did not have the edge map for edge supervision. Can please try to use the scripts to generate the object contour map based on the mask annotation first? The example code is here: https://github.com/lkevinzc/dance/blob/master/datasets/prepare_edge_map_cityscapes.py

[zhenghan408]

Seems that you did not have the edge map for edge supervision. Can please try to use the scripts to generate the object contour map based on the mask annotation first? The example code is here: https://github.com/lkevinzc/dance/blob/master/datasets/prepare_edge_map_cityscapes.py

i did this ,however,then ,Do I need to modify anything?because ,i have the contour map but the error no change

i use the command：python train_net.py --num-gpus 1 --config-file configs/Dance_R_50_3x.yaml

[lkevinzc]

You may need to modify the config file to add your dataset like this:

_BASE_: "Base-DANCE.yaml"
MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  RESNETS:
    DEPTH: 50
  EDGE_HEAD:
    NAME: "EdgeSnakeFPNHead"
    CONVS_DIM: 256
    STRONG_FEAT: True
    IN_FEATURES: ['p2', 'p3', 'p4', 'p5']
  SNAKE_HEAD:
    NUM_SAMPLING: 196
    DETACH: True
    INITIAL: 'box'
    NEW_MATCHING: True
    ATTENTION: True
    INDIVIDUAL_SCALE: True
DATASETS: # <----------------------------------------- modification!
  TRAIN: ("your_dataset_train",)
  TEST: ("your_dataset_test",)
SOLVER:
  STEPS: (480000, 520000)
  MAX_ITER: 540000
  CHECKPOINT_PERIOD: 60000
OUTPUT_DIR: "output/coco/dance_r50_3x/"

Then, you also need to register your dataset by modifying core/data/builtin.py. You can check the Detectron2 tutorial for this.

It may take some time to learn the Detectron2 framework, but after you get familiar with it you can do a lot with it :)

[zhenghan408]

''' Register COCO dataset with edge map annotations '''

SPLITS_COCO_W_EDGE = { "zh_train": (

original directory/annotations coco detection

    "coco/train2017",
    "coco/annotations/instances_train2017.json",
    # directory for edge map created by datasets/prepare_edge_map.py
    # takes ~ 12 mins on a machine with 64 Xeon(R) Gold 6130 CPUs
    "coco/edge_train2017"
),
"zh_val": (
    "coco/val2017",
    "coco/annotations/instances_val2017.json",
    "/coco/edge_val2017"
),

}

def register_all_coco_edge(root="datasets"): for name, (image_root, json_file, edge_root) in SPLITS_COCO_W_EDGE.items():

Assume pre-defined datasets live in ./datasets.

    register_coco_edge_map(
        name,
        _get_builtin_metadata("coco"),
        os.path.join(root, image_root),
        os.path.join(root, edge_root),
        os.path.join(root, json_file) if "://" not in json_file else json_file
    )

register_all_coco_edge()

[zhenghan408]

You may need to modify the config file to add your dataset like this:

_BASE_: "Base-DANCE.yaml"
MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  RESNETS:
    DEPTH: 50
  EDGE_HEAD:
    NAME: "EdgeSnakeFPNHead"
    CONVS_DIM: 256
    STRONG_FEAT: True
    IN_FEATURES: ['p2', 'p3', 'p4', 'p5']
  SNAKE_HEAD:
    NUM_SAMPLING: 196
    DETACH: True
    INITIAL: 'box'
    NEW_MATCHING: True
    ATTENTION: True
    INDIVIDUAL_SCALE: True
DATASETS: # <----------------------------------------- modification!
  TRAIN: ("your_dataset_train",)
  TEST: ("your_dataset_test",)
SOLVER:
  STEPS: (480000, 520000)
  MAX_ITER: 540000
  CHECKPOINT_PERIOD: 60000
OUTPUT_DIR: "output/coco/dance_r50_3x/"

Then, you also need to register your dataset by modifying core/data/builtin.py. You can check the Detectron2 tutorial for this.

It may take some time to learn the Detectron2 framework, but after you get familiar with it you can do a lot with it :)

after i register my datasets , the new problem:

Traceback (most recent call last): File "train_net.py", line 82, in args=(args,), File "/media/dxy/EE36CE0236CDCBB1/zh/detectron2/detectron2/engine/launch.py", line 52, in launch main_func(*args) File "train_net.py", line 67, in main trainer = Trainer(cfg) File "/media/dxy/EE36CE0236CDCBB1/zh/detectron2/detectron2/engine/defaults.py", line 253, in init data_loader = self.build_train_loader(cfg) File "/media/dxy/EE36CE0236CDCBB1/zh/detectron2/detectron2/engine/defaults.py", line 430, in build_train_loader return build_detection_train_loader(cfg) File "/media/dxy/EE36CE0236CDCBB1/zh/detectron2/detectron2/data/build.py", line 362, in build_detection_train_loader proposal_files=cfg.DATASETS.PROPOSAL_FILES_TRAIN if cfg.MODEL.LOAD_PROPOSALS else None, File "/media/dxy/EE36CE0236CDCBB1/zh/detectron2/detectron2/data/build.py", line 225, in get_detection_dataset_dicts dataset_dicts = [DatasetCatalog.get(dataset_name) for dataset_name in dataset_names] File "/media/dxy/EE36CE0236CDCBB1/zh/detectron2/detectron2/data/build.py", line 225, in dataset_dicts = [DatasetCatalog.get(dataset_name) for dataset_name in dataset_names] File "/media/dxy/EE36CE0236CDCBB1/zh/detectron2/detectron2/data/catalog.py", line 62, in get return f() File "/media/dxy/EE36CE0236CDCBB1/zh/dance-master/core/data/datasets/register_coco_edge.py", line 14, in load_coco_json(instances_json, image_root, ds_name), File "/media/dxy/EE36CE0236CDCBB1/zh/detectron2/detectron2/data/datasets/coco.py", line 70, in load_coco_json meta.thing_classes = thing_classes File "/media/dxy/EE36CE0236CDCBB1/zh/detectron2/detectron2/data/catalog.py", line 137, in setattr "to a different value!\n{} != {}".format(key, self.name, oldval, val) AssertionError: Attribute 'thing_classes' in the metadata of 'zh_train' cannot be set to a different value! ['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light', 'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow', 'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee', 'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard', 'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch', 'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', 'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear', 'hair drier', 'toothbrush'] != ['building']

[lkevinzc]

Hi @zhenghan408 , it still seems to be the dataset registration issue. I would suggest that you use any model in Detectron2 first and follow the tutorial to successfully train on your dataset, then running DANCE using similar registration codes should be fine.

[zhenghan408]

Hi @zhenghan408 , it still seems to be the dataset registration issue. I would suggest that you use any model in Detectron2 first and follow the tutorial to successfully train on your dataset, then running DANCE using similar registration codes should be fine.

thanks a lot ,i want to ask a simple question: i use the code :https://github.com/lkevinzc/dance/blob/master/datasets/prepare_edge_map_cityscapes.py do i also use the code:https://github.com/lkevinzc/dance/blob/master/datasets/prepare_edge_map.py

[lkevinzc]

Hi @zhenghan408 , it still seems to be the dataset registration issue. I would suggest that you use any model in Detectron2 first and follow the tutorial to successfully train on your dataset, then running DANCE using similar registration codes should be fine.

thanks a lot ,i want to ask a simple question: i use the code :https://github.com/lkevinzc/dance/blob/master/datasets/prepare_edge_map_cityscapes.py do i also use the code:https://github.com/lkevinzc/dance/blob/master/datasets/prepare_edge_map.py

Hi @zhenghan408 , actually they are a bit different. The "prepare_edge_map_cityscapes.py" one is for data that is in COCO format; the "prepare_edge_map.py" further requires panoptic annotation (that's why you can see this import).

If your data is in COCO format but does not have panoptic annotation, just use the first one :)