json detectron2训练键错误

m2xkgtsf 于 12个月前发布在其他

关注(0)|答案(2)|浏览(74)

我试图用detectron 2训练我自己的COCO数据集，但是当我开始自己的训练时，我遇到了一个关键错误
KeyError：'类别_id

error code : https://i.stack.imgur.com/yO5IO.png

//this is the code i am training with 
from detectron2.engine import DefaultTrainer
from detectron2.config import get_cfg
import os

cfg = get_cfg()
cfg.merge_from_file(model_zoo.get_config_file("COCO- 
InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml"))
cfg.DATASETS.TRAIN = ("coco_train_new",)
cfg.DATASETS.TEST = ()
cfg.DATALOADER.NUM_WORKERS = 2
cfg.MODEL.WEIGHTS = "detectron2://COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl"  
cfg.SOLVER.IMS_PER_BATCH = 2
cfg.SOLVER.BASE_LR = 0.00025  # pick a good LR
cfg.SOLVER.MAX_ITER = 1000    # 300 iterations seems good enough for this toy dataset; you may need to train longer for a practical dataset
cfg.MODEL.ROI_HEADS.BATCH_SIZE_PER_IMAGE = 512   # faster, and good enough for this toy dataset (default: 512)
cfg.MODEL.ROI_HEADS.NUM_CLASSES = 1  # only has one class (ballon)

os.makedirs(cfg.OUTPUT_DIR, exist_ok=True)
trainer = DefaultTrainer(cfg) 
trainer.resume_or_load(resume=False)
trainer.train()

字符串
所以我回去检查我的COCO json文件，但是json文件是用标准COCO格式输出的，有什么想法可能会导致问题吗
p.s我正在用detectron2示例代码训练数据，所以我认为应该没有问题

JSON

来源：https://stackoverflow.com/questions/63582319/detectron2-training-keyerror

2条答案

按热度按时间

qni6mghb1#

我猜（没有看你的json构造代码）你在注解中缺少了'category_id'。你可以按照下面的方法来创建一个类。

# Main dict
    dataset_dicts = {"images": [],
                     "type": "Balloon-detection",
                     "annotations": [],
                     "categories": []
                     }
    # Adding categories. At the moment only for balloon.
    category = {'supercategory': 'object', 'id': 1, 'name': 'balloon'}
    dataset_dicts['categories'].append(category)

    for <iterate for all images>:
    ....
    ....
        for <iterate for all objects>:
        ....
        ....
            # Save annotation
            annotation = {
                    'image_id': index,
                    "bbox": [xmin, ymin, o_width, o_height],
                    "area": o_width*o_height,
                    "bbox_mode": BoxMode.XYWH_ABS,

                    "category_id": 1,
                    "iscrowd": 0,
                    'id': annotation_id
                }
                dataset_dicts['annotations'].append(annotation)

字符串
希望你明白了。

赞(0）回复(0）举报 12个月前

sauutmhj2#

以防万一..

赞(0）回复(0）举报 12个月前