[BUG]在使用paddleDetection时候，使用VOC数据集导出的模型的infer_info的label_list与正常一样，但是每次使用COCO数据集，指点数据集的位置和分类的种类数目，但是每次导出模型的infer_info的label_list都是80个，且模型无效，不能预测出测试集的目标。

[Craw-B]

在我的coco数据集的格式如下 metric: COCO num_classes: 4

TrainDataset: !COCODataSet image_dir: images anno_path: annotations/train.json dataset_dir: dataset/roadsign_coco data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']

EvalDataset: !COCODataSet image_dir: images anno_path: annotations/valid.json dataset_dir: dataset/roadsign_coco

TestDataset: !ImageFolder anno_path: annnotations/valid.json 但是导出模型就先80个，而且无法进行预测和部署 如下 mode: fluid draw_threshold: 0.5 metric: COCO use_dynamic_shape: false arch: SSD min_subgraph_size: 60 Preprocess:

• interp: 1 keep_ratio: false target_size:
  • 300
  • 300 type: Resize
• is_scale: true mean:
  • 0.485
  • 0.456
  • 0.406 std:
  • 0.229
  • 0.224
  • 0.225 type: NormalizeImage
• type: Permute label_list:
• 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

[ghostxsl]

https://github.com/PaddlePaddle/PaddleDetection/blob/develop/configs/datasets/coco_detection.yml#L19 更换指定anno_path内的json文件里的标注类别名称

[Craw-B]

你的意思时写成拒绝路径对吗，按照这个coco_detection的例子他不是绝对路经啊。我不太懂你的意思，我如果要用自己的coco数据应该怎么办，能给我一个具体的指导意见吗，卡了好几天了

[ghostxsl]

如果你没有指定anno_file，框架会默认加载coco的类别标签，参考：https://github.com/PaddlePaddle/PaddleDetection/blob/develop/ppdet/engine/trainer.py#L545

[ghostxsl]

anno_file得写成绝对路径，要么你就直接在代码里改也行，参考：https://github.com/PaddlePaddle/PaddleDetection/blob/b615336fe3a9ff740fdb1b889be7bc865b6d20fa/ppdet/data/source/category.py#L29

[paddle-bot-old[bot]]

Since this issue has not been updated for more than three months, it will be closed, if it is not solved or there is a follow-up one, please reopen it at any time and we will continue to follow up. It is recommended to pull and try the latest code first. 由于该问题超过三个月未更新，将会被关闭，若问题未解决或有后续问题，请随时重新打开（建议先拉取最新代码进行尝试），我们会继续跟进。