Detectron2：预测中没有实例

Posted 2023-03-29

【中文标题】Detectron2：预测中没有实例

【英文标题】：Detectron2: No instances in prediction

【发布时间】：2022-01-07 21:37:40

【问题描述】：

我正在尝试在我用coco-annotator 注释的自定义数据集上训练 Detectron2。训练后我想预测我的图像的实例，但我没有得到任何显示。

培训：

from detectron2.engine import DefaultTrainer

cfg = get_cfg()
cfg.merge_from_file(model_zoo.get_config_file("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml"))
cfg.DATASETS.TRAIN = ("TrashTron_train",)
cfg.DATASETS.TEST = ("TrashTron_val",)
# cfg.DATASETS.TEST = ()
cfg.DATALOADER.NUM_WORKERS = 2
cfg.MODEL.WEIGHTS = model_zoo.get_checkpoint_url("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml")  # Let training initialize from model zoo
cfg.SOLVER.IMS_PER_BATCH = 2
cfg.SOLVER.BASE_LR = 0.00025  # pick a good LR
cfg.SOLVER.MAX_ITER = 300    # 300 iterations seems good enough for this toy dataset; you will need to train longer for a practical dataset
cfg.SOLVER.STEPS = []        # do not decay learning rate
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 = 24  # only has one class (ballon). (see https://detectron2.readthedocs.io/tutorials/datasets.html#update-the-config-for-new-datasets)
# NOTE: this config means the number of classes, but a few popular unofficial tutorials incorrect uses num_classes+1 here.

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

预测：

test_data = ['1191.jpg': '/content/datasets/val/1191.jpg',
              'image_id': 1308]

cfg = get_cfg()
cfg.merge_from_file(model_zoo.get_config_file("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml"))
cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.7   # set a custom testing threshold
cfg.MODEL.WEIGHTS = os.path.join(cfg.OUTPUT_DIR, "model_final.pth")  # path to the model we just trained
cfg.MODEL.ROI_HEADS.NUM_CLASSES = 24
predictor = DefaultPredictor(cfg)
outputs = predictor(im)
# print(outputs["instances"].pred_densepose)
im = cv2.imread(test_data[0]["1191.jpg"])

v = Visualizer(im[:, :, ::-1],
               metadata=MetadataCatalog.get(cfg.DATASETS.TRAIN[0]),
               scale=0.5,
               instance_mode=ColorMode.IMAGE_BW)
out = v.draw_instance_predictions(outputs["instances"].to("cpu"))
img = cv2.cvtColor(out.get_image()[:, :, ::-1], cv2.COLOR_RGBA2RGB)
plt.imshow(img)

显示了相应的图像，但没有实例。 有什么建议？总体评价分数不是很好，但是我选了最好的那一班，我也没有得到任何预测...

【问题讨论】：

只是为了确认一下 - 你看过outputs["instances"] 来检查是否有任何预测的实例吗？

你能把输入图片也加进去吗？

【参考方案1】：

我会尽量降低门槛，因为你说过整体训练成绩不是很好。

在answer in official repo 中，建议使用以下代码更改阈值：

cfg.MODEL.TENSOR_MASK.SCORE_THRESH_TEST = 0.5

在另一个answer at the same thread，其他阈值也被修改。

cfg.MODEL.RETINANET.SCORE_THRESH_TEST = args.confidence_threshold 
cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = args.confidence_threshold 
cfg.MODEL.PANOPTIC_FPN.COMBINE.INSTANCES_CONFIDENCE_THRESH = args.confidence_threshold