3

我正在尝试使用 Detectron2 和 COCO 数据集训练模型以进行车辆和人员检测，但我遇到了模型加载问题。

我在 SO 和https://github.com/immersive-limit/coco-manager（filter.py 文件）代码上使用了帖子来过滤 COCO 数据集，以仅包含来自“人”、“汽车”类的注释和图像、“自行车”、“卡车”和“自行车”。现在我的目录结构是：

main
  - annotations:
    - instances_train2017_filtered.json
    - instances_val2017_filtered.json
  - images:
    - train2017_filtered (lots of images inside)
    - val2017_filtered (lots of images inside)

基本上，我在这里所做的唯一一件事就是删除与这些类不对应的文档和图像，并更改它们的 ID（因此它们从 1 变为 5）。

然后我使用了 Detectron2 教程中的代码：

import random

import cv2
from detectron2.data import MetadataCatalog, DatasetCatalog
from detectron2.data.datasets import register_coco_instances
from detectron2.engine import DefaultTrainer, DefaultPredictor
from detectron2.config import get_cfg
import os

from detectron2.model_zoo import model_zoo
from detectron2.utils.visualizer import Visualizer

register_coco_instances("train",
                        {},
                        "/home/jakub/Projects/coco/annotations/instances_train2017_filtered.json",
                        "/home/jakub/Projects/coco/images/train2017_filtered/")

register_coco_instances("val",
                        {},
                        "/home/jakub/Projects/coco/annotations/instances_val2017_filtered.json",
                        "/home/jakub/Projects/coco/images/val2017_filtered/")

metadata = MetadataCatalog.get("train")
dataset_dicts = DatasetCatalog.get("train")

cfg = get_cfg()
cfg.merge_from_file(model_zoo.get_config_file("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml"))
cfg.DATASETS.TRAIN = ("train",)
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")
cfg.SOLVER.IMS_PER_BATCH = 2
cfg.SOLVER.BASE_LR = 0.00025
cfg.SOLVER.MAX_ITER = 300
cfg.MODEL.ROI_HEADS.BATCH_SIZE_PER_IMAGE = 512
cfg.MODEL.ROI_HEADS.NUM_CLASSES = 5

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

cfg.MODEL.WEIGHTS = os.path.join(cfg.OUTPUT_DIR, "model_final.pth")
cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.5
cfg.DATASETS.TEST = ("val", )
predictor = DefaultPredictor(cfg)

img = cv2.imread("demo/input.jpg")
outputs = predictor(img)

for d in random.sample(dataset_dicts, 1):
    im = cv2.imread(d["file_name"])
    outputs = predictor(im)
    v = Visualizer(im[:, :, ::-1],
                   metadata=metadata,
                   scale=0.8)
    out = v.draw_instance_predictions(outputs["instances"].to("cpu"))
    cv2.imwrite('demo/output_retrained.jpg', out.get_image()[:, :, ::-1])

在训练期间，我收到以下错误：

Unable to load 'roi_heads.box_predictor.cls_score.weight' to the model due to incompatible shapes: (81, 1024) in the checkpoint but (6, 1024) in the model!
Unable to load 'roi_heads.box_predictor.cls_score.bias' to the model due to incompatible shapes: (81,) in the checkpoint but (6,) in the model!
Unable to load 'roi_heads.box_predictor.bbox_pred.weight' to the model due to incompatible shapes: (320, 1024) in the checkpoint but (20, 1024) in the model!
Unable to load 'roi_heads.box_predictor.bbox_pred.bias' to the model due to incompatible shapes: (320,) in the checkpoint but (20,) in the model!
Unable to load 'roi_heads.mask_head.predictor.weight' to the model due to incompatible shapes: (80, 256, 1, 1) in the checkpoint but (5, 256, 1, 1) in the model!
Unable to load 'roi_heads.mask_head.predictor.bias' to the model due to incompatible shapes: (80,) in the checkpoint but (5,) in the model!

尽管在训练期间减少了总损失，但该模型无法预测训练后的任何有用信息。我知道由于大小不匹配（我减少了课程数量），我应该收到警告，这从我在互联网上看到的情况来看是正常的，但在每个错误行之后我都没有得到“跳过”。我认为该模型实际上没有在这里加载任何东西，我想知道为什么以及如何解决这个问题。

编辑

为了比较，几乎相同情况下的类似行为被报告为问题，但它在每个错误行的末尾都有“跳过”，使它们有效地发出警告，而不是错误： https ://github.com/facebookresearch/detectron2/问题/196

4

1 回答 1

1

这个“警告”基本上是说您正在尝试从在不同数量的类上训练的模型中初始化权重。正如您所阅读的那样，这是预期的。

我怀疑您没有从培训中获得任何结果，因为您的 MetadataCatalog 没有设置“thing_classes”属性。你只是在打电话

MetadataCatalog.get("train")

打电话

MetadataCatalog.get("train").set(thing_classes=["person", "car", "bike", "truck", "bicycle"])

应该解决这个问题，但如果没有，我很确定你的 json 已损坏。

于 2021-04-12T11:08:12.423 回答