Python 如何使用Detectron2的tensorboard获得测试精度？

我正在学习使用Detecron2。我按照链接创建了一个自定义对象检测器。 我的培训代码-

# training Detectron2
from detectron2.engine import DefaultTrainer
from detectron2.config import get_cfg
import os

cfg = get_cfg()
cfg.merge_from_file("./detectron2_repo/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml")
cfg.DATASETS.TRAIN = ("pedestrian",)
cfg.DATASETS.TEST = ()   # no metrics implemented for this dataset
cfg.DATALOADER.NUM_WORKERS = 2
cfg.MODEL.WEIGHTS = "detectron2://COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl"  # initialize from model zoo
cfg.SOLVER.IMS_PER_BATCH = 2
cfg.SOLVER.BASE_LR = 0.02
cfg.SOLVER.MAX_ITER = 300    # 300 iterations seems good enough, but you can certainly train longer
cfg.MODEL.ROI_HEADS.BATCH_SIZE_PER_IMAGE = 128   # faster, and good enough for this dataset
cfg.MODEL.ROI_HEADS.NUM_CLASSES = 1  

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

它在output dir中保存了一个日志文件，因此我可以使用tensorboard来显示训练的准确性-

%load_ext tensorboard
%tensorboard --logdir output

它运行良好，我可以看到我的模型的训练精度。但是在测试/验证模型时-

cfg.MODEL.WEIGHTS = os.path.join(cfg.OUTPUT_DIR, "model_final.pth")
cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.7   # set the testing threshold for this model
cfg.DATASETS.TEST = ("pedestrian_day", )
predictor = DefaultPredictor(cfg)

虽然从Detectron2教程中我得到了-

from detectron2.evaluation import COCOEvaluator, inference_on_dataset
from detectron2.data import build_detection_test_loader
evaluator = COCOEvaluator("pedestrian_day", cfg, False, output_dir="./output/")
val_loader = build_detection_test_loader(cfg, "pedestrian_day", mapper=None)
inference_on_dataset(trainer.model, val_loader, evaluator)

但这将为AP、AP50、AP75、APm、APl和APs提供培训和测试。 我的问题是，我如何才能像训练板那样在张力板中看到测试的准确性？

默认情况下

如果你想启用它，你必须设置以下参数

#设置评估步长间隔
cfg.TEST.EVAL_期间=

但要使评估工作正常，您必须修改detectron2/engine/defaults.py中的函数

repo的tools/train_net.py脚本中提供了一个函数示例

讨论如何创建自定义LossEvalHook来监视评估损失，这听起来是一个很好的尝试方法