无法使用自己的预训练模型,损失值变为 NaN

当我尝试使用自己的预训练模型时，它运行出现了错误： trainer.setTrainConfig(object_names_array=["insetos"], batch_size=6, num_experiments=270, train_from_pretrained_model="yolov3_insetos_mAP-0.54737_epoch-30.pt")

Generating anchor boxes for training images... thr=0.25: 1.0000 best possible recall, 8.64 anchors past thr n=9, img_size=416, metric_all=0.640/0.884-mean/best, past_thr=0.658-mean: pretrained weight loading failed. Defaulting to using random weight. ==================== Pretrained YOLOv3 model loaded to initialize weights ====================

但是，我通过将整个路径放入其中来“解决”了“预训练权重加载失败”的错误，但结果和损失仍然为 0.0000 和 Nan