GuangxingHan
query_cls = query_cls[0] IndexError: list index out of range
亲爱的作者，当我运行CUDA_VISIBLE_DEVICES=3 python3 fsod_train_net.py --num-gpus 1 --dist-url auto --config-file configs/fsod/meta_training_coco_resnet101_stage_1.yaml您所说的训练脚本时候，会报 query_cls = query_cls[0] IndexError: list index out of range的错误，我看您在query_cls = query_cls[0] 位置也有专门输出查看，请问这个错误我该如何解决呢？
Sorry for the late reply. The error is because self.support_df does not find the bounding box with id defined by dataset_dict['annotations'][0]['id']. But I do not know why it happens. You can debug the program like this.
According to my understanding, self.support_df are built from "datasets/coco/new_annotations/final_split_non_voc_instances_train2014.json". dataset_dict is also sampled from the exact same json file. Therefore, bounding boxes in self.support_df and dataset_dict should be the exact same.
你好，非常冒昧打扰您，我能加您一个联系方式吗，咨询您关于Meta-Faster-RCNN有关的代码问题吗，想在您代码的基础上开展工作，希望能得到你的回复！！
------------------ 原始邮件 ------------------ 发件人: "GuangxingHan/Meta-Faster-R-CNN" @.>; 发送时间: 2023年5月9日(星期二) 下午4:49 @.>; @.@.>; 主题: Re: [GuangxingHan/Meta-Faster-R-CNN] query_cls = query_cls[0] IndexError: list index out of range (Issue #30)
Sorry for the late reply. The error is because self.support_df does not find the bounding box with id defined by dataset_dict['annotations'][0]['id']. But I do not know why it happens. You can debug the program like this.
According to my understanding, self.support_df are built from "datasets/coco/new_annotations/final_split_non_voc_instances_train2014.json". dataset_dict is also sampled from the exact same json file. Therefore, bounding boxes in self.support_df and dataset_dict should be the exact same.
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>
Feel free to contact me by email ([email protected]) or open issues here for any technical issues. I will check them regularly. Thanks.