H.Y.Chen

@chenbinghui1 Thank you for providing the source code. May I ask which configurations should I change if I want to use a single GPU for training and testing?

@wondervictor 首先，这是一个很棒的工作，向作者及团队致意！ 其次，我决定使用中文，因为我的英文水平有限，怕不能准确描述我遇到的问题，对其他看到这个问题的英语母语研究者表示抱歉。 以下是我遇到的问题： 当我顺利进行微调之后，在推理图像过程中偶尔会出现未知类别，如图所示：   我在微调时，只设置了一个类别‘crop’：`coco_train_dataset = dict(_delete_=True, type='MultiModalDataset', dataset=dict( type='YOLOv5CocoDataset', metainfo=dict(classes=['crop']), data_root=r'C:\Users\lenovo\Desktop\self_coco_plus', ann_file=r'C:\Users\lenovo\Desktop\self_coco_plus\train.json', data_prefix=dict(img=r'C:\Users\lenovo\Desktop\self_coco_plus\train'), filter_cfg=dict(filter_empty_gt=False, min_size=32)), class_text_path=r'C:\Users\lenovo\Desktop\self_coco_plus\coco_class_text.json', pipeline=train_pipeline)` coco_class_text.json中的内容为：[["crop"]] 推理过程中设置的类别为：’crop‘ 我现在完全不明白为什么会出现这样的情况，希望作者能抽时间解答！

Regarding the Results of Single Image Testing

1

@jinlinyi Firstly, thank you for sharing this wonderful work. I tried to test on a single image using the demo you provided, and I found that the test results did...

Regarding the issue of parameters

2

Thank you for providing the project code. During the testing process, I found that the predicted metric depth result was not ideal. Is this due to different camera parameters? If...