数据预处理出错（Data preprocessing error）

[miracle-74]

Hello, I am running Python extract bboxes. py --proj root=<path/to/project root> --dataset In the code name=ped2 --mode=train, I found that the length of the dataset I got was 0. Why there was no data. （你好，请问我在运行python extract_bboxes.py --proj_root=<path/to/project_root> --dataset_name=ped2 --mode=train这一代码时发现我得到的dataset的长度为0没有数据是什么原因。） The problems are as follows （出现的问题如下所示）

[SHAOjav]

this is due to your path is wrong ! i have meeting

[miracle-74]

this is due to your path is wrong ! i have meeting

你好,感谢你的回复,我在之前解决了问题.我的问题并不是由于路径不对引起的,而是我下载了作者提供的数据集的图片后缀是.jpg但是作者在代码中对数据预处理的代码中的后缀是.tif Hello, thank you for your reply. I solved the problem before My problem is not caused by the wrong path, but that I downloaded the image suffix of the dataset provided by the author Jpg, but the suffix in the code of data preprocessing is tif

[yyyyyyyy0224]

Hello, I am running Python extract bboxes. py --proj root=<path/to/project root> --dataset In the code name=ped2 --mode=train, I found that the length of the dataset I got was 0. Why there was no data. （你好，请问我在运行python extract_bboxes.py --proj_root=<path/to/project_root> --dataset_name=ped2 --mode=train这一代码时发现我得到的dataset的长度为0没有数据是什么原因。） The problems are as follows （出现的问题如下所示）

Hello, I met the same problem with you. Could you tell me how to solve this problem?

[miracle-74]

Hello, I am running Python extract bboxes. py --proj root=<path/to/project root> --dataset In the code name=ped2 --mode=train, I found that the length of the dataset I got was 0. Why there was no data. （你好，请问我在运行python extract_bboxes.py --proj_root=<path/to/project_root> --dataset_name=ped2 --mode=train这一代码时发现我得到的dataset的长度为0没有数据是什么原因。） The problems are as follows （出现的问题如下所示）

Hello, I met the same problem with you. Could you tell me how to solve this problem?

Hello, the reason for this problem is that the suffix of ped2 dataset image in the author code is TIF, but the dataset image provided in the author link is a JPG image, which only needs to be in the author's dataset In the PY file, just change the label corresponding to ped2 to jpg

[yyyyyyyy0224]

Thanks, I will try again!

[BancroftLee]

Hello, the reason for this problem is that the suffix of ped2 dataset image in the author code is TIF, but the dataset image provided in the author link is a JPG image, which only needs to be in the author's dataset In the PY file, just change the label corresponding to ped2 to jpg

Excuse me, I have changed the label, but the length is still 0. I wonder if I have got this wrong or there may be another reason.

[miracle-74]

Hello, I remember that there are two places that need to be modified. You can check whether they have been modified in both places and search tif globally

[BancroftLee]

Thank you for your reply. I have modified these two places before but it didn't work. Have you met this warning while running extract_ bboxes.py? I'm not sure if it's related.

_\mmdetection-master\mmdet\models\builder.py:51: UserWarning: train_cfg and testcfg is deprecated, please specify them in model warnings.warn(

[miracle-74]

Thank you for your reply. I have modified these two places before but it didn't work. Have you met this warning while running extract_ bboxes.py? I'm not sure if it's related. This seems to have no effect. If the length is 0, the dataset is not loaded. You can debug step by step to see what the problem is

[BancroftLee]

Thank you for your reply. I have modified these two places before but it didn't work. Have you met this warning while running extract_ bboxes.py? I'm not sure if it's related. This seems to have no effect. If the length is 0, the dataset is not loaded. You can debug step by step to see what the problem is

Thank you for your help. I'll check it again.

[zjd1836]

Have u solve this problem？

[miracle-74]

I solved the problem before My problem is not caused by the wrong path, but that I downloaded the image suffix of the dataset provided by the author Jpg, but the suffix in the code of data preprocessing is tif

[panyaning]

this is due to your path is wrong ! i have meeting

你好,感谢你的回复,我在之前解决了问题.我的问题并不是由于路径不对引起的,而是我下载了作者提供的数据集的图片后缀是.jpg但是作者在代码中对数据预处理的代码中的后缀是.tif Hello, thank you for your reply. I solved the problem before My problem is not caused by the wrong path, but that I downloaded the image suffix of the dataset provided by the author Jpg, but the suffix in the code of data preprocessing is tif

你好，作者提供的数据集链接打不开了，你能分享一下嘛，谢谢！

[lixiaoxiaozhao]

Running extract_ Flows.py TypeError: forward() takes 3 positional arguments but 5 were given May I ask how to solve this problem