The use of dataset

[zhangts1]

I want to use a Caltech Pedestrian dataset for training, but for the transformation of the data set don't correspond with code format and don't know you is how to convert the data set.How to write in CSV, has met the needs of the code format?

[msha096]

I used the Caltech dataset for training. My method is not convenient, I use the matlab toolbox to transfer .vbb and .seq file to jpg and .txt/.csv first. (There are lots of blogs about this). (https://blog.csdn.net/a2008301610258/article/details/45873867) one of the blogs I read and referenced.

Then I write code to transfer to the format I want to feed this model.

[zhangts1]

I used the Caltech dataset for training. My method is not convenient, I use the matlab toolbox to transfer .vbb and .seq file to jpg and .txt/.csv first. (There are lots of blogs about this). (https://blog.csdn.net/a2008301610258/article/details/45873867) one of the blogs I read and referenced.

Then I write code to transfer to the format I want to feed this model.

Thank you very much for your reply. I have used the method mentioned above before.Now I have extracted.jpg and.txt with the code given by the official website of California institute of technology. Could you please share the code of your conversion format? Thank you very much!

[zhangts1]

I used the Caltech dataset for training. My method is not convenient, I use the matlab toolbox to transfer .vbb and .seq file to jpg and .txt/.csv first. (There are lots of blogs about this). (https://blog.csdn.net/a2008301610258/article/details/45873867) one of the blogs I read and referenced.

Then I write code to transfer to the format I want to feed this model.

I have seen the blog you quoted. Does this blog have only the annotations of the whole pedestrian box and no annotations of the visible part?

[msha096]

I used the Caltech dataset for training. My method is not convenient, I use the matlab toolbox to transfer .vbb and .seq file to jpg and .txt/.csv first. (There are lots of blogs about this). (https://blog.csdn.net/a2008301610258/article/details/45873867) one of the blogs I read and referenced. Then I write code to transfer to the format I want to feed this model.

I have seen the blog you quoted. Does this blog have only the annotations of the whole pedestrian box and no annotations of the visible part?

Yes the blog only have full box, you need to change a little bit in the official Matlab tool box to get visible box info. Changing format code is really case by case and every time I will change the code to fit different requirements.

[zhangts1]

I used the Caltech dataset for training. My method is not convenient, I use the matlab toolbox to transfer .vbb and .seq file to jpg and .txt/.csv first. (There are lots of blogs about this). (https://blog.csdn.net/a2008301610258/article/details/45873867) one of the blogs I read and referenced. Then I write code to transfer to the format I want to feed this model.

I have seen the blog you quoted. Does this blog have only the annotations of the whole pedestrian box and no annotations of the visible part?

Yes the blog only have full box, you need to change a little bit in the official Matlab tool box to get visible box info. Changing format code is really case by case and every time I will change the code to fit different requirements.

Thank you very much for your help!