Xiaohu Huang

@tonylins Hi, thanks. Do you mean I should train on the whole UCF101 dataset and test on split1?

@tonylins Thanks, but I dont really konw waht you mean. Firstly, I download the three train/test split files from [UCF101 dataset official site](https://www.crcv.ucf.edu/data/UCF101.php) and as I can see, each train/test...

@tonylins And can you share your train/val/test split files with me? Thanks very much.

em.... worong folder path i was so stupid...

@Z-Z-Han if u wanto train on VOC, just use VOC is ok , because in Pelee_VOC.py file,  this shows the dataset path, that all u need to do is...

@Z-Z-Han i am still working on this codebase, if u have any question, u are welcome to ask...

@zhuixunforever i replace backbone with shuffleNetV2 and i train on VOC, i use 1080i gpu and almost train 3days, 400 epoch. by the way my batchsize is 64. the final...

@Z-Z-Han what dataset u train on? and waht map u get?

@Z-Z-Han have ever tried on public dataset , like voc or coco?

@Z-Z-Han all right