rginpan

@colinzhaoxp 你好 我无法用我自己训练的模型测试 训练的模型是在trained_models/ XXX.dat 对吗 python full_eval.py --gpu-ids 0 --detr --save-model-dir {SAVE_MODEL_DIR} --results-json ./result.json --model VTNetModel --title a3c_previstrans_base 之后报错： AttributeError: 'NoneType' object has no attribute 'seek'. You can only...

> Looks like a problem opening that file for writing when running the tracker - try running the tracking command outside my script, making sure the paths are all correct....

Thanks for your reply, about multi-category score predictor, does it mean select the top-k score in foreground token? "multi-category" is a little bit confused me.