NAE4PS
NAE4PS copied to clipboard
Norm-Aware Embedding for Efficient Person Search (CVPR'20)
 

NAE4PS/lib/datasets/prw.py in Line 208 Why multiply the recall rate to AP which already considers the recall rate? To consider the detection performance? If so, is person search metric not exactly...
直接下载本项目,执行后出现如下的错误,请问是什么原因。除了修改数据集路径,未做任何改动 RuntimeError: The expanded size of the tensor (896) must match the existing size (900) at non-singleton dimension 1. Target sizes: [3, 896, 1125]. Tensor sizes: [3, 900, 1125]
Hi, Can you please tell how can I reproduce OIM-base results. Is there a separate model file for it? Can you please share? Regards Bharti
问题
大家能运行吗? apex报错有没有遇到的?