chuanfushen

Results 9 comments of chuanfushen

How many GPU card do you use to inference model? We evaluate with eight GPU (RTX 6000). I forgot exact sequence number for OUMVLP, but 133478 seems no problem for...

We highly recommend that users use Linux rather than Windows, since we haven't evaluated our framework on the Windows platform.

As you mentioned, you are interested in the shape of the final vectors, you could check the original implement form https://github.com/bb12346/GaitGL/blob/a169610383d58cfc3fa3f5cc7e293860e705e2c1/model/network/vgg_c3d.py#L196 OpenGait wraps the embedding into a python dictionary format,...

Hi, you should use pretreatment.py to pre-process data. With parameter setting of pretreatment.py, you process dataset to pickle data format, and specific resolution(64/or 128). https://github.com/ShiqiYu/OpenGait/blob/master/docs/2.prepare_dataset.md Then, you should modify transform...

https://github.com/ShiqiYu/OpenGait/blob/c5e7f6501edeebc3edd0369c511058d1f605d373/configs/default.yaml#L20-L22 https://github.com/ShiqiYu/OpenGait/blob/c5e7f6501edeebc3edd0369c511058d1f605d373/datasets/pretreatment.py#L137