fei

use inference mode

@youthM same issue in the third training step, have you resolved it?

我也是遇到这个问题，用 train_ml.py在同一个GPU上训练两个model就会报这个错，分别在market1501和duke数据集上，均会出现此问题（cuhk03暂时没有测试），可能跟线程有关系，有时跑完第一个epoch不会报错，有时第一个epoch没跑完就会报错 ---------------------------------------- duke test set ---------------------------------------- NO. Images: 19889 NO. IDs: 1110 NO. Query Images: 2228 NO. Gallery Images: 17661 NO. Multi-query Images: 0 ---------------------------------------- Exception in thread Thread-5:...

@huanghoujing 暂时没有哈，我这边目前仅能用一个GPU，所以才发现了这个问题。

貌似是python版本原因，换回2.7版本没有出现这个问题，(lll￢ω￢)

@Gavin666Github 可我已经用mutual learning在同一个gpu上训练过好多次了，之后均没出现过问题，显存占用基本在95%左右，没有爆显存的情况

@huanghoujing 调小一点是可以的

@Coler1994 -d ((0,),(0,)) --num_models 2

Problem solved, thanks for helping!! One more question, how long did it took for training the dcgan on market1501? I'm now on epoch 300, but the sample images are still...

> Hi! Random question, could this code be used to render NeRFs in UE? Yes，you can extract rgb density slices, and use the nerf rendering formula by modify little code.