starsky68

我这边也是同样的问题，请问有优化方案吗

> > If your dataset is a image classification dataset, you could implement your own dataset class to read your data. > > see more details here: > > https://pytorch.org/docs/stable/data.html#torch.utils.data.Dataset...

> 嗨@shreyasrajesh，谢谢你的问题，我们已经解决了！ How did you solve it？thanks

> Hi @starsky68, > > Can you please provide more context ? In particular: > > * What is `self.weight` for ? It looks like it is never used in...

> Hi @starsky68, > > Can you please provide more context ? In particular: > > * What is `self.weight` for ? It looks like it is never used in...

> Did you found a solution @starsky68 ? I get the same error Maybe your DCNv2 version is lower, please use [DCNv2](https://github.com/lbin/DCNv2)

> > I have tried this new DCNv2 which you provided, but still get the same error > > > > Did you found a solution @starsky68 ? I get...

> /home/xinan/.conda/envs/ssh/bin/python3.6 /home/xinan/PycharmProjects/2.Tiny_Faces_in_Tensorflow-master/tiny_face_eval.py /home/xinan/.conda/envs/ssh/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:469: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,))...

> coco预训练权重在哪里阿？没有找到 就在主页了

> 相同的问题，在一张卡上能跑，问题出现在yolox/core/launch.py 的mp.start_processes，偶尔2张卡也能跑 我目前是停了后切换模型训练，效果来看，没啥影响，然后你遇到这个多卡不可以跑的问题，可能是你改动了loss或者bs 线程数啥的都需要仔细调整