Rex Cheng comments

Results 104 comments of


                                            Rex Cheng

trafficstars

static dataset in download_dataset.py

1. For pretraining. See our paper or the STM paper. 2. A subset of it. You can download our pre-generated fusion_data to check but I don't think it matters too...

CPU profile 2 process throwing CUDA out of memory for one image with multiple items when propagate button is clicked

I did not write the boundary condition for a single image, so it might be doing some extra work. It is also not the intended usage of the GUI. If...

CPU profile 2 process throwing CUDA out of memory for one image with multiple items when propagate button is clicked

It still uses the GPU even with mem_profile=2. We just buffer less on the GPU. I cannot think of a general use case where it will be useful to do...

CPU profile 2 process throwing CUDA out of memory for one image with multiple items when propagate button is clicked

If you don't need to propagate then just don't click that button

CPU profile 2 process throwing CUDA out of memory for one image with multiple items when propagate button is clicked

I see. That's a memory error (it is expected to use the GPU) and if we were to solve it we would need to guard against all CUDA OOM errors....

有新版本的后续吗？

Hi @zhanglonghao1992 , I have made a fork that is compatible with the new Caffe, hope it helps: https://github.com/silver-rush/Weighted_Softmax_Loss

有新版本的后续吗？

@sophiazy 你好，適用的。可以把pos_cid設成額外多的類別id，然後把pos_multi設成小於1、大於0的數，具體數字視乎不均衡的比例。

有新版本的后续吗？

@zzh928253398 這個做不到，現在只支持一個

新版caffe如何处理

Hi @Li1991 , I have made a fork that is compatible with the new Caffe, hope it helps: https://github.com/silver-rush/Weighted_Softmax_Loss

About loss being NaN, lr_scheduler.step(), optimizer.step()

The warning can be ignored. It doesn't matter. I think the problem is in the backbone (I see that you are using ConvNext). I've also tried ConvNext, but 1) It...