jiangwenj02
jiangwenj02
[from pystopwatch2.watch import PyStopwatch](https://github.com/ildoonet/pystopwatch2/commit/64ecd49a2a164b665f44c54d7015b0f7d8497b7e)
The results of coarse detector is bbox_mAP: 0.1370, bbox_mAP_50: 0.2440, bbox_mAP_75: 0.1410, bbox_mAP_s: 0.1070, bbox_mAP_m: 0.2130, bbox_mAP_l: 0.2520, bbox_mAP_copypaste: 0.137 0.244 0.141 0.107 0.213 0.252. The results of mp-det is...
Ok, i will try it. thank you very much. PuAnysh ***@***.***> 于2022年4月10日周日 23:14写道： > This code is for the VisDrone dataset. > Because UAVDT is annotated for tracking tasks, there...
> hello Did you reimplement and train this repository by yourself? I cant find mmcv and mmengine suitable version for this project. I got different errors while trying to train...
i am sorry. i change my job and do not backup the environment. 获取Outlook for Android ________________________________ From: mahilaMoghadami ***@***.***> Sent: Sunday, October 22, 2023 9:44:19 PM To: PuAnysh/UFPMP-Det ***@***.***>...
> 1. For the kl_loss function **_"pairwise_kl_loss"_**, why the **"kldiv_loss_per_pair = weighted_t_softmax * ( jnp.log(weighted_t_softmax) - s_softmax_temp) # [n, m]".** > Actually, in my understanding, for the KL divergence, D_KL(A||B)=sum(AlogA-AlogB),...
also waitting
the tilelang version is 0.1.3. The following is the errors. /root/anaconda3/envs/openseed/lib/python3.10/site-packages/tilelang/src/tl_templates/cuda/common.h(122): error: no instance of overloaded function "atomicAdd" matches the argument list argument types are: (__nv_bfloat16 *, __nv_bfloat16) atomicAdd(reinterpret_cast(address), ^...
@LeiWang1999 Sadly, my CUDA version is 12.1. Is it possible that the RTX Titan doesn't support the bfloat16 data type? nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2023 NVIDIA...
@LeiWang1999 To reproduce, I simply ran the examples without modifications. Here are my environment details: sys.platform: linux Python: 3.10.4 (main, Mar 31 2022, 08:41:55) [GCC 7.5.0] CUDA available: True MUSA...