Ignite616

我使用时，页面显示服务器错误，未能获取到数据，请重试。 请问为什么会这样呢？昨天早上还能用

I installed cooler using pip install --no-deps cooler on win10, but installing simplejson fails

> Hi, dear author, I use 8 32GV100 to train bevformer_base, but the training progress seems too slow, which needs 60days. Have you trained bevformer_base on 8 V100? How long...

I also have the similar question

> 尝试跑了一下test，不管是m0还是m5，速度大概都不到1帧/s tools/test.py configs/fastbev/exp/paper/fastbev_m5_r50_s512x1408_v250x250x6_c256_d6_f4.py work_dirs/fastbev/exp/paper/fastbev_m5_r50_s512x1408_v250x250x6_c256_d6_f4/epoch_20.pth --eval bbox > > [>> ] 331/6019, 0.5 task/s, elapsed: 636s, ETA: 10922s > > CUDA_VISIBLE_DEVICES=3 python -m torch.distributed.launch --nproc_per_node=1 --master_port=29503 tools/test.py configs/fastbev/exp/paper/fastbev_m0_r18_s256x704_v200x200x4_c192_d2_f4.py work_dirs/fastbev/exp/paper/fastbev_m0_r18_s256x704_v200x200x4_c192_d2_f4/epoch_20.pth --eval...

> 你好，请问你完成部署了吗？我现在也在解决这个问题，但不知道如何用tensorrt加速这个模型，因为模型中含有Project2Dto3D这个层，tensorrt识别不了，如何利用作者提供的.cu转成tensorrt可识别的插件？ Hello, did you achieve the speed in the paper before deployment? I use the M1 model in the paper, and the inference speed on the GTX 3090 is...

> 怎么转换到KITTI的数据格式 您好，请问您有转换的代码吗？我使用时,rope3d的3d框和kitti的略有不同。不知道怎么调整

May I ask if you gave up CBGSDatasets and tried, how is the effect?