在mmdet3d==v1.0.0rc2 和torch\==1.11.0+cu113的时候没有这个错误,但并行worker开太大就会出现cuda out of memory的错误。 不同版本的错误情况 cuda11.3 + mmdet3d=0.17.3 + torch=1.10.2 + $waymo waymo-open-dataset-tf-2-6-0:eval和train中的eval都报错。 waymo-open-dataset-tf-2-5-0:降级到2...
I briefly searched for some information about "cuda runtime error 2". It seems that it is a simple "out of memory" error, but I don't know why the error traceback did not elaborate it. I think you can try to reduce the number of "samples_per_gpu" in the config first. I will ...
在得到memory后,便送入decoder部分。首先看下整体逻辑: # encoder输出的memory memory = memory.permute(1, 0, 2) # [b, num_querie,256] bs, _, c = memory.shape # 一阶段部分 else: # 可学习的nn.Embedding:[300,512],即decoder中的可学习位置编码 query_pos, query = torch.split(query_em...
--device cuda:0 --log-level INFO --show --dump-info I have updated the mmdeploy code to latest, and I have checked my TensorRT installtion, and ran sampleMNIST successfully (the running result is fail, but got no error). I didn't know how to fix it. Thanks a lot. ...
注意: 在MMCV-v2.x 中,mmcv-full 改名为 mmcv,如果你想安装不包含 CUDA 算子精简版,可以通过 mim install "mmcv-lite>=2.0.0rc1" 来安装。 步骤1. 安装MMDetection。因为我们想运行demo,所以就用方案A啦 方案a:如果你开发并直接运行 mmdet,从源码安装它: git clone https://github.com/open-mmlab/mmdetec...
📚 The doc issue Hi, I am a beginner of mmdeploy. Recently I have trained my own mmdet model(faster-RCNN) and mmpose model(Res50) for my real-time webcam project. But when I used topdown_demo_with_mmdet.py on my gpu(RTX-3090), the fps was...
torch version: 1.11.0+cu113 cuda: True mmdetection: 3.0.0rc5 mmcv: 2.0.0rc3 mmengine: 0.4.0 Reproduces the problem - code sample start training runner.train() Reproduces the problem - command or script start training runner.train() ...
'torch.cuda._utils', 'torch.cuda.streams', 'torch.cuda.memory', 'torch.cuda.random', 'torch.cuda.sparse', 'torch.cuda.profiler', 'torch.cuda.nvtx', 'torch.cuda.amp.autocast_mode', 'torch.cuda.amp.common', 'torch.cuda.amp.grad_scaler', 'torch.cuda.amp', 'torch.cuda', 'torch....
ENV FORCE_CUDA="1" RUN pip install mmdet3d==0.17.2 but it doesn't work.I don't see why it happens.Thegit clonethe today's master branch is the same version of0.17.2. Do you have an idea? The part of the error message is ...
(a.k.a. OpenMP 4.5) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 11.1 - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=...