8/17 - 입력값 분석 및 쿠다 재설치

목표 시간	10000
총 시간
공부 시간
시작 시간	00 : 43
종료 시간	xx : xx

목표 :  cuda installation again

---

 

정리했더니 쿠다 삭제됨...다시 설치함.

 

https://developer.nvidia.com/cuda-toolkit-archive

CUDA Toolkit Archive

 

11.8 버전 설치 후

ubuntu-drivers devices

sudo apt install nvidia-driver-535

wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-ubuntu2204.pin
sudo mv cuda-ubuntu2204.pin /etc/apt/preferences.d/cuda-repository-pin-600
wget https://developer.download.nvidia.com/compute/cuda/11.8.0/local_installers/cuda-repo-ubuntu2204-11-8-local_11.8.0-520.61.05-1_amd64.deb
sudo dpkg -i cuda-repo-ubuntu2204-11-8-local_11.8.0-520.61.05-1_amd64.deb
sudo cp /var/cuda-repo-ubuntu2204-11-8-local/cuda-*-keyring.gpg /usr/share/keyrings/
sudo apt-get update
sudo apt-get -y install cuda-toolkit-11-8

 

설치함.

 

'img_metas':
[{'T_global': array([[-4.81423770e...000e+00]]), 'T_global_inv': array([[-4.81423770e...000e+00]]), 'timestamp': 1533151603.54759}]
'img':
tensor([[[[[ 0.5022,  0.9988,  1.4098,  ..., -1.0904, -1.3130, -1.3644],
           [ 0.3823,  0.8961,  1.3413,  ..., -1.1075, -1.2788, -1.3815],
           [ 0.3652,  0.8447,  1.3242,  ..., -1.0904, -1.2445, -1.3644],
           ...,
           [-0.7479, -0.6794, -0.6965,  ..., -0.4911, -0.4054, -0.3541],
           [-0.7137, -0.6281, -0.6281,  ..., -0.4739, -0.4739, -0.4739],
           [-0.6794, -0.5938, -0.5938,  ..., -0.4568, -0.4739, -0.4739]],

          [[ 0.2577,  0.9755,  1.6408,  ..., -0.9853, -1.2129, -1.2479],
           [ 0.2227,  0.9230,  1.6057,  ..., -0.9853, -1.1604, -1.2654],
           [ 0.1877,  0.8529,  1.5532,  ..., -0.9678, -1.1254, -1.2479],
           ...,
           [-0.5301, -0.4601, -0.4776,  ..., -0.2675, -0.1800, -0.1275],
           [-0.5126, -0.4251, -0.4076,  ..., -0.3025, -0.3025, -0.3025],
           [-0.4776, -0.3901, -0.3901,  ..., -0.3025, -0.3200, -0.3200]],

          [[ 0.7925,  1.4897,  2.0125,  ..., -0.8284, -1.0550, -1.0898],
           [ 0.6182,  1.3502,  1.9951, ...
'timestamp':
tensor([1.5332e+09], device='cuda:0', dtype=torch.float64)
'projection_mat':
tensor([[[[ 5.4692e+02,  3.6989e+02,  1.4416e+01, -1.5591e+02],
          [-6.3702e+00,  9.6405e+01, -5.4680e+02, -2.2414e+02],
          [-1.1703e-02,  9.9847e-01,  5.4022e-02, -4.2520e-01],
          [ 0.0000e+00,  0.0000e+00,  0.0000e+00,  1.0000e+00]],

         [[ 6.0058e+02, -2.7248e+02, -1.7749e+01, -2.0312e+02],
          [ 4.8886e+01,  6.5852e+01, -5.5001e+02, -2.1927e+02],
          [ 8.4341e-01,  5.3631e-01,  3.2160e-02, -6.1037e-01],
          [ 0.0000e+00,  0.0000e+00,  0.0000e+00,  1.0000e+00]],

         [[ 1.4243e+01,  6.6139e+02,  3.4154e+01, -1.3307e+02],
          [-5.6023e+01,  6.1763e+01, -5.5025e+02, -2.2479e+02],
          [-8.2342e-01,  5.6594e-01,  4.1220e-02, -5.2968e-01],
          [ 0.0000e+00,  0.0000e+00,  0.0000e+00,  1.0000e+00]],

         [[-3.5375e+02, -3.7432e+02, -1.1633e+01, -3.8315e+02],
          [-3.5956e+00, -5.6038e+01, -3.5308e+02, -1.6952e+02],
          [-8.3335e-03, -9.9920e-01, -3.9103e-02, -1.0165e+00],
          [ 0.0000e+00,  0.0000e+00,  0.0000e+00,  1.0000e...
'image_wh':
tensor([[[704., 256.],
         [704., 256.],
         [704., 256.],
         [704., 256.],
         [704., 256.],
         [704., 256.]]], device='cuda:0')
len():
5

 

 

 

data['img'].shape
torch.Size([1, 6, 3, 256, 704])

data['timestamp'].shape
torch.Size([1])

data['timestamp']
tensor([1.5332e+09], device='cuda:0', dtype=torch.float64)

data['image_wh']
tensor([[[704., 256.],
         [704., 256.],
         [704., 256.],
         [704., 256.],
         [704., 256.],
         [704., 256.]]], device='cuda:0')
data['image_wh'].shape
torch.Size([1, 6, 2])

data['image_wh'][0].shape
torch.Size([6, 2])