Ubuntu安裝和卸載CUDA和CUDNN的實(shí)現(xiàn)

sudo vim /etc/modprobe.d/blacklist.conf

blacklist nouveau
options nouveau modeset=0

sudo update-initramfs -u

lsmod | grep nouveau

NVIDIA-Linux-x86_64-410.93.run

Ctrl-Alt+F1

sudo service lightdm stop

sudo apt-get remove --purge nvidia*
sudo chmod +x NVIDIA-Linux-x86_64-410.93.run
sudo ./NVIDIA-Linux-x86_64-410.93.run --uninstall

sudo ./NVIDIA-Linux-x86_64-410.93.run

sudo service lightdm start

reboot

sudo /usr/local/cuda-8.0/bin/uninstall_cuda_8.0.pl

sudo rm -rf /usr/local/cuda-8.0/

chmod +x cuda_10.0.130_410.48_linux.run

./cuda_10.0.130_410.48_linux.run

（是否同意條款，必須同意才能繼續(xù)安裝）
accept/decline/quit: accept

（這里不要安裝驅(qū)動，因?yàn)橐呀?jīng)安裝最新的驅(qū)動了，否則可能會安裝舊版本的顯卡驅(qū)動，導(dǎo)致重復(fù)登錄的情況）
Install NVIDIA Accelerated Graphics Driver for Linux-x86_64 410.48?
(y)es/(n)o/(q)uit: n

Install the CUDA 10.0 Toolkit?（是否安裝CUDA 10 ，這里必須要安裝）
(y)es/(n)o/(q)uit: y

Enter Toolkit Location（安裝路徑，使用默認(rèn)，直接回車就行）
 [ default is /usr/local/cuda-10.0 ]: 

Do you want to install a symbolic link at /usr/local/cuda?（同意創(chuàng)建軟鏈接）
(y)es/(n)o/(q)uit: y

Install the CUDA 10.0 Samples?（不用安裝測試，本身就有了）
(y)es/(n)o/(q)uit: n

Installing the CUDA Toolkit in /usr/local/cuda-10.0 ...（開始安裝）

export CUDA_HOME=/usr/local/cuda-10.0
export LD_LIBRARY_PATH=${CUDA_HOME}/lib64
export PATH=${CUDA_HOME}/bin:${PATH}

test@test:~$ nvcc -V
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2018 NVIDIA Corporation
Built on Sat_Aug_25_21:08:01_CDT_2018
Cuda compilation tools, release 10.0, V10.0.130

cd /usr/local/cuda-10.0/samples/1_Utilities/deviceQuery
make
./deviceQuery

./deviceQuery Starting...

 CUDA Device Query (Runtime API) version (CUDART static linking)

Detected 1 CUDA Capable device(s)

Device 0: "GeForce RTX 2070"
 CUDA Driver Version / Runtime Version   10.0 / 10.0
 CUDA Capability Major/Minor version number: 7.5
 Total amount of global memory:     7950 MBytes (8335982592 bytes)
 (36) Multiprocessors, ( 64) CUDA Cores/MP:  2304 CUDA Cores
 GPU Max Clock rate:       1620 MHz (1.62 GHz)
 Memory Clock rate:        7001 Mhz
 Memory Bus Width:        256-bit
 L2 Cache Size:         4194304 bytes
 Maximum Texture Dimension Size (x,y,z)   1D=(131072), 2D=(131072, 65536), 3D=(16384, 16384, 16384)
 Maximum Layered 1D Texture Size, (num) layers 1D=(32768), 2048 layers
 Maximum Layered 2D Texture Size, (num) layers 2D=(32768, 32768), 2048 layers
 Total amount of constant memory:    65536 bytes
 Total amount of shared memory per block:  49152 bytes
 Total number of registers available per block: 65536
 Warp size:          32
 Maximum number of threads per multiprocessor: 1024
 Maximum number of threads per block:   1024
 Max dimension size of a thread block (x,y,z): (1024, 1024, 64)
 Max dimension size of a grid size (x,y,z): (2147483647, 65535, 65535)
 Maximum memory pitch:       2147483647 bytes
 Texture alignment:        512 bytes
 Concurrent copy and kernel execution:   Yes with 3 copy engine(s)
 Run time limit on kernels:      Yes
 Integrated GPU sharing Host Memory:   No
 Support host page-locked memory mapping:  Yes
 Alignment requirement for Surfaces:   Yes
 Device has ECC support:      Disabled
 Device supports Unified Addressing (UVA):  Yes
 Device supports Compute Preemption:   Yes
 Supports Cooperative Kernel Launch:   Yes
 Supports MultiDevice Co-op Kernel Launch:  Yes
 Device PCI Domain ID / Bus ID / location ID: 0 / 1 / 0
 Compute Mode:
  < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 10.0, CUDA Runtime Version = 10.0, NumDevs = 1
Result = PASS

cudnn-10.0-linux-x64-v7.4.2.24.tgz 

tar -zxvf cudnn-10.0-linux-x64-v7.4.2.24.tgz 

cuda/include/cudnn.h
cuda/NVIDIA_SLA_cuDNN_Support.txt
cuda/lib64/libcudnn.so
cuda/lib64/libcudnn.so.7
cuda/lib64/libcudnn.so.7.4.2
cuda/lib64/libcudnn_static.a

cp cuda/lib64/* /usr/local/cuda-10.0/lib64/
cp cuda/include/* /usr/local/cuda-10.0/include/

cat /usr/local/cuda/include/cudnn.h | grep CUDNN_MAJOR -A 2

pip3 install https://download.pytorch.org/whl/cu100/torch-1.0.0-cp35-cp35m-linux_x86_64.whl
pip3 install torchvision

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import torch.backends.cudnn as cudnn
from torchvision import datasets, transforms


class Net(nn.Module):
 def __init__(self):
  super(Net, self).__init__()
  self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
  self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
  self.conv2_drop = nn.Dropout2d()
  self.fc1 = nn.Linear(320, 50)
  self.fc2 = nn.Linear(50, 10)

 def forward(self, x):
  x = F.relu(F.max_pool2d(self.conv1(x), 2))
  x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
  x = x.view(-1, 320)
  x = F.relu(self.fc1(x))
  x = F.dropout(x, training=self.training)
  x = self.fc2(x)
  return F.log_softmax(x, dim=1)


def train(model, device, train_loader, optimizer, epoch):
 model.train()
 for batch_idx, (data, target) in enumerate(train_loader):
  data, target = data.to(device), target.to(device)
  optimizer.zero_grad()
  output = model(data)
  loss = F.nll_loss(output, target)
  loss.backward()
  optimizer.step()
  if batch_idx % 10 == 0:
   print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
    epoch, batch_idx * len(data), len(train_loader.dataset),
      100. * batch_idx / len(train_loader), loss.item()))

def main():
 cudnn.benchmark = True
 torch.manual_seed(1)
 device = torch.device("cuda")
 kwargs = {'num_workers': 1, 'pin_memory': True}
 train_loader = torch.utils.data.DataLoader(
  datasets.MNIST('../data', train=True, download=True,
      transform=transforms.Compose([
       transforms.ToTensor(),
       transforms.Normalize((0.1307,), (0.3081,))
      ])),
  batch_size=64, shuffle=True, **kwargs)

 model = Net().to(device)
 optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)

 for epoch in range(1, 11):
  train(model, device, train_loader, optimizer, epoch)


if __name__ == '__main__':
 main()