Page History

$ export PATH=$PATH:/usr/local/cuda-11.8/bin/

# change shell to bash for installations
$ bash

# install miniforge (or any anaconda manager)
$ wget https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-Linux-x86_64.sh
$ chmod +x Miniforge3-Linux-x86_64.sh
$ ./Miniforge3-Linux-x86_64.sh

#When it asks, conda init? answer yes
#Do you wish the installer to initialize Miniforge3
#by running conda init? [yes|no]
#[no] >>> 
$ yes

$ exit
$ bash

# create conda environment
$ conda create -n ML python=3.8

# activate the environment
$ conda activate ML

# install packages, note that installing tensorflow-gpu and keras also installs: CUDA toolkit, cuDNN (CUDA Deep Neural Network library), Numpy, Scipy, Pillow
$ conda install tensorflow-gpu keras

# (OPTIONAL) cudatoolkit is installed automatically while installing keras and tensorflow-gpu, but if you need a specific (or latest) version run below command.
$ conda install -c anaconda cudatoolkit

# (OPTIONAL) Installing pytorch GPU, pytorch might need cuda 11.8
$ conda install pytorch torchvision torchaudio pytorch-cuda=11.8 -c pytorch -c nvidia

$ nvidia-smi
Mon Feb  5 13:14:45 2024
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 470.223.02   Driver Version: 470.223.02   CUDA Version: 11.4     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|                               |                      |               MIG M. |
|===============================+======================+======================|
|   0  NVIDIA RTXA6000-6C  On   | 00000000:00:05.0 Off |                    0 |
| N/A   N/A    P8    N/A /  N/A |    512MiB /  5976MiB |      0%      Default |
|                               |                      |                  N/A |
+-------------------------------+----------------------+----------------------+

+-----------------------------------------------------------------------------+
| Processes:                                                                  |
|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |
|        ID   ID                                                   Usage      |
|=============================================================================|
|  No running processes found                                                 |
+-----------------------------------------------------------------------------+

$ python3 --version
Python 3.8.18

$ nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2022 NVIDIA Corporation
Built on Wed_Sep_21_10:33:58_PDT_2022
Cuda compilation tools, release 11.8, V11.8.89
Build cuda_11.8.r11.8/compiler.31833905_0

$ whereis cuda
cuda: /usr/local/cuda

$ cat /home/<USERNAME>/miniforge3/envs/ML/include/cudnn.h
.
.
.
/*   cudnn : Neural Networks Library

*/

#if !defined(CUDNN_H_)
#define CUDNN_H_

#include <cuda_runtime.h>
#include <stdint.h>

#include "cudnn_version.h"
#include "cudnn_ops_infer.h"
#include "cudnn_ops_train.h"
#include "cudnn_adv_infer.h"
#include "cudnn_adv_train.h"
#include "cudnn_cnn_infer.h"
#include "cudnn_cnn_train.h"

#include "cudnn_backend.h"

#if defined(__cplusplus)
extern "C" {
#endif

#if defined(__cplusplus)
}
#endif

#endif /* CUDNN_H_ */

$ conda list | grep tensorflow
tensorflow                2.13.1          cuda118py38h409af0c_1    conda-forge
tensorflow-base           2.13.1          cuda118py38h52ca5c6_1    conda-forge
tensorflow-estimator      2.13.1          cuda118py38ha2f8a09_1    conda-forge
tensorflow-gpu            2.13.1          cuda118py38h0240f8b_1    conda-forge

$ conda list | grep keras
keras                     2.13.1             pyhd8ed1ab_0    conda-forge

$ python
import tensorflow as tf
tf.test.is_built_with_cuda()
True
tf.config.list_physical_devices('GPU')
[PhysicalDevice(name='/physical_device:GPU:0', device_type='GPU')]
print(tf.__version__)
2.13.1

# (OPTIONAL) Check pytorch
$ python
import torch

$ python
print(torch.__version__)  # Print PyTorch version
2.2.0

$ python
print(torch.cuda.is_available())  # Check if CUDA is available
True

$ python
print(torch.version.cuda)  # Print the CUDA version PyTorch is using
11.8

$ python
if torch.cuda.is_available():
    # Create a tensor and move it to GPU
    x = torch.tensor([1.0, 2.0]).cuda()
    print(x)  # Print the tensor to verify it's on the GPU
else:
    print("CUDA is not available. Check your PyTorch installation.")

tensor([1., 2.], device='cuda:0')