STEP 7: Create Environment 

In VS CODE --> View --> Terminal

b) Create Environment

conda create --name OpenPCDetEnv python=3.10

Press 'y' to proceed

c) Activate environment  

If base environment is automaticlly updated then

Disable auto-activation of the base environment: (optional)

conda config --set auto_activate_base false

after that activate openPCDetEnv

 conda activate OpenPCDetEnv

If Enviroment name is not displayed on the bottom right side of status bar despite being activated 

Then click on this 'Select Interpetor' on the status bar

Or
Press "CTRL+SIFT+P' 

Click on the 'Python: Select Interpreter' -->  and the name of the environment 'OpenPCDetEnv'

if still it shows 'Select Interpreter' instead of the environment name then close the 'VS Code' and open it again

It will show the envirnment name 'OpenPCDetEnv' instead of 'Select Interpretor'

STEP 8: Install PyTorch 2.3.1 (inside Environment)

We will isntall PyTorch compatible with CUDA 11.8.

https://pytorch.org/get-started/previous-versions/

b) In the terminal 

# CUDA 11.8

conda install pytorch==2.3.1 torchvision==0.18.1 torchaudio==2.3.1 pytorch-cuda=11.8 -c pytorch -c nvidia

2) Check pytorch version

python3 -c "import torch; print(torch.__version__)"

3) Check Cuda Version

python3 -c "import torch; print(torch.version.cuda)"

or 

python3

import torch

print("PyTorch version:", torch.__version__)

print("CUDA version:", torch.version.cuda)

STEP 9:  Install SpConv: Spatially Sparse Convolution Library (inside Environment)

install The OpenPCDet asked us to install SpConv, so you can visit the repository and find the version and choose that matches with the cuda

pip install spconv-cu118

https://github.com/traveller59/spconv

For CUDA 11.8

pip install spconv-cu118

Step 10: 

Step 6: Install the Required Packages

In the openpcdet environment, we will install the required packages listed in the requirements.txt file:

pip install -r requirements.txt

At the end of installation of 'requrieent.txt' get the following message

This output shows the installation of various Python packages

It also shows  Dependency Conflicts:

• ipykernel requires psutil, which is not installed.

• ultralytics requires:

  • matplotlib>=3.3.0 (not installed).

  • psutil (not installed).

These are warnings indicating that these packages might not work correctly until their dependencies are resolved.

a) pip upldate 

 pip install --upgrade pip

pip --version

24.3.1

b) Install Missing Dependencies:

• To resolve the dependency issues for ipykernel and ultralytics, install the missing packages:

pip install psutil matplotlib

c) Update Pip (Optional):

• Keeping pip up to date ensures you have the latest features and bug fixes:

pip install --upgrade pip

Step 11: 

Step 6: Build the OpenPCDet

pip install -r requirements.txt

 After succefful build, get the following output