Ensure that you have the following for both GPU and CPU Installations:

• PyCharm Community
• Anaconda

Ensure that you have the following installed if you are doing the GPU Implementation:

• NVIDIA Drivers (Updated to Latest)
• CUDA Toolkit 11.1

Create Conda Environment

conda create --name yolor-gpu

 conda activate yolor-gpu

Install PyTorch, Cython and PyCocoTools

 pip install torch==1.9.0+cu111 torchvision==0.10.0+cu111 torchaudio===0.9.0 -f https://download.pytorch.org/whl/torch_stable.html

 pip install -U cython

 pip install "git+https://github.com/philferriere/cocoapi.git#egg=pycocotools&subdirectory=PythonAPI"

Change Directory to Downloaded Files

pip install -r requirements-gpu.txt 

Create Conda Environment

conda create --name yolor-cpu

conda activate yolor-cpu

Install Dependencies

pip install seaborn thop

pip install -r requirements-cpu.txt

 pip install "git+https://github.com/philferriere/cocoapi.git#egg=pycocotools&subdirectory=PythonAPI"

GPU

python detect.py --source inference/images/horses.jpg --cfg cfg/yolor_p6.cfg --weights yolor_p6.pt --conf 0.25 --img-size 1280 --device 0

CPU

python detect.py --source inference/images/horses.jpg --cfg cfg/yolor_p6.cfg --weights yolor_p6.pt --conf 0.25 --img-size 1280 --device cpu

Ensure that Webcam is connected.

GPU

python detect.py --source 0 --cfg cfg/yolor_p6.cfg --weights yolor_p6.pt --conf 0.25 --img-size 1280 --device 0

CPU

python detect.py --source 0 --cfg cfg/yolor_p6.cfg --weights yolor_p6.pt --conf 0.25 --img-size 1280 --device cpu