Train YOLOv4 Large

[ducnguyent]

Hello, I'm going to train YOLOv4 large. I wonder does colab pro GPU Tesla V100 be albe to train YOLOv4 P5 or P7 with our dataset. Thank you!

[AlexanderJGomez]

I am also interested in this, I have been unable to install mish-cuda with my Tesla K80

[piyalitt]

@wdrqef for p5 it is work but for p7 colab pro it doesn't have enough RAM even if high-ram setting.

[WongKinYiu]

for colab,

# pip install required packages
pip install -qr requirements.txt

# install mish-cuda if you want to use mish activation
# https://github.com/thomasbrandon/mish-cuda
# https://github.com/JunnYu/mish-cuda
git clone https://github.com/JunnYu/mish-cuda
cd mish-cuda
python setup.py build install
cd ..

requirements.txt

# pip install -qr requirements.txt

# base ----------------------------------------
Cython
matplotlib>=3.2.2
numpy>=1.18.5
opencv-python>=4.1.2
Pillow
PyYAML>=5.3.1
scipy>=1.4.1
tensorboard>=1.5
torch==1.7.0
torchvision==0.8.1
tqdm>=4.41.0

# logging -------------------------------------
# wandb

# plotting ------------------------------------
seaborn>=0.11.0
pandas

# export --------------------------------------
# coremltools>=4.1
# onnx>=1.8.1
# scikit-learn==0.19.2  # for coreml quantization

# extras --------------------------------------
thop  # FLOPS computation
pycocotools==2.0  # COCO mAP