Gnort1002/face-analysis-lightning

Face Analysis PyTorch-Lightning with Hydra

Description

Training face analysis model

Installation

Pip

# clone project
git clone https://github.com/dungnq271/face-analysis-lightning.git
cd face-analysis-lightning

# [OPTIONAL] create conda environment
conda create -n face python=3.11
conda activate face

# install pytorch according to instructions
# https://pytorch.org/get-started/

# install requirements
pip install -r requirements.txt

Conda

# clone project
git clone https://github.com/dungnq271/face-analysis-lightning.git
cd face-analysis-lightning

# create conda environment and install dependencies
conda env create -f environment.yaml -n face

# activate conda environment
conda activate face

How to run

Train model with default configuration

# train on CPU
python src/train.py trainer=cpu

# train on GPU
python src/train.py trainer=gpu

Train model with chosen experiment configuration from configs/experiment/

python src/train.py experiment=experiment_1.yaml

You can override any parameter from command line like this

python src/train.py trainer.max_epochs=20 data.batch_size=64

Convert to TorchScript:

Edit the code in notebooks/evaluate/0.2-export-model-torchscript.py