You can deploy this model and start earning money today!

mir-sajad-01/
facialExpressionModel

Name: facialExpressionModel
Availability: InStock

Views

No views yet

FER2013 training (from your `DATASET/fer2013.csv/fer2013.csv`)

powershell

python -m venv .venv
.\.venv\Scripts\Activate.ps1
python -m pip install -U pip
pip install -r requirements.txt

Choose one:

pip install torch torchvision

NVIDIA GPU (CUDA): follow the official selector and install command for your CUDA version.

python .\train_fer2013.py --epochs 15 --batch-size 128

The script automatically uses GPU if available. It saves the best validation checkpoint to runs/fer2013_cnn.pt.

.\.venv\Scripts\python .\predict_fer2013.py "path\to\your\image.jpg"

Tip: this works best if the image is already a cropped face (the script does a simple center-crop).