This is a resnet34 model fine-tuned with fastai to
classify real and fake Pokemon cards (dataset).
Here is a colab notebook that shows how the model was trained and pushed to the hub:
link.
This model is trained to identify real vs fake cards based on the backs of the cards, not the front.
1from huggingface_hub import from_pretrained_fastai
2
3# Pull model from hub
4learn = from_pretrained_fastai('hugginglearners/pokemon-card-checker')
5
6# Get prediction for this image
7pred_label, _, scores = learn.predict(img)
