Resnet34 Pokemon Card Classifier
Model Description
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.
Intended uses & limitation
This model is trained to identify real vs fake cards based on the backs of the cards, not the front.
How to use
from huggingface_hub import from_pretrained_fastai
# Pull model from hub
learn = from_pretrained_fastai('hugginglearners/pokemon-card-checker')
# Get prediction for this image
pred_label, _, scores = learn.predict(img)
Training data
Dataset located here: link.
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.