Run on Ainize

Pokémon Classifier


A fine-tuned version of ViT-base on a collected set of Pokémon images. You can read more about the model here.

Using the model

from transformers import ViTForImageClassification, ViTFeatureExtractor
from PIL import Image
import torch

# Loading in Model
device = "cuda" if torch.cuda.is_available() else "cpu"
model = ViTForImageClassification.from_pretrained( "imjeffhi/pokemon_classifier").to(device)
feature_extractor = ViTFeatureExtractor.from_pretrained('imjeffhi/pokemon_classifier')

# Caling the model on a test image
img ='test.jpg')
extracted = feature_extractor(images=img, return_tensors='pt').to(device)
predicted_id = model(**extracted).logits.argmax(-1).item()
predicted_pokemon = model.config.id2label[predicted_id]
Downloads last month
Hosted inference API
Drag image file here or click to browse from your device
This model can be loaded on the Inference API on-demand.

Spaces using imjeffhi/pokemon_classifier