Upload README.md

README.md

@@ -0,0 +1,24 @@
+# Pokémon Classifier
+
+# Intro
+
+A fine-tuned version of ViT-base on a collected set of Pokémon images. You can read more about the model [here](https://medium.com/@imjeffhi4/tutorial-using-vision-transformer-vit-to-create-a-pok%C3%A9mon-classifier-cb3f26ff2c20). 
+
+# Using the model
+
+```python
+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( "./PokemonModel").to(device)
+feature_extractor = ViTFeatureExtractor.from_pretrained('google/vit-base-patch16-224')
+
+# Caling the model on a test image
+img = Image.open('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]
+```