Update app.py

app.py

@@ -1,14 +1,22 @@
-import streamlit as st
 from transformers import pipeline
 
 vision_classifier = pipeline(task="image-classification")
+result = vision_classifier(images="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg")
 
-text = st.text_area('Enter a link to an image:')
+from transformers import AutoFeatureExtractor, AutoModelForImageClassification
+import torch
+from datasets import load_dataset
 
-if text:
-  result = vision_classifier(images=text)
-  st.text("\n".join([f"Class {d['label']} with score {round(d['score'], 4)}" for d in result]))
-  
-#result = vision_classifier(images="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg")
-#print("\n".join([f"Class {d['label']} with score {round(d['score'], 4)}" for d in result]))
-#st.text("\n".join([f"Class {d['label']} with score {round(d['score'], 4)}" for d in result]))
+dataset = load_dataset("huggingface/cats-image")
+image = dataset["test"]["image"][0]
+
+feature_extractor = AutoFeatureExtractor.from_pretrained("google/vit-base-patch16-224")
+model = AutoModelForImageClassification.from_pretrained("google/vit-base-patch16-224")
+
+inputs = feature_extractor(image, return_tensors="pt")
+
+with torch.no_grad():
+    logits = model(**inputs).logits
+
+predicted_label = logits.argmax(-1).item()
+print(model.config.id2label[predicted_label])