Upload 2 files

app.py

@@ -0,0 +1,46 @@
+import gradio as gr
+from transformers import pipeline
+
+vit_classifier = pipeline("image-classification", model="dein-nutzername/vit-90-animals")
+clip_detector = pipeline(model="openai/clip-vit-large-patch14", task="zero-shot-image-classification")
+
+labels_animals = [
+    'antelope', 'badger', 'bat', 'bear', 'bee', 'beetle', 'bison', 'boar', 'butterfly', 'cat', 'caterpillar',
+    'chimpanzee', 'cockroach', 'cow', 'coyote', 'crab', 'crow', 'deer', 'dog', 'dolphin', 'donkey',
+    'dragonfly', 'duck', 'eagle', 'elephant', 'flamingo', 'fly', 'fox', 'goat', 'goldfish', 'goose',
+    'gorilla', 'grasshopper', 'hamster', 'hare', 'hedgehog', 'hippopotamus', 'hornbill', 'horse',
+    'hummingbird', 'hyena', 'jellyfish', 'kangaroo', 'koala', 'ladybugs', 'leopard', 'lion', 'lizard',
+    'lobster', 'mosquito', 'moth', 'mouse', 'octopus', 'okapi', 'orangutan', 'otter', 'owl', 'ox',
+    'oyster', 'panda', 'parrot', 'pelecaniformes', 'penguin', 'pig', 'pigeon', 'porcupine', 'possum',
+    'raccoon', 'rat', 'reindeer', 'rhinoceros', 'sandpiper', 'seahorse', 'seal', 'shark', 'sheep',
+    'snake', 'sparrow', 'squid', 'squirrel', 'starfish', 'swan', 'tiger', 'turkey', 'turtle', 'whale',
+    'wolf', 'wombat', 'woodpecker', 'zebra'
+]
+
+def classify_animal(image):
+    vit_results = vit_classifier(image)
+    vit_output = {result['label']: round(result['score'], 3) for result in vit_results}
+
+    clip_results = clip_detector(image, candidate_labels=labels_animals)
+    clip_output = {result['label']: round(result['score'], 3) for result in clip_results}
+
+    return {
+        "ViT Fine-Tuned": vit_output,
+        "CLIP Zero-Shot": clip_output
+    }
+example_images = [
+    ["example_images/lion.jpg"],
+    ["example_images/bee.jpg"],
+    ["example_images/dog.jpg"]
+]
+
+iface = gr.Interface(
+    fn=classify_animal,
+    inputs=gr.Image(type="filepath"),
+    outputs=gr.JSON(),
+    title="Animal Classification Comparison",
+    description="Upload an image of an animal and compare predictions between a fine-tuned ViT model and a zero-shot CLIP model.",
+    examples=example_images
+)
+
+iface.launch()

requirements.txt

@@ -0,0 +1,5 @@
+transformers
+torch
+gradio
+kagglehub
+datasets