File size: 1,348 Bytes
2b880c6 d77ad2a 2b880c6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 | # -*- coding: utf-8 -*-
"""image classification general.ipynb
Automatically generated by Colab.
Original file is located at
https://colab.research.google.com/drive/1IKVz7857OWmXGom1Z2zq884jI84gkSUx
"""
#!pip install gradio
#!pip install transformers torch
import gradio as gr
from transformers import ViTImageProcessor, AutoModelForImageClassification
from PIL import Image
import torch
# Load pre-trained model and feature extractor
model_name = "google/vit-base-patch16-224"
feature_extractor = ViTImageProcessor.from_pretrained(model_name)
model = AutoModelForImageClassification.from_pretrained(model_name)
# Define the prediction function
def classify_image(img):
inputs = feature_extractor(images=img, return_tensors="pt")
with torch.no_grad():
outputs = model(**inputs)
logits = outputs.logits
predicted_class_idx = logits.argmax(-1).item()
predicted_label = model.config.id2label[predicted_class_idx]
return predicted_label
# Build the Gradio interface
interface = gr.Interface(fn=classify_image,
inputs=gr.Image(type="pil"),
outputs="text",
title="Image Classification with ViT",
description="Upload an image and classify it using Vision Transformer (ViT)")
# Launch the app
interface.launch()
|