Spaces:
Paused
Paused
File size: 1,067 Bytes
6611bfa d889240 06fd5a4 d889240 06fd5a4 d889240 3e31d99 6611bfa d889240 06fd5a4 4bb934d 6611bfa 8c67b0b 6611bfa 06fd5a4 6611bfa 8c67b0b |
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 |
import gradio as gr
from transformers import ViTForImageClassification
import torch
from PIL import Image
import torchvision.transforms as transforms
# Load the model
model = ViTForImageClassification.from_pretrained("google/vit-base-patch16-224")
model.eval()
# Define the image preprocessing pipeline
transform = transforms.Compose([
transforms.Resize((224, 224)),
transforms.ToTensor(),
transforms.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5]),
])
def predict_image(img):
# Apply the transformations
tensor_img = transform(img).unsqueeze(0)
# Make prediction
with torch.no_grad():
outputs = model(tensor_img)
predictions = outputs.logits.argmax(-1)
return model.config.id2label[predictions.item()]
# Create the interface
iface = gr.Interface(
fn=predict_image,
inputs=gr.Image(shape=(224, 224)),
outputs="text",
live=True,
capture_session=True,
title="Image recognition",
description="Upload an image you want to categorize.",
theme="Monochrome"
)
iface.launch() |