File size: 1,668 Bytes
22ba041 |
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 44 |
import gradio as gr
from transformers import AutoImageProcessor
from transformers import SiglipForImageClassification
from transformers.image_utils import load_image
from PIL import Image
import torch
# Load model and processor
model_name = "prithivMLmods/Alphabet-Sign-Language-Detection"
model = SiglipForImageClassification.from_pretrained(model_name)
processor = AutoImageProcessor.from_pretrained(model_name)
def sign_language_classification(image):
"""Predicts sign language alphabet category for an image."""
image = Image.fromarray(image).convert("RGB")
inputs = processor(images=image, return_tensors="pt")
with torch.no_grad():
outputs = model(**inputs)
logits = outputs.logits
probs = torch.nn.functional.softmax(logits, dim=1).squeeze().tolist()
labels = {
"0": "A", "1": "B", "2": "C", "3": "D", "4": "E", "5": "F", "6": "G", "7": "H", "8": "I", "9": "J",
"10": "K", "11": "L", "12": "M", "13": "N", "14": "O", "15": "P", "16": "Q", "17": "R", "18": "S", "19": "T",
"20": "U", "21": "V", "22": "W", "23": "X", "24": "Y", "25": "Z"
}
predictions = {labels[str(i)]: round(probs[i], 3) for i in range(len(probs))}
return predictions
# Create Gradio interface
iface = gr.Interface(
fn=sign_language_classification,
inputs=gr.Image(type="numpy"),
outputs=gr.Label(label="Prediction Scores"),
title="Alphabet Sign Language Detection",
description="Upload an image to classify it into one of the 26 sign language alphabet categories."
)
# Launch the app
if __name__ == "__main__":
iface.launch()
|