app.py

import streamlit as st
from transformers import pipeline
from PIL import Image
from transformers import (
    AutoImageProcessor,
    AutoModelForImageClassification
)
import torch.nn.functional as F
import numpy as np


pre_process = AutoImageProcessor.from_pretrained('adwod/VIT_10000')

st.title("Veo,veo....")

file_name = st.file_uploader("Upload a candidate image")

if file_name is not None:
    col1, col2 = st.columns(2)

    image = Image.open(file_name)
    col1.image(image, use_column_width=True)
    inputs = pre_process(images=image, return_tensors="pt")
    input_pixels = inputs.pixel_values
    model = AutoModelForImageClassification.from_pretrained('adwod/VIT_10000')
    outputs = model(input_pixels)
    probs = F.softmax(outputs.logits, dim=-1).detach().cpu().numpy()[0]
    labels = model.config.id2label.values()
    label_probs = zip(labels, probs)
    for label, prob in label_probs:
        col2.write(f"{label}: {prob:.2f}")
    col2.header(model.config.id2label[outputs.logits.argmax(-1).item()])