app.py

from transformers import AutoFeatureExtractor, ResNetForImageClassification
import torch
# from datasets import load_dataset

# dataset = load_dataset("huggingface/cats-image")
# image = dataset["test"]["image"][0]

feature_extractor = AutoFeatureExtractor.from_pretrained("microsoft/resnet-50")
model = ResNetForImageClassification.from_pretrained("microsoft/resnet-50")

import gradio as gr
def segment(image):
    inputs = feature_extractor(image, return_tensors="pt")
    
    with torch.no_grad():
        logits = model(**inputs).logits
    
    # model predicts one of the 1000 ImageNet classes
    predicted_label = logits.argmax(-1).item()
    # print(model.config.id2label[predicted_label])
    
    return model.config.id2label[predicted_label]

gr.Interface(fn=segment, inputs="image", outputs="label").launch()