app.py

import io
import gradio as gr
import matplotlib.pyplot as plt
import requests, validators
import torch
import pathlib
from PIL import Image
from transformers import AutoFeatureExtractor, DetrForObjectDetection, YolosForObjectDetection

import os

# colors for visualization
COLORS = [
    [0.000, 0.447, 0.741],
    [0.850, 0.325, 0.098],
    [0.929, 0.694, 0.125],
    [0.494, 0.184, 0.556],
    [0.466, 0.674, 0.188],
    [0.301, 0.745, 0.933]
]

def make_prediction(img, feature_extractor, model):
    inputs = feature_extractor(img, return_tensors="pt")
    outputs = model(**inputs)
    img_size = torch.tensor([tuple(reversed(img.size))])
    processed_outputs = feature_extractor.post_process(outputs, img_size)
    return processed_outputs[0]

def fig2img(fig):
    buf = io.BytesIO()
    fig.savefig(buf)
    buf.seek(0)
    img = Image.open(buf)
    return img


def visualize_prediction(pil_img, output_dict, threshold=0.7, id2label=None):
    keep = output_dict["scores"] > threshold
    boxes = output_dict["boxes"][keep].tolist()
    scores = output_dict["scores"][keep].tolist()
    labels = output_dict["labels"][keep].tolist()
    if id2label is not None:
        labels = [id2label[x] for x in labels]

    plt.figure(figsize=(16, 10))
    plt.imshow(pil_img)
    ax = plt.gca()
    colors = COLORS * 100
    for score, (xmin, ymin, xmax, ymax), label, color in zip(scores, boxes, labels, colors):
        ax.add_patch(plt.Rectangle((xmin, ymin), xmax - xmin, ymax - ymin, fill=False, color=color, linewidth=3))
        ax.text(xmin, ymin, f"{label}: {score:0.2f}", fontsize=15, bbox=dict(facecolor="yellow", alpha=0.5))
    plt.axis("off")
    return fig2img(plt.gcf())

def detect_objects(model_name,url_input,image_input,threshold):
    
    #Extract model and feature extractor
    feature_extractor = AutoFeatureExtractor.from_pretrained(model_name)
    
    
        
    model = DetrForObjectDetection.from_pretrained(model_name)
        

    

    image = image_input
    
    #Make prediction
    processed_outputs = make_prediction(image, feature_extractor, model)
    
    #Visualize prediction
    viz_img = visualize_prediction(image, processed_outputs, threshold, model.config.id2label)
    
    return viz_img   
        
def set_example_image(example: list) -> dict:
    return gr.Image.update(value=example[0])

def set_example_url(example: list) -> dict:
    return gr.Textbox.update(value=example[0])


title = """<h1 id="title">Object Detection App with DETR and YOLOS</h1>"""

description = """
Links to HuggingFace Models:
- [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50)  
- [facebook/detr-resnet-101](https://huggingface.co/facebook/detr-resnet-101)  
- [hustvl/yolos-small](https://huggingface.co/hustvl/yolos-small)
- [hustvl/yolos-tiny](https://huggingface.co/hustvl/yolos-tiny)
"""

models = ["omarhkh/detr-finetuned-omar8"]


css = '''
h1#title {
  text-align: center;
}
'''

demo = gr.Blocks(css=css)

with demo:
    gr.Markdown(title)
    gr.Markdown(description)
    
    options = gr.Dropdown(choices=models,label='Select Object Detection Model',show_label=True)
    slider_input = gr.Slider(minimum=0.1,maximum=1,value=0.7,label='Prediction Threshold')
    
    with gr.Tabs():
        
     
        with gr.TabItem('Image Upload'):
            with gr.Row():
                img_input = gr.Image(type='pil')
                img_output_from_upload= gr.Image(shape=(650,650))
                
            with gr.Row(): 
                example_images = gr.Dataset(components=[img_input], samples=[[path.as_posix()] for path in sorted(pathlib.Path('images').rglob('*.jpg'))])
                
            img_but = gr.Button('Detect')
        
    
 
    img_but.click(detect_objects,inputs=[options,img_input,img_input,slider_input],outputs=img_output_from_upload,queue=True)
    example_images.click(fn=set_example_image,inputs=[example_images],outputs=[img_input])
    
    


    
demo.launch(enable_queue=True)