Update app.py

app.py

@@ -1,14 +1,118 @@
+import io
 import gradio as gr
-
+import matplotlib.pyplot as plt
+import requests, validators
+import torch
+import pathlib
 from PIL import Image
-import numpy as np
+from transformers import AutoFeatureExtractor, YolosForObjectDetection
 import os
 
-title = """<h1 id="title">App Detection</h1>"""
+os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"
+
+# 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)
+    pil_img = Image.open(buf)
+    basewidth = 750
+    wpercent = (basewidth/float(pil_img.size[0]))
+    hsize = int((float(pil_img.size[1])*float(wpercent)))
+    img = pil_img.resize((basewidth,hsize), Image.Resampling.LANCZOS) 
+    return img
+
+
+def visualize_prediction(img, output_dict, threshold=0.5, 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=(50, 50))
+    plt.imshow(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=5))
+        ax.text(xmin, ymin, f"{label}: {score:0.2f}", fontsize=30, bbox=dict(facecolor="yellow", alpha=0.5))
+    plt.axis("off")
+    return fig2img(plt.gcf())
+    
+def get_original_image(url_input):
+    if validators.url(url_input):
+        image = Image.open(requests.get(url_input, stream=True).raw)
+        
+        return image
+
+def detect_objects(model_name,url_input,image_input,webcam_input,threshold):
+    
+    #Extract model and feature extractor
+    feature_extractor = AutoFeatureExtractor.from_pretrained(model_name)
+    
+    model = YolosForObjectDetection.from_pretrained(model_name)
+    
+    
+    if validators.url(url_input):
+        image = get_original_image(url_input)
+         
+    elif image_input:
+        image = image_input
+        
+    elif webcam_input:
+        image = webcam_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]), gr.Image.update(value=get_original_image(example[0]))
+
+
+title = """<h1 id="title">Face Mask Detection with YOLOS</h1>"""
+
+description = """
+YOLOS is a Vision Transformer (ViT) trained using the DETR loss. Despite its simplicity, a base-sized YOLOS model is able to achieve 42 AP on COCO validation 2017 (similar to DETR and more complex frameworks such as Faster R-CNN).
+The YOLOS model was fine-tuned on COCO 2017 object detection (118k annotated images). It was introduced in the paper [You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection](https://arxiv.org/abs/2106.00666) by Fang et al. and first released in [this repository](https://github.com/hustvl/YOLOS). 
+This model was further fine-tuned on the [face mask dataset]("https://www.kaggle.com/datasets/andrewmvd/face-mask-detection") from Kaggle. The dataset consists of 853 images of people with annotations categorised as "with mask","without mask" and "mask not worn correctly". The model was trained for 200 epochs on a single GPU.
+Links to HuggingFace Models:
+- [nickmuchi/yolos-small-finetuned-masks](https://huggingface.co/nickmuchi/yolos-small-finetuned-masks)
+- [hustlv/yolos-small](https://huggingface.co/hustlv/yolos-small)  
+"""
 
 models = ["nickmuchi/yolos-small-finetuned-masks","nickmuchi/yolos-base-finetuned-masks"]
 urls = ["https://api.time.com/wp-content/uploads/2020/03/hong-kong-mask-admiralty.jpg","https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcQ7wiGZhgAFuIpwFJzbpv8kUMM_Q3WaAWYf5NpSJduxvHQ7V2WnqZ0wMWS6cK5gvlfPGxc&usqp=CAU"]
 
+twitter_link = """
+[![](https://img.shields.io/twitter/follow/nickmuchi?label=@nickmuchi&style=social)](https://twitter.com/nickmuchi)
+"""
+
 css = '''
 h1#title {
   text-align: center;
@@ -17,9 +121,12 @@ h1#title {
 demo = gr.Blocks(css=css)
 
 with demo:
+    with gr.Box():
     
         gr.Markdown(title)
-        options = gr.Dropdown(choices=models,label='Detection',show_label=True)
+        gr.Markdown(description)
+        gr.Markdown(twitter_link)
+        options = gr.Dropdown(choices=models,label='Object Detection Model',show_label=True)
         slider_input = gr.Slider(minimum=0.2,maximum=1,value=0.5,step=0.1,label='Prediction Threshold')
         
         with gr.Tabs():
@@ -62,4 +169,7 @@ with demo:
         example_url.click(fn=set_example_url,inputs=[example_url],outputs=[url_input,original_image])
         
     
-demo.launch(debug=True,enable_queue=True)
+        gr.Markdown("![visitor badge](https://visitor-badge.glitch.me/badge?page_id=nickmuchi-face-mask-detections-with-yolos)")
+
+    
+demo.launch(debug=True,enable_queue=True)