Create app.py

app.py

@@ -0,0 +1,106 @@
+import io
+import gradio as gr
+import matplotlib.pyplot as plt
+import requests, validators
+import torch
+from PIL import Image
+from transformers import AutoFeatureExtractor, DetrForObjectDetection, YolosForObjectDetection
+
+import os
+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]
+]
+
+title = 'Object Detection App with DETR and YOLOS'
+
+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)
+
+"""
+
+models = ["facebook/detr-resnet-50","facebook/detr-resnet-101",'hustvl/yolos-small']
+
+options = gr.Dropdown(choices=models,label='Select Object Detection Model',show_label=True)
+
+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,image_upload,threshold):
+    
+    #Extract model and feature extractor
+    feature_extractor = AutoFeatureExtractor.from_pretrained(model_name)
+    
+    if 'detr' in model_name:
+        
+        model = DetrForObjectDetection.from_pretrained(model_name)
+        
+    elif 'yolos' in model_name:
+    
+        model = YolosForObjectDetection.from_pretrained(model_name)
+        
+    if validators.url(url):
+        image = Image.open(requests.get(url, stream=True).raw)
+    elif image_upload:
+        image = image_upload
+    
+    #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   
+    
+gr.Interface(
+    fn = detect_objects,
+    inputs = [options,
+             gr.Textbox(lines=1,label='Enter valid image URL here..'),
+             gr.Image(type='pil'),
+             gr.Slider(minimum=0.2,maximum=1,value=0.7,label='Prediction Threshold')],
+    outputs=gr.Image(shape=(400,400)),
+    title = title,
+    description=description
+    
+).launch()