Upload 4 files

README.md

@@ -1,10 +1,10 @@
 ---
-title: Smart Vehicle Classification
-emoji: 🌍
-colorFrom: indigo
-colorTo: green
+title: License Plate Detection with YOLOS
+emoji: 🚗
+colorFrom: green
+colorTo: gray
 sdk: gradio
-sdk_version: 6.3.0
+sdk_version: 3.1.4
 app_file: app.py
 pinned: false
 ---

app.py

@@ -0,0 +1,203 @@
+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, YolosForObjectDetection, DetrForObjectDetection
+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]
+]
+
+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):
+    if label == 'license-plates':
+
+        # Crop plate
+        plate_crop = img.crop((xmin, ymin, xmax, ymax))
+
+        # Check EV
+        ev = is_green_plate(plate_crop)
+
+        if ev:
+            plate_type = "EV (Green Plate)"
+            box_color = "green"
+        else:
+            plate_type = "Non-EV Plate"
+            box_color = "red"
+
+        ax.add_patch(
+            plt.Rectangle((xmin, ymin), xmax - xmin, ymax - ymin,
+                          fill=False, color=box_color, linewidth=10)
+        )
+
+        ax.text(
+            xmin, ymin - 20,
+            f"{plate_type} | {score:0.2f}",
+            fontsize=50,
+            bbox=dict(facecolor=box_color, alpha=0.7),
+            color="white"
+        )
+    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)
+    
+    if "yolos" in model_name:
+        model = YolosForObjectDetection.from_pretrained(model_name)
+    elif "detr" in model_name:
+        model = DetrForObjectDetection.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">License Plate 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 [Car license plate dataset]("https://www.kaggle.com/datasets/andrewmvd/car-plate-detection") from Kaggle. The dataset consists of 443 images of vehicle with annotations categorised as "Vehicle" and "Rego Plates". The model was trained for 200 epochs on a single GPU.
+Links to HuggingFace Models:
+- [nickmuchi/yolos-small-rego-plates-detection](https://huggingface.co/nickmuchi/yolos-small-rego-plates-detection)
+- [hustlv/yolos-small](https://huggingface.co/hustlv/yolos-small)  
+"""
+
+models = ["nickmuchi/yolos-small-finetuned-license-plate-detection","nickmuchi/detr-resnet50-license-plate-detection"]
+urls = ["https://drive.google.com/uc?id=1j9VZQ4NDS4gsubFf3m2qQoTMWLk552bQ","https://drive.google.com/uc?id=1p9wJIqRz3W50e2f_A0D8ftla8hoXz4T5"]
+images = [[path.as_posix()] for path in sorted(pathlib.Path('images').rglob('*.j*g'))]
+
+twitter_link = """
+[![](https://img.shields.io/twitter/follow/nickmuchi?label=@nickmuchi&style=social)](https://twitter.com/nickmuchi)
+"""
+
+css = '''
+h1#title {
+  text-align: center;
+}
+'''
+demo = gr.Blocks(css=css)
+
+with demo:
+    gr.Markdown(title)
+    gr.Markdown(description)
+    gr.Markdown(twitter_link)
+    options = gr.Dropdown(choices=models,label='Object Detection Model',value=models[0],show_label=True)
+    slider_input = gr.Slider(minimum=0.2,maximum=1,value=0.5,step=0.1,label='Prediction Threshold')
+    
+    with gr.Tabs():
+        with gr.TabItem('Image URL'):
+            with gr.Row():
+                with gr.Column():
+                    url_input = gr.Textbox(lines=2,label='Enter valid image URL here..')
+                    original_image = gr.Image(shape=(750,750))
+                    url_input.change(get_original_image, url_input, original_image)
+                with gr.Column():
+                    img_output_from_url = gr.Image(shape=(750,750))
+                
+            with gr.Row():
+                example_url = gr.Examples(examples=urls,inputs=[url_input])
+                
+            
+            url_but = gr.Button('Detect')
+     
+        with gr.TabItem('Image Upload'):
+            with gr.Row():
+                img_input = gr.Image(type='pil',shape=(750,750))
+                img_output_from_upload= gr.Image(shape=(750,750))
+                
+            with gr.Row(): 
+                example_images = gr.Examples(examples=images,inputs=[img_input])                            
+                                                   
+                
+            img_but = gr.Button('Detect')
+            
+        with gr.TabItem('WebCam'):
+            with gr.Row():
+                web_input = gr.Image(source='webcam',type='pil',shape=(750,750),streaming=True)
+                img_output_from_webcam= gr.Image(shape=(750,750))
+
+            cam_but = gr.Button('Detect')
+            
+    url_but.click(detect_objects,inputs=[options,url_input,img_input,web_input,slider_input],outputs=[img_output_from_url],queue=True)
+    img_but.click(detect_objects,inputs=[options,url_input,img_input,web_input,slider_input],outputs=[img_output_from_upload],queue=True)
+    cam_but.click(detect_objects,inputs=[options,url_input,img_input,web_input,slider_input],outputs=[img_output_from_webcam],queue=True)
+
+    gr.Markdown("![visitor badge](https://visitor-badge.glitch.me/badge?page_id=nickmuchi-license-plate-detection-with-yolos)")
+
+    
+demo.launch(debug=True,enable_queue=True)

gitattributes

@@ -0,0 +1,31 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

requirements.txt

@@ -0,0 +1,7 @@
+beautifulsoup4
+bs4
+requests-file
+torch
+transformers
+validators
+timm