Duplicate from Stuti/detect-for-drone

Co-authored-by: Stuti <[email protected]>

.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
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: Detect For Drone
+emoji: 🐢
+colorFrom: red
+colorTo: blue
+sdk: gradio
+sdk_version: 3.3
+app_file: app.py
+pinned: false
+duplicated_from: Stuti/detect-for-drone
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,122 @@
+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
+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,image_input,threshold):
+    
+    #Extract model and feature extractor
+    feature_extractor = AutoFeatureExtractor.from_pretrained(model_name)
+    
+    if 'detr' in model_name:    
+        model = DetrForObjectDetection.from_pretrained(model_name)     
+        
+    if image_input:
+        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])
+
+
+
+title = """<h1 id="title">Detection for Drone</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)  
+"""
+
+models = ["facebook/detr-resnet-50","facebook/detr-resnet-101"]
+#examples = ['1daaadc1e83fcecc7bfa920ed2773653.jpeg']
+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=0.2,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('*.jpeg'))])
+                
+            img_but = gr.Button('Detect')
+        
+    
+    img_but.click(detect_objects,inputs=[options,img_input,slider_input],outputs=img_output_from_upload,queue=True)
+    example_images.click(fn=set_example_image,inputs=[example_images],outputs=[img_input])
+    
+
+    #gr.Markdown("![visitor badge](https://visitor-badge.glitch.me/badge?page_id=nickmuchi-object-detection-with-detr-and-yolos)")
+
+    
+demo.launch(enable_queue=True)

requirements.txt

@@ -0,0 +1,7 @@
+beautifulsoup4==4.9.3
+bs4==0.0.1
+requests-file==1.5.1
+torch==1.10.1
+git+https://github.com/huggingface/transformers.git
+validators==0.18.2
+timm==0.5.4