File size: 5,133 Bytes
9dd566f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5b2fe4b
9dd566f
 
 
 
 
5b2fe4b
9dd566f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
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)
    
    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_input):
        image = Image.open(requests.get(url_input, stream=True).raw)
        
    elif 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])

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 = ["facebook/detr-resnet-50","facebook/detr-resnet-101",'hustvl/yolos-small','hustvl/yolos-tiny']
urls = ["https://c8.alamy.com/comp/J2AB4K/the-new-york-stock-exchange-on-the-wall-street-in-new-york-J2AB4K.jpg"]

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 URL'):
            with gr.Row():
                url_input = gr.Textbox(lines=2,label='Enter valid image URL here..')
                img_output_from_url = gr.Image(shape=(650,650))
                
            with gr.Row():
                example_url = gr.Dataset(components=[url_input],samples=[[str(url)] for url in urls])
            
            url_but = gr.Button('Detect')
     
        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')
        
    
    url_but.click(detect_objects,inputs=[options,url_input,img_input,slider_input],outputs=img_output_from_url,queue=True)
    img_but.click(detect_objects,inputs=[options,url_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])
    example_url.click(fn=set_example_url,inputs=[example_url],outputs=[url_input])
    
demo.launch(enable_queue=True)