Hugging Face's logo

Spaces:
PKaushik
/
humandetect
Build error

App Files Community
humandetect
File size: 4,350 Bytes 
75c605c
 
 
 
 
 
 
 
 
 
9e48a2a
75c605c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
import subprocess
import tempfile
import time
from pathlib import Path

import cv2
import gradio as gr

from inferer import Inferer

pipeline = Inferer("PKaushik/humandetect", device='cuda')
print(f"GPU on? {'🟢' if pipeline.device.type != 'cpu' else '🔴'}")

def fn_image(image, conf_thres, iou_thres):
    return pipeline(image, conf_thres, iou_thres)


def fn_video(video_file, conf_thres, iou_thres, start_sec, duration):
    start_timestamp = time.strftime("%H:%M:%S", time.gmtime(start_sec))
    end_timestamp = time.strftime("%H:%M:%S", time.gmtime(start_sec + duration))

    suffix = Path(video_file).suffix

    clip_temp_file = tempfile.NamedTemporaryFile(suffix=suffix)
    subprocess.call(
        f"ffmpeg -y -ss {start_timestamp} -i {video_file} -to {end_timestamp} -c copy {clip_temp_file.name}".split()
    )

    # Reader of clip file
    cap = cv2.VideoCapture(clip_temp_file.name)

    # This is an intermediary temp file where we'll write the video to
    # Unfortunately, gradio doesn't play too nice with videos rn so we have to do some hackiness
    # with ffmpeg at the end of the function here.
    with tempfile.NamedTemporaryFile(suffix=".mp4") as temp_file:
        out = cv2.VideoWriter(temp_file.name, cv2.VideoWriter_fourcc(*"MP4V"), 100, (1280, 720))

        num_frames = 0
        max_frames = duration * 100
        while cap.isOpened():
            try:
                ret, frame = cap.read()
                if not ret:
                    break
            except Exception as e:
                print(e)
                continue

            out.write(pipeline(frame, conf_thres, iou_thres))
            num_frames += 1
            print("Processed {} frames".format(num_frames))
            if num_frames == max_frames:
                break

        out.release()

        # Aforementioned hackiness
        out_file = tempfile.NamedTemporaryFile(suffix="out.mp4", delete=False)
        subprocess.run(f"ffmpeg -y -loglevel quiet -stats -i {temp_file.name} -c:v libx264 {out_file.name}".split())

    return out_file.name


image_interface = gr.Interface(
    fn=fn_image,
    inputs=[
        "image",
        gr.Slider(0, 1, value=0.5, label="Confidence Threshold"),
        gr.Slider(0, 1, value=0.5, label="IOU Threshold"),
    ],
    outputs=gr.Image(type="file"),
    examples=[["example_1.jpg", 0.5, 0.5], ["example_2.jpg", 0.25, 0.45], ["example_3.jpg", 0.25, 0.45]],
    title="Human Detection",
    description=(
        "Gradio demo for Human detection on images. To use it, simply upload your image or click one of the"
        " examples to load them. Read more at the links below."
    ),
    allow_flagging=False,
    allow_screenshot=False,
)

video_interface = gr.Interface(
    fn=fn_video,
    inputs=[
        gr.Video(type="file"),
        gr.Slider(0, 1, value=0.25, label="Confidence Threshold"),
        gr.Slider(0, 1, value=0.45, label="IOU Threshold"),
        gr.Slider(0, 100, value=0, label="Start Second", step=1),
        gr.Slider(0, 100 if pipeline.device.type != 'cpu' else 3, value=4, label="Duration", step=1),
    ],
    outputs=gr.Video(type="file", format="mp4"),
    examples=[
        ["example_1.mp4", 0.25, 0.45, 0, 2],
        ["example_2.mp4", 0.25, 0.45, 5, 3],
        ["example_3.mp4", 0.25, 0.45, 6, 3],
    ],
    title="Human Detection",
    description=(
        "Gradio demo for Human detection on videos. To use it, simply upload your video or click one of the"
        " examples to load them. Read more at the links below."
    ),
    allow_flagging=False,
    allow_screenshot=False,
)

webcam_interface = gr.Interface(
    fn_image,
    inputs=[
        gr.Image(source='webcam', streaming=True),
        gr.Slider(0, 1, value=0.5, label="Confidence Threshold"),
        gr.Slider(0, 1, value=0.5, label="IOU Threshold"),
    ],
    outputs=gr.Image(type="file"),
    live=True,
    title="Human Detection",
    description=(
        "Gradio demo for Human detection on real time webcam. To use it, simply allow the browser to access"
        " your webcam. Read more at the links below."
    ),
    allow_flagging=False,
    allow_screenshot=False,
)

if __name__ == "__main__":
    gr.TabbedInterface(
        [video_interface, image_interface, webcam_interface],
        ["Run on Videos!", "Run on Images!", "Run on Webcam!"],
    ).launch()