File size: 6,181 Bytes
f11983f
 
 
 
 
fd57de8
 
 
 
 
 
 
 
 
f11983f
 
fd57de8
 
 
 
 
 
f11983f
 
 
 
fd57de8
 
 
 
f11983f
 
fd57de8
 
 
 
 
 
 
 
 
 
f11983f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fd57de8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f11983f
 
 
 
 
 
 
 
fd57de8
 
 
7a6049c
 
 
fd57de8
f11983f
 
 
967a6ae
f11983f
967a6ae
f11983f
 
 
 
 
fd57de8
967a6ae
 
 
f11983f
 
 
 
fd57de8
f11983f
fd57de8
 
f11983f
fd57de8
f11983f
 
 
 
 
 
fd57de8
 
967a6ae
 
 
 
 
739106a
967a6ae
f11983f
 
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
149
150
151
152
153
154
import os
import sys
from pathlib import Path
import uuid
import gradio as gr
from PIL import Image
import cv2
import torch
import numpy as np
import copy
import retinaface

device = 'cuda' if torch.cuda.is_available() else 'cpu'

try:
    from spiga.demo.app import video_app
    from spiga.inference.config import ModelConfig
    from spiga.inference.framework import SPIGAFramework
    from spiga.demo.visualize.plotter import Plotter
    import spiga.demo.analyze.track.retinasort.config as cfg


except:
    os.system("pip install -e ./SPIGA[demo]")
    sys.path.append(os.path.abspath("./SPIGA"))
    from spiga.demo.app import video_app
    from spiga.inference.config import ModelConfig
    from spiga.inference.framework import SPIGAFramework
    from spiga.demo.visualize.plotter import Plotter
    import spiga.demo.analyze.track.retinasort.config as cfg


face_processor = SPIGAFramework(ModelConfig('wflw'))
config = cfg.cfg_retinasort
face_detector = retinaface.RetinaFaceDetector(model=config['retina']['model_name'],
                                              device=device,
                                              extra_features=config['retina']['extra_features'],
                                              cfg_postreat=config['retina']['postreat'])


def predict_video(video_in):
    if video_in == None:
        raise gr.Error("Please upload a video or image.")

    video_in = Path(video_in)
    output_path = Path("/tmp")
    video_file_name = str(uuid.uuid4())
    new_video_path = output_path / f"{video_file_name}{video_in.suffix}"
    video_in.rename(new_video_path)

    video_app(str(new_video_path),
              # Choices=['wflw', '300wpublic', '300wprivate', 'merlrav']
              spiga_dataset='wflw',
              # Choices=['RetinaSort', 'RetinaSort_Res50']
              tracker='RetinaSort',
              save=True,
              output_path=output_path,
              visualize=False,
              plot=['fps', 'face_id', 'landmarks', 'headpose'])
    video_output_path = f"{output_path}/{new_video_path.name[:-4]}.mp4"

    return video_output_path


def predict_image(image_in_video, image_in_img):
    if image_in_video == None and image_in_img == None:
        raise gr.Error("Please upload a video or image.")

    if image_in_video or image_in_img:
        print("image", image_in_video, image_in_img)
        image = image_in_img if image_in_img else image_in_video
        image = Image.open(image).convert("RGB")
        cv2_image = cv2.cvtColor(np.array(image), cv2.COLOR_RGB2BGR)
        face_detector.set_input_shape(image.size[1], image.size[0])
        features = face_detector.inference(image)
        if features:
            bboxes = features['bbox']
            bboxes_n = []
            for bbox in bboxes:
                x1, y1, x2, y2 = bbox[:4]
                bbox_wh = [x1, y1, x2-x1, y2-y1]
                bboxes_n.append(bbox_wh)
            face_features = face_processor.inference(cv2_image, bboxes_n)
            canvas = copy.deepcopy(cv2_image)
            plotter = Plotter()
            for landmarks, headpose, bbox in zip(face_features['landmarks'], face_features['headpose'], bboxes_n):
                x0, y0, w, h = bbox
                landmarks = np.array(landmarks)
                headpose = np.array(headpose)
                canvas = plotter.landmarks.draw_landmarks(canvas, landmarks)
                canvas = plotter.hpose.draw_headpose(
                    canvas, [x0, y0, x0+w, y0+h], headpose[:3], headpose[3:], euler=True)

            return Image.fromarray(cv2.cvtColor(canvas, cv2.COLOR_BGR2RGB))


def toggle(choice):
    if choice == "webcam":
        return gr.update(visible=True, value=None), gr.update(visible=False, value=None)
    else:
        return gr.update(visible=False, value=None), gr.update(visible=True, value=None)


with gr.Blocks() as blocks:
    gr.Markdown("""
    # Unofficia Demo: SPIGA
    ## Shape Preserving Facial Landmarks with Graph Attention Networks.

    * https://github.com/andresprados/SPIGA
    * https://arxiv.org/abs/2210.07233
""")
    with gr.Tab("Video") as tab:
        with gr.Row():
            with gr.Column():
                video_or_file_opt = gr.Radio(["upload", "webcam"], value="upload",
                                             label="How would you like to upload your video?")
                video_in = gr.Video(source="upload", include_audio=False)
                video_or_file_opt.change(fn=lambda s: gr.update(source=s, value=None), inputs=video_or_file_opt,
                                         outputs=video_in, queue=False)
            with gr.Column():
                video_out = gr.Video()
        run_btn = gr.Button("Run")
        run_btn.click(fn=predict_video, inputs=[video_in], outputs=[video_out])
        gr.Examples(fn=predict_video, examples=[["./examples/temp.mp4"]],
                    inputs=[video_in], outputs=[video_out],
                    cache_examples=True)

    with gr.Tab("Image"):
        with gr.Row():
            with gr.Column():
                image_or_file_opt = gr.Radio(["file", "webcam"], value="file",
                                             label="How would you like to upload your image?")
                image_in_video = gr.Image(
                    source="webcam", type="filepath", visible=False)
                image_in_img = gr.Image(
                    source="upload", visible=True, type="filepath")

                image_or_file_opt.change(fn=toggle, inputs=[image_or_file_opt],
                                         outputs=[image_in_video, image_in_img], queue=False)
            with gr.Column():
                image_out = gr.Image()
        run_btn = gr.Button("Run")
        run_btn.click(fn=predict_image,
                      inputs=[image_in_img, image_in_video], outputs=[image_out])
        gr.Examples(fn=predict_image, examples=[
            ["./examples/52_Photographers_photographertakingphoto_52_315.jpg", None],
            ["./examples/6_Funeral_Funeral_6_759.jpg", None]
        ],
            inputs=[image_in_img, image_in_video], outputs=[image_out],
            cache_examples=True
        )

blocks.launch()