File size: 6,084 Bytes
16aee22
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
# Copyright (c) Facebook, Inc. and its affiliates.
# Modified by Bowen Cheng from: https://github.com/facebookresearch/detectron2/blob/master/demo/demo.py
import argparse
import glob
import multiprocessing as mp
import os

# fmt: off
import sys
sys.path.insert(1, os.path.join(sys.path[0], '..'))
# fmt: on

import tempfile
import time
import warnings

import cv2
import numpy as np
import tqdm

from torch.cuda.amp import autocast

from detectron2.config import get_cfg
from detectron2.data.detection_utils import read_image
from detectron2.projects.deeplab import add_deeplab_config
from detectron2.utils.logger import setup_logger

from mask2former import add_maskformer2_config
from mask2former_video import add_maskformer2_video_config
from predictor import VisualizationDemo


# constants
WINDOW_NAME = "mask2former video demo"


def setup_cfg(args):
    # load config from file and command-line arguments
    cfg = get_cfg()
    add_deeplab_config(cfg)
    add_maskformer2_config(cfg)
    add_maskformer2_video_config(cfg)
    cfg.merge_from_file(args.config_file)
    cfg.merge_from_list(args.opts)
    cfg.freeze()
    return cfg


def get_parser():
    parser = argparse.ArgumentParser(description="maskformer2 demo for builtin configs")
    parser.add_argument(
        "--config-file",
        default="configs/youtubevis_2019/video_maskformer2_R50_bs16_8ep.yaml",
        metavar="FILE",
        help="path to config file",
    )
    parser.add_argument("--video-input", help="Path to video file.")
    parser.add_argument(
        "--input",
        nargs="+",
        help="A list of space separated input images; "
        "or a single glob pattern such as 'directory/*.jpg'"
        "this will be treated as frames of a video",
    )
    parser.add_argument(
        "--output",
        help="A file or directory to save output visualizations. "
        "If not given, will show output in an OpenCV window.",
    )

    parser.add_argument(
        "--save-frames",
        default=False,
        help="Save frame level image outputs.",
    )

    parser.add_argument(
        "--confidence-threshold",
        type=float,
        default=0.5,
        help="Minimum score for instance predictions to be shown",
    )
    parser.add_argument(
        "--opts",
        help="Modify config options using the command-line 'KEY VALUE' pairs",
        default=[],
        nargs=argparse.REMAINDER,
    )
    return parser


def test_opencv_video_format(codec, file_ext):
    with tempfile.TemporaryDirectory(prefix="video_format_test") as dir:
        filename = os.path.join(dir, "test_file" + file_ext)
        writer = cv2.VideoWriter(
            filename=filename,
            fourcc=cv2.VideoWriter_fourcc(*codec),
            fps=float(30),
            frameSize=(10, 10),
            isColor=True,
        )
        [writer.write(np.zeros((10, 10, 3), np.uint8)) for _ in range(30)]
        writer.release()
        if os.path.isfile(filename):
            return True
        return False


if __name__ == "__main__":
    mp.set_start_method("spawn", force=True)
    args = get_parser().parse_args()
    setup_logger(name="fvcore")
    logger = setup_logger()
    logger.info("Arguments: " + str(args))

    cfg = setup_cfg(args)

    demo = VisualizationDemo(cfg)

    if args.output:
        os.makedirs(args.output, exist_ok=True)

    if args.input:
        if len(args.input) == 1:
            args.input = glob.glob(os.path.expanduser(args.input[0]))
            assert args.input, "The input path(s) was not found"

        vid_frames = []
        for path in args.input:
            img = read_image(path, format="BGR")
            vid_frames.append(img)

        start_time = time.time()
        with autocast():
            predictions, visualized_output = demo.run_on_video(vid_frames)
        logger.info(
            "detected {} instances per frame in {:.2f}s".format(
                len(predictions["pred_scores"]), time.time() - start_time
            )
        )

        if args.output:
            if args.save_frames:
                for path, _vis_output in zip(args.input, visualized_output):
                    out_filename = os.path.join(args.output, os.path.basename(path))
                    _vis_output.save(out_filename)

            H, W = visualized_output[0].height, visualized_output[0].width

            cap = cv2.VideoCapture(-1)
            fourcc = cv2.VideoWriter_fourcc(*"mp4v")
            out = cv2.VideoWriter(os.path.join(args.output, "visualization.mp4"), fourcc, 10.0, (W, H), True)
            for _vis_output in visualized_output:
                frame = _vis_output.get_image()[:, :, ::-1]
                out.write(frame)
            cap.release()
            out.release()

    elif args.video_input:
        video = cv2.VideoCapture(args.video_input)
        
        vid_frames = []
        while video.isOpened():
            success, frame = video.read()
            if success:
                vid_frames.append(frame)
            else:
                break

        start_time = time.time()
        with autocast():
            predictions, visualized_output = demo.run_on_video(vid_frames)
        logger.info(
            "detected {} instances per frame in {:.2f}s".format(
                len(predictions["pred_scores"]), time.time() - start_time
            )
        )

        if args.output:
            if args.save_frames:
                for idx, _vis_output in enumerate(visualized_output):
                    out_filename = os.path.join(args.output, f"{idx}.jpg")
                    _vis_output.save(out_filename)

            H, W = visualized_output[0].height, visualized_output[0].width

            cap = cv2.VideoCapture(-1)
            fourcc = cv2.VideoWriter_fourcc(*"mp4v")
            out = cv2.VideoWriter(os.path.join(args.output, "visualization.mp4"), fourcc, 10.0, (W, H), True)
            for _vis_output in visualized_output:
                frame = _vis_output.get_image()[:, :, ::-1]
                out.write(frame)
            cap.release()
            out.release()