File size: 6,996 Bytes
b6396ac
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
196
# 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 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 fcclip import add_maskformer2_config, add_fcclip_config
from predictor import VisualizationDemo


# constants
WINDOW_NAME = "fc-clip 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_fcclip_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="fcclip demo for builtin configs")
    parser.add_argument(
        "--config-file",
        default="configs/coco/panoptic-segmentation/fcclip/fcclip_convnext_large_eval_ade20k.yaml",
        metavar="FILE",
        help="path to config file",
    )
    parser.add_argument("--webcam", action="store_true", help="Take inputs from webcam.")
    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'",
    )
    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(
        "--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.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"
        for path in tqdm.tqdm(args.input, disable=not args.output):
            # use PIL, to be consistent with evaluation
            img = read_image(path, format="BGR")
            start_time = time.time()
            predictions, visualized_output = demo.run_on_image(img)
            logger.info(
                "{}: {} in {:.2f}s".format(
                    path,
                    "detected {} instances".format(len(predictions["instances"]))
                    if "instances" in predictions
                    else "finished",
                    time.time() - start_time,
                )
            )

            if args.output:
                if os.path.isdir(args.output):
                    assert os.path.isdir(args.output), args.output
                    out_filename = os.path.join(args.output, os.path.basename(path))
                else:
                    assert len(args.input) == 1, "Please specify a directory with args.output"
                    out_filename = args.output
                visualized_output.save(out_filename)
            else:
                cv2.namedWindow(WINDOW_NAME, cv2.WINDOW_NORMAL)
                cv2.imshow(WINDOW_NAME, visualized_output.get_image()[:, :, ::-1])
                if cv2.waitKey(0) == 27:
                    break  # esc to quit
    elif args.webcam:
        assert args.input is None, "Cannot have both --input and --webcam!"
        assert args.output is None, "output not yet supported with --webcam!"
        cam = cv2.VideoCapture(0)
        for vis in tqdm.tqdm(demo.run_on_video(cam)):
            cv2.namedWindow(WINDOW_NAME, cv2.WINDOW_NORMAL)
            cv2.imshow(WINDOW_NAME, vis)
            if cv2.waitKey(1) == 27:
                break  # esc to quit
        cam.release()
        cv2.destroyAllWindows()
    elif args.video_input:
        video = cv2.VideoCapture(args.video_input)
        width = int(video.get(cv2.CAP_PROP_FRAME_WIDTH))
        height = int(video.get(cv2.CAP_PROP_FRAME_HEIGHT))
        frames_per_second = video.get(cv2.CAP_PROP_FPS)
        num_frames = int(video.get(cv2.CAP_PROP_FRAME_COUNT))
        basename = os.path.basename(args.video_input)
        codec, file_ext = (
            ("x264", ".mkv") if test_opencv_video_format("x264", ".mkv") else ("mp4v", ".mp4")
        )
        if codec == ".mp4v":
            warnings.warn("x264 codec not available, switching to mp4v")
        if args.output:
            if os.path.isdir(args.output):
                output_fname = os.path.join(args.output, basename)
                output_fname = os.path.splitext(output_fname)[0] + file_ext
            else:
                output_fname = args.output
            assert not os.path.isfile(output_fname), output_fname
            output_file = cv2.VideoWriter(
                filename=output_fname,
                # some installation of opencv may not support x264 (due to its license),
                # you can try other format (e.g. MPEG)
                fourcc=cv2.VideoWriter_fourcc(*codec),
                fps=float(frames_per_second),
                frameSize=(width, height),
                isColor=True,
            )
        assert os.path.isfile(args.video_input)
        for vis_frame in tqdm.tqdm(demo.run_on_video(video), total=num_frames):
            if args.output:
                output_file.write(vis_frame)
            else:
                cv2.namedWindow(basename, cv2.WINDOW_NORMAL)
                cv2.imshow(basename, vis_frame)
                if cv2.waitKey(1) == 27:
                    break  # esc to quit
        video.release()
        if args.output:
            output_file.release()
        else:
            cv2.destroyAllWindows()