File size: 12,222 Bytes
7734d5b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b1e3471
7734d5b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
from loguru import logger

import cv2

import torch

from yolox.data.data_augment import preproc
from yolox.exp import get_exp
from yolox.utils import fuse_model, get_model_info, postprocess, vis
from yolox.utils.visualize import plot_tracking
from yolox.tracker.byte_tracker import BYTETracker
from yolox.tracking_utils.timer import Timer

import argparse
import os
import time

IMAGE_EXT = [".jpg", ".jpeg", ".webp", ".bmp", ".png"]


def make_parser():
    parser = argparse.ArgumentParser("ByteTrack Demo!")
    parser.add_argument(
        "demo", default="image", help="demo type, eg. image, video and webcam"
    )
    parser.add_argument("-expn", "--experiment-name", type=str, default=None)
    parser.add_argument("-n", "--name", type=str, default=None, help="model name")

    parser.add_argument(
        #"--path", default="./datasets/mot/train/MOT17-05-FRCNN/img1", help="path to images or video"
        "--path", default="./videos/palace.mp4", help="path to images or video"
    )
    parser.add_argument("--camid", type=int, default=0, help="webcam demo camera id")
    parser.add_argument(
        "--save_result",
        action="store_true",
        help="whether to save the inference result of image/video",
    )

    # exp file
    parser.add_argument(
        "-f",
        "--exp_file",
        default=None,
        type=str,
        help="pls input your expriment description file",
    )
    parser.add_argument("-c", "--ckpt", default=None, type=str, help="ckpt for eval")
    parser.add_argument(
        "--device",
        default="gpu",
        type=str,
        help="device to run our model, can either be cpu or gpu",
    )
    parser.add_argument("--conf", default=None, type=float, help="test conf")
    parser.add_argument("--nms", default=None, type=float, help="test nms threshold")
    parser.add_argument("--tsize", default=None, type=int, help="test img size")
    parser.add_argument(
        "--fp16",
        dest="fp16",
        default=False,
        action="store_true",
        help="Adopting mix precision evaluating.",
    )
    parser.add_argument(
        "--fuse",
        dest="fuse",
        default=False,
        action="store_true",
        help="Fuse conv and bn for testing.",
    )
    parser.add_argument(
        "--trt",
        dest="trt",
        default=False,
        action="store_true",
        help="Using TensorRT model for testing.",
    )
    # tracking args
    parser.add_argument("--track_thresh", type=float, default=0.5, help="tracking confidence threshold")
    parser.add_argument("--track_buffer", type=int, default=30, help="the frames for keep lost tracks")
    parser.add_argument("--match_thresh", type=int, default=0.8, help="matching threshold for tracking")
    parser.add_argument('--min-box-area', type=float, default=10, help='filter out tiny boxes')
    parser.add_argument("--mot20", dest="mot20", default=False, action="store_true", help="test mot20.")
    return parser


def get_image_list(path):
    image_names = []
    for maindir, subdir, file_name_list in os.walk(path):
        for filename in file_name_list:
            apath = os.path.join(maindir, filename)
            ext = os.path.splitext(apath)[1]
            if ext in IMAGE_EXT:
                image_names.append(apath)
    return image_names


def write_results(filename, results):
    save_format = '{frame},{id},{x1},{y1},{w},{h},{s},-1,-1,-1\n'
    with open(filename, 'w') as f:
        for frame_id, tlwhs, track_ids, scores in results:
            for tlwh, track_id, score in zip(tlwhs, track_ids, scores):
                if track_id < 0:
                    continue
                x1, y1, w, h = tlwh
                line = save_format.format(frame=frame_id, id=track_id, x1=round(x1, 1), y1=round(y1, 1), w=round(w, 1), h=round(h, 1), s=round(score, 2))
                f.write(line)
    logger.info('save results to {}'.format(filename))


class Predictor(object):
    def __init__(
        self,
        model,
        exp,
        trt_file=None,
        decoder=None,
        device="cpu",
        fp16=False
    ):
        self.model = model
        self.decoder = decoder
        self.num_classes = exp.num_classes
        self.confthre = exp.test_conf
        self.nmsthre = exp.nmsthre
        self.test_size = exp.test_size
        self.device = device
        self.fp16 = fp16
        if trt_file is not None:
            from torch2trt import TRTModule

            model_trt = TRTModule()
            model_trt.load_state_dict(torch.load(trt_file))

            x = torch.ones(1, 3, exp.test_size[0], exp.test_size[1]).cuda()
            self.model(x)
            self.model = model_trt
        self.rgb_means = (0.485, 0.456, 0.406)
        self.std = (0.229, 0.224, 0.225)

    def inference(self, img, timer):
        img_info = {"id": 0}
        if isinstance(img, str):
            img_info["file_name"] = os.path.basename(img)
            img = cv2.imread(img)
        else:
            img_info["file_name"] = None

        height, width = img.shape[:2]
        img_info["height"] = height
        img_info["width"] = width
        img_info["raw_img"] = img

        img, ratio = preproc(img, self.test_size, self.rgb_means, self.std)
        img_info["ratio"] = ratio
        img = torch.from_numpy(img).unsqueeze(0)
        img = img.float()
        if self.device == "gpu":
            img = img.cuda()
            if self.fp16:
                img = img.half()  # to FP16

        with torch.no_grad():
            timer.tic()
            outputs = self.model(img)
            if self.decoder is not None:
                outputs = self.decoder(outputs, dtype=outputs.type())
            outputs = postprocess(
                outputs, self.num_classes, self.confthre, self.nmsthre
            )
            #logger.info("Infer time: {:.4f}s".format(time.time() - t0))
        return outputs, img_info


def image_demo(predictor, vis_folder, path, current_time, save_result):
    if os.path.isdir(path):
        files = get_image_list(path)
    else:
        files = [path]
    files.sort()
    tracker = BYTETracker(args, frame_rate=30)
    timer = Timer()
    frame_id = 0
    results = []
    for image_name in files:
        if frame_id % 20 == 0:
            logger.info('Processing frame {} ({:.2f} fps)'.format(frame_id, 1. / max(1e-5, timer.average_time)))
        outputs, img_info = predictor.inference(image_name, timer)
        online_targets = tracker.update(outputs[0], [img_info['height'], img_info['width']], exp.test_size)
        online_tlwhs = []
        online_ids = []
        online_scores = []
        for t in online_targets:
            tlwh = t.tlwh
            tid = t.track_id
            vertical = tlwh[2] / tlwh[3] > 1.6
            if tlwh[2] * tlwh[3] > args.min_box_area and not vertical:
                online_tlwhs.append(tlwh)
                online_ids.append(tid)
                online_scores.append(t.score)
        timer.toc()
        # save results
        results.append((frame_id + 1, online_tlwhs, online_ids, online_scores))
        online_im = plot_tracking(img_info['raw_img'], online_tlwhs, online_ids, frame_id=frame_id + 1,
                                          fps=1. / timer.average_time)

        #result_image = predictor.visual(outputs[0], img_info, predictor.confthre)
        if save_result:
            save_file_name = "out.jpg"
            cv2.imwrite(save_file_name, online_im)
        ch = cv2.waitKey(0)
        frame_id += 1
        if ch == 27 or ch == ord("q") or ch == ord("Q"):
            break
    #write_results(result_filename, results)


def imageflow_demo(predictor, vis_folder, current_time, args):
    cap = cv2.VideoCapture(args.path if args.demo == "video" else args.camid)
    width = cap.get(cv2.CAP_PROP_FRAME_WIDTH)  # float
    height = cap.get(cv2.CAP_PROP_FRAME_HEIGHT)  # float
    fps = cap.get(cv2.CAP_PROP_FPS)
    save_folder = os.path.join(
        vis_folder, time.strftime("%Y_%m_%d_%H_%M_%S", current_time)
    )
    os.makedirs(save_folder, exist_ok=True)
    if args.demo == "video":
        save_path = os.path.join(save_folder, args.path.split("/")[-1])
    else:
        save_path = os.path.join(save_folder, "camera.mp4")
    logger.info(f"video save_path is {save_path}")
    vid_writer = cv2.VideoWriter(
        save_path, cv2.VideoWriter_fourcc(*"mp4v"), fps, (int(width), int(height))
    )
    tracker = BYTETracker(args, frame_rate=30)
    timer = Timer()
    frame_id = 0
    results = []
    while True:
        if frame_id % 20 == 0:
            logger.info('Processing frame {} ({:.2f} fps)'.format(frame_id, 1. / max(1e-5, timer.average_time)))
        ret_val, frame = cap.read()
        if ret_val:
            outputs, img_info = predictor.inference(frame, timer)
            online_targets = tracker.update(outputs[0], [img_info['height'], img_info['width']], exp.test_size)
            online_tlwhs = []
            online_ids = []
            online_scores = []
            for t in online_targets:
                tlwh = t.tlwh
                tid = t.track_id
                vertical = tlwh[2] / tlwh[3] > 1.6
                if tlwh[2] * tlwh[3] > args.min_box_area and not vertical:
                    online_tlwhs.append(tlwh)
                    online_ids.append(tid)
                    online_scores.append(t.score)
            timer.toc()
            results.append((frame_id + 1, online_tlwhs, online_ids, online_scores))
            online_im = plot_tracking(img_info['raw_img'], online_tlwhs, online_ids, frame_id=frame_id + 1,
                                      fps=1. / timer.average_time)
            if args.save_result:
                vid_writer.write(online_im)
            ch = cv2.waitKey(1)
            if ch == 27 or ch == ord("q") or ch == ord("Q"):
                break
        else:
            break
        frame_id += 1


def main(exp, args):
    if not args.experiment_name:
        args.experiment_name = exp.exp_name

    file_name = os.path.join(exp.output_dir, args.experiment_name)
    os.makedirs(file_name, exist_ok=True)

    if args.save_result:
        vis_folder = os.path.join(file_name, "track_vis")
        os.makedirs(vis_folder, exist_ok=True)

    if args.trt:
        args.device = "gpu"

    logger.info("Args: {}".format(args))

    if args.conf is not None:
        exp.test_conf = args.conf
    if args.nms is not None:
        exp.nmsthre = args.nms
    if args.tsize is not None:
        exp.test_size = (args.tsize, args.tsize)

    model = exp.get_model()
    logger.info("Model Summary: {}".format(get_model_info(model, exp.test_size)))

    if args.device == "gpu":
        model.cuda()
    model.eval()

    if not args.trt:
        if args.ckpt is None:
            ckpt_file = os.path.join(file_name, "best_ckpt.pth.tar")
        else:
            ckpt_file = args.ckpt
        logger.info("loading checkpoint")
        ckpt = torch.load(ckpt_file, map_location="cpu")
        # load the model state dict
        model.load_state_dict(ckpt["model"])
        logger.info("loaded checkpoint done.")

    if args.fuse:
        logger.info("\tFusing model...")
        model = fuse_model(model)
    
    if args.fp16:
            model = model.half()  # to FP16

    if args.trt:
        assert not args.fuse, "TensorRT model is not support model fusing!"
        trt_file = os.path.join(file_name, "model_trt.pth")
        assert os.path.exists(
            trt_file
        ), "TensorRT model is not found!\n Run python3 tools/trt.py first!"
        model.head.decode_in_inference = False
        decoder = model.head.decode_outputs
        logger.info("Using TensorRT to inference")
    else:
        trt_file = None
        decoder = None

    predictor = Predictor(model, exp, trt_file, decoder, args.device, args.fp16)
    current_time = time.localtime()
    if args.demo == "image":
        image_demo(predictor, vis_folder, args.path, current_time, args.save_result)
    elif args.demo == "video" or args.demo == "webcam":
        imageflow_demo(predictor, vis_folder, current_time, args)


if __name__ == "__main__":
    args = make_parser().parse_args()
    exp = get_exp(args.exp_file, args.name)

    main(exp, args)