File size: 9,715 Bytes
f8f62f3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# Copyright (c) Facebook, Inc. and its affiliates.
# Copied from: https://github.com/facebookresearch/detectron2/blob/master/demo/predictor.py
import atexit
import bisect
import multiprocessing as mp
from collections import deque

import cv2
import torch

from detectron2.data import MetadataCatalog
from detectron2.engine.defaults import DefaultPredictor
from detectron2.utils.video_visualizer import VideoVisualizer
from detectron2.utils.visualizer import ColorMode, Visualizer

from cat_seg.third_party import imagenet_templates
from types import SimpleNamespace as ns

class VisualizationDemo(object):
    def __init__(self, cfg, instance_mode=ColorMode.IMAGE, parallel=False, text=None):
        """
        Args:
            cfg (CfgNode):
            instance_mode (ColorMode):
            parallel (bool): whether to run the model in different processes from visualization.
                Useful since the visualization logic can be slow.
        """
        self.metadata = MetadataCatalog.get(
            cfg.DATASETS.TEST[0] if len(cfg.DATASETS.TEST) else "__unused"
        )
        self.cpu_device = torch.device("cpu")
        self.instance_mode = instance_mode

        self.parallel = parallel
        if parallel:
            num_gpu = torch.cuda.device_count()
            self.predictor = AsyncPredictor(cfg, num_gpus=num_gpu)
        else:
            self.predictor = DefaultPredictor(cfg)

        # set classes
        templates = ['A photo of a {} in the scene',]
        #templates = imagenet_templates.IMAGENET_TEMPLATES
        if text is not None:
            pred = self.predictor.model.sem_seg_head.predictor
            pred.test_class_texts = [t.strip() for t in text.split(',')]
            pred.text_features_test = pred.class_embeddings(pred.test_class_texts, 
                templates,
                pred.clip_model).permute(1, 0, 2).float()
            if len(templates) == 1:
                pred.text_features_test = pred.text_features_test.repeat(1, 80, 1)
            self.metadata = ns()
            self.metadata.stuff_classes = pred.test_class_texts
        
        self.filter_background = False

    def run_on_image(self, image, text=None, use_sam=False):
        """
        Args:
            image (np.ndarray): an image of shape (H, W, C) (in BGR order).
                This is the format used by OpenCV.
        Returns:
            predictions (dict): the output of the model.
            vis_output (VisImage): the visualized image output.
        """
        vis_output = None

        if text is not None:
            pred = self.predictor.model.sem_seg_head.predictor
            pred.test_class_texts = text.split(',')
            pred.text_features_test = pred.class_embeddings(pred.test_class_texts, 
                #imagenet_templates.IMAGENET_TEMPLATES, 
                 ['A photo of a {} in the scene',],
                pred.clip_model).permute(1, 0, 2).float().repeat(1, 80, 1)
            self.metadata = ns()
            self.metadata.stuff_classes = pred.test_class_texts
            self.metadata.thing_classes = pred.test_class_texts

        self.predictor.model.use_sam = use_sam

        predictions = self.predictor(image)
        # Convert image from OpenCV BGR format to Matplotlib RGB format.
        image = image[:, :, ::-1]
        visualizer = Visualizer(image, self.metadata, instance_mode=self.instance_mode)
        #import pdb; pdb.set_trace()
        if "panoptic_seg" in predictions:
            panoptic_seg, segments_info = predictions["panoptic_seg"]
            vis_output = visualizer.draw_panoptic_seg_predictions(
                panoptic_seg.to(self.cpu_device), segments_info,
                alpha=0.5,
            )
        else:
            if "sem_seg" in predictions:
                vis_output = visualizer.draw_sem_seg(
                    self.filter_bg(predictions["sem_seg"].argmax(dim=0).to(self.cpu_device)),
                    alpha=0.5,
                )
            if "instances" in predictions:
                instances = predictions["instances"].to(self.cpu_device)
                vis_output = visualizer.draw_instance_predictions(predictions=instances)

        return predictions, vis_output

    def _frame_from_video(self, video):
        while video.isOpened():
            success, frame = video.read()
            if success:
                yield frame
            else:
                break

    def run_on_video(self, video):
        """
        Visualizes predictions on frames of the input video.
        Args:
            video (cv2.VideoCapture): a :class:`VideoCapture` object, whose source can be
                either a webcam or a video file.
        Yields:
            ndarray: BGR visualizations of each video frame.
        """
        video_visualizer = VideoVisualizer(self.metadata, self.instance_mode)

        def process_predictions(frame, predictions):
            import pdb; pdb.set_trace()
            frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
            if "panoptic_seg" in predictions:
                panoptic_seg, segments_info = predictions["panoptic_seg"]
                vis_frame = video_visualizer.draw_panoptic_seg_predictions(
                    frame, panoptic_seg.to(self.cpu_device), segments_info
                )
            elif "instances" in predictions:
                predictions = predictions["instances"].to(self.cpu_device)
                vis_frame = video_visualizer.draw_instance_predictions(frame, predictions)
            elif "sem_seg" in predictions:
                vis_frame = video_visualizer.draw_sem_seg(
                    frame, 
                    predictions["sem_seg"].argmax(dim=0).to(self.cpu_device),
                )

            # Converts Matplotlib RGB format to OpenCV BGR format
            vis_frame = cv2.cvtColor(vis_frame.get_image(), cv2.COLOR_RGB2BGR)
            return vis_frame

        frame_gen = self._frame_from_video(video)
        if self.parallel:
            buffer_size = self.predictor.default_buffer_size

            frame_data = deque()

            for cnt, frame in enumerate(frame_gen):
                frame_data.append(frame)
                self.predictor.put(frame)

                if cnt >= buffer_size:
                    frame = frame_data.popleft()
                    predictions = self.predictor.get()
                    yield process_predictions(frame, predictions)

            while len(frame_data):
                frame = frame_data.popleft()
                predictions = self.predictor.get()
                yield process_predictions(frame, predictions)
        else:
            for frame in frame_gen:
                yield process_predictions(frame, self.predictor(frame))

    def filter_bg(self, pred):
        if self.filter_background:
            pred[pred == 0] = 255
        return pred


class AsyncPredictor:
    """
    A predictor that runs the model asynchronously, possibly on >1 GPUs.
    Because rendering the visualization takes considerably amount of time,
    this helps improve throughput a little bit when rendering videos.
    """

    class _StopToken:
        pass

    class _PredictWorker(mp.Process):
        def __init__(self, cfg, task_queue, result_queue):
            self.cfg = cfg
            self.task_queue = task_queue
            self.result_queue = result_queue
            super().__init__()

        def run(self):
            predictor = DefaultPredictor(self.cfg)

            while True:
                task = self.task_queue.get()
                if isinstance(task, AsyncPredictor._StopToken):
                    break
                idx, data = task
                result = predictor(data)
                self.result_queue.put((idx, result))

    def __init__(self, cfg, num_gpus: int = 1):
        """
        Args:
            cfg (CfgNode):
            num_gpus (int): if 0, will run on CPU
        """
        num_workers = max(num_gpus, 1)
        self.task_queue = mp.Queue(maxsize=num_workers * 3)
        self.result_queue = mp.Queue(maxsize=num_workers * 3)
        self.procs = []
        for gpuid in range(max(num_gpus, 1)):
            cfg = cfg.clone()
            cfg.defrost()
            cfg.MODEL.DEVICE = "cuda:{}".format(gpuid) if num_gpus > 0 else "cpu"
            self.procs.append(
                AsyncPredictor._PredictWorker(cfg, self.task_queue, self.result_queue)
            )

        self.put_idx = 0
        self.get_idx = 0
        self.result_rank = []
        self.result_data = []

        for p in self.procs:
            p.start()
        atexit.register(self.shutdown)

    def put(self, image):
        self.put_idx += 1
        self.task_queue.put((self.put_idx, image))

    def get(self):
        self.get_idx += 1  # the index needed for this request
        if len(self.result_rank) and self.result_rank[0] == self.get_idx:
            res = self.result_data[0]
            del self.result_data[0], self.result_rank[0]
            return res

        while True:
            # make sure the results are returned in the correct order
            idx, res = self.result_queue.get()
            if idx == self.get_idx:
                return res
            insert = bisect.bisect(self.result_rank, idx)
            self.result_rank.insert(insert, idx)
            self.result_data.insert(insert, res)

    def __len__(self):
        return self.put_idx - self.get_idx

    def __call__(self, image):
        self.put(image)
        return self.get()

    def shutdown(self):
        for _ in self.procs:
            self.task_queue.put(AsyncPredictor._StopToken())

    @property
    def default_buffer_size(self):
        return len(self.procs) * 5