File size: 7,782 Bytes
3f9c56c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import numpy as np
import cv2
import torch

import os
from modules import devices
from annotator.annotator_path import models_path

import mmcv
from mmdet.apis import inference_detector, init_detector
from mmpose.apis import inference_top_down_pose_model
from mmpose.apis import init_pose_model, process_mmdet_results, vis_pose_result


def preprocessing(image, device):
    # Resize
    scale = 640 / max(image.shape[:2])
    image = cv2.resize(image, dsize=None, fx=scale, fy=scale)
    raw_image = image.astype(np.uint8)

    # Subtract mean values
    image = image.astype(np.float32)
    image -= np.array(
        [
            float(104.008),
            float(116.669),
            float(122.675),
        ]
    )

    # Convert to torch.Tensor and add "batch" axis
    image = torch.from_numpy(image.transpose(2, 0, 1)).float().unsqueeze(0)
    image = image.to(device)

    return image, raw_image


def imshow_keypoints(img,
                     pose_result,
                     skeleton=None,
                     kpt_score_thr=0.1,
                     pose_kpt_color=None,
                     pose_link_color=None,
                     radius=4,
                     thickness=1):
    """Draw keypoints and links on an image.
    Args:
            img (ndarry): The image to draw poses on.
            pose_result (list[kpts]): The poses to draw. Each element kpts is
                a set of K keypoints as an Kx3 numpy.ndarray, where each
                keypoint is represented as x, y, score.
            kpt_score_thr (float, optional): Minimum score of keypoints
                to be shown. Default: 0.3.
            pose_kpt_color (np.array[Nx3]`): Color of N keypoints. If None,
                the keypoint will not be drawn.
            pose_link_color (np.array[Mx3]): Color of M links. If None, the
                links will not be drawn.
            thickness (int): Thickness of lines.
    """

    img_h, img_w, _ = img.shape
    img = np.zeros(img.shape)

    for idx, kpts in enumerate(pose_result):
        if idx > 1:
            continue
        kpts = kpts['keypoints']
        # print(kpts)
        kpts = np.array(kpts, copy=False)

        # draw each point on image
        if pose_kpt_color is not None:
            assert len(pose_kpt_color) == len(kpts)

            for kid, kpt in enumerate(kpts):
                x_coord, y_coord, kpt_score = int(kpt[0]), int(kpt[1]), kpt[2]

                if kpt_score < kpt_score_thr or pose_kpt_color[kid] is None:
                    # skip the point that should not be drawn
                    continue

                color = tuple(int(c) for c in pose_kpt_color[kid])
                cv2.circle(img, (int(x_coord), int(y_coord)),
                           radius, color, -1)

        # draw links
        if skeleton is not None and pose_link_color is not None:
            assert len(pose_link_color) == len(skeleton)

            for sk_id, sk in enumerate(skeleton):
                pos1 = (int(kpts[sk[0], 0]), int(kpts[sk[0], 1]))
                pos2 = (int(kpts[sk[1], 0]), int(kpts[sk[1], 1]))

                if (pos1[0] <= 0 or pos1[0] >= img_w or pos1[1] <= 0 or pos1[1] >= img_h or pos2[0] <= 0
                        or pos2[0] >= img_w or pos2[1] <= 0 or pos2[1] >= img_h or kpts[sk[0], 2] < kpt_score_thr
                        or kpts[sk[1], 2] < kpt_score_thr or pose_link_color[sk_id] is None):
                    # skip the link that should not be drawn
                    continue
                color = tuple(int(c) for c in pose_link_color[sk_id])
                cv2.line(img, pos1, pos2, color, thickness=thickness)

    return img


human_det, pose_model = None, None
det_model_path = "https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth"
pose_model_path = "https://download.openmmlab.com/mmpose/top_down/hrnet/hrnet_w48_coco_256x192-b9e0b3ab_20200708.pth"

modeldir = os.path.join(models_path, "keypose")
old_modeldir = os.path.dirname(os.path.realpath(__file__))

det_config = 'faster_rcnn_r50_fpn_coco.py'
pose_config = 'hrnet_w48_coco_256x192.py'

det_checkpoint = 'faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth'
pose_checkpoint = 'hrnet_w48_coco_256x192-b9e0b3ab_20200708.pth'
det_cat_id = 1
bbox_thr = 0.2

skeleton = [
    [15, 13], [13, 11], [16, 14], [14, 12], [11, 12], [5, 11], [6, 12], [5, 6], [5, 7], [6, 8],
    [7, 9], [8, 10],
    [1, 2], [0, 1], [0, 2], [1, 3], [2, 4], [3, 5], [4, 6]
]

pose_kpt_color = [
    [51, 153, 255], [51, 153, 255], [51, 153, 255], [51, 153, 255], [51, 153, 255],
    [0, 255, 0],
    [255, 128, 0], [0, 255, 0], [255, 128, 0], [0, 255, 0], [255, 128, 0], [0, 255, 0],
    [255, 128, 0],
    [0, 255, 0], [255, 128, 0], [0, 255, 0], [255, 128, 0]
]

pose_link_color = [
    [0, 255, 0], [0, 255, 0], [255, 128, 0], [255, 128, 0],
    [51, 153, 255], [51, 153, 255], [51, 153, 255], [51, 153, 255], [0, 255, 0],
    [255, 128, 0],
    [0, 255, 0], [255, 128, 0], [51, 153, 255], [51, 153, 255], [51, 153, 255],
    [51, 153, 255],
    [51, 153, 255], [51, 153, 255], [51, 153, 255]
]

def find_download_model(checkpoint, remote_path):
    modelpath = os.path.join(modeldir, checkpoint)
    old_modelpath = os.path.join(old_modeldir, checkpoint)
        
    if os.path.exists(old_modelpath):
        modelpath = old_modelpath
    elif not os.path.exists(modelpath):
        from basicsr.utils.download_util import load_file_from_url
        load_file_from_url(remote_path, model_dir=modeldir)
        
    return modelpath

def apply_keypose(input_image):
    global human_det, pose_model
    if netNetwork is None:
        det_model_local = find_download_model(det_checkpoint, det_model_path)
        hrnet_model_local = find_download_model(pose_checkpoint, pose_model_path)
        det_config_mmcv = mmcv.Config.fromfile(det_config)
        pose_config_mmcv = mmcv.Config.fromfile(pose_config)
        human_det = init_detector(det_config_mmcv, det_model_local, device=devices.get_device_for("controlnet"))
        pose_model = init_pose_model(pose_config_mmcv, hrnet_model_local, device=devices.get_device_for("controlnet"))

    assert input_image.ndim == 3
    input_image = input_image.copy()
    with torch.no_grad():
        image = torch.from_numpy(input_image).float().to(devices.get_device_for("controlnet"))
        image = image / 255.0
        mmdet_results = inference_detector(human_det, image)
        
        # keep the person class bounding boxes.
        person_results = process_mmdet_results(mmdet_results, det_cat_id)
        
        return_heatmap = False
        dataset = pose_model.cfg.data['test']['type']
        
        # e.g. use ('backbone', ) to return backbone feature
        output_layer_names = None
        pose_results, _ = inference_top_down_pose_model(
            pose_model,
            image,
            person_results,
            bbox_thr=bbox_thr,
            format='xyxy',
            dataset=dataset,
            dataset_info=None,
            return_heatmap=return_heatmap,
            outputs=output_layer_names
        )
        
        im_keypose_out = imshow_keypoints(
            image,
            pose_results,
            skeleton=skeleton,
            pose_kpt_color=pose_kpt_color,
            pose_link_color=pose_link_color,
            radius=2,
            thickness=2
        )
        im_keypose_out = im_keypose_out.astype(np.uint8)

        # image_hed = rearrange(image_hed, 'h w c -> 1 c h w')
        # edge = netNetwork(image_hed)[0]
        # edge = (edge.cpu().numpy() * 255.0).clip(0, 255).astype(np.uint8)
        return im_keypose_out


def unload_hed_model():
    global netNetwork
    if netNetwork is not None:
        netNetwork.cpu()