Spaces:
Running
Running
File size: 9,740 Bytes
95f8bbc |
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 |
import collections
import math
import re
import time
import cv2
import numpy as np
import torch
from torch._six import string_classes
RED = (0, 0, 255)
GREEN = (0, 255, 0)
BLUE = (255, 0, 0)
CYAN = (255, 255, 0)
YELLOW = (0, 255, 255)
ORANGE = (0, 165, 255)
PURPLE = (255, 0, 255)
numpy_type_map = {
'float64': torch.DoubleTensor,
'float32': torch.FloatTensor,
'float16': torch.HalfTensor,
'int64': torch.LongTensor,
'int32': torch.IntTensor,
'int16': torch.ShortTensor,
'int8': torch.CharTensor,
'uint8': torch.ByteTensor,
}
_use_shared_memory = True
def collate_fn(batch):
r"""Puts each data field into a tensor with outer dimension batch size"""
error_msg = "batch must contain tensors, numbers, dicts or lists; found {}"
elem_type = type(batch[0])
if isinstance(batch[0], torch.Tensor):
out = None
if _use_shared_memory:
# If we're in a background process, concatenate directly into a
# shared memory tensor to avoid an extra copy
numel = sum([x.numel() for x in batch])
storage = batch[0].storage()._new_shared(numel)
out = batch[0].new(storage)
return torch.stack(batch, 0, out=out)
elif elem_type.__module__ == 'numpy' and elem_type.__name__ != 'str_' \
and elem_type.__name__ != 'string_':
elem = batch[0]
if elem_type.__name__ == 'ndarray':
# array of string classes and object
if re.search('[SaUO]', elem.dtype.str) is not None:
raise TypeError(error_msg.format(elem.dtype))
return torch.stack([torch.from_numpy(b) for b in batch], 0)
if elem.shape == (): # scalars
py_type = float if elem.dtype.name.startswith('float') else int
return numpy_type_map[elem.dtype.name](list(map(py_type, batch)))
elif isinstance(batch[0], int):
return torch.LongTensor(batch)
elif isinstance(batch[0], float):
return torch.DoubleTensor(batch)
elif isinstance(batch[0], string_classes):
return batch
elif isinstance(batch[0], collections.Mapping):
return {key: collate_fn([d[key] for d in batch]) for key in batch[0]}
elif isinstance(batch[0], collections.Sequence):
transposed = zip(*batch)
return [collate_fn(samples) for samples in transposed]
raise TypeError((error_msg.format(type(batch[0]))))
def collate_fn_list(batch):
img, inp, im_name = zip(*batch)
img = collate_fn(img)
im_name = collate_fn(im_name)
return img, inp, im_name
def vis_frame_fast(frame, im_res, format='coco'):
'''
frame: frame image
im_res: im_res of predictions
format: coco or mpii
return rendered image
'''
if format == 'coco':
l_pair = [
(0, 1), (0, 2), (1, 3), (2, 4), # Head
(5, 6), (5, 7), (7, 9), (6, 8), (8, 10),
(17, 11), (17, 12), # Body
(11, 13), (12, 14), (13, 15), (14, 16)
]
p_color = [(0, 255, 255), (0, 191, 255), (0, 255, 102), (0, 77, 255), (0, 255, 0), # Nose, LEye, REye, LEar, REar
(77, 255, 255), (77, 255, 204), (77, 204, 255), (191, 255, 77), (77, 191, 255), (191, 255, 77),
# LShoulder, RShoulder, LElbow, RElbow, LWrist, RWrist
(204, 77, 255), (77, 255, 204), (191, 77, 255), (77, 255, 191), (127, 77, 255), (77, 255, 127),
(0, 255, 255)] # LHip, RHip, LKnee, Rknee, LAnkle, RAnkle, Neck
line_color = [(0, 215, 255), (0, 255, 204), (0, 134, 255), (0, 255, 50),
(77, 255, 222), (77, 196, 255), (77, 135, 255), (191, 255, 77), (77, 255, 77),
(77, 222, 255), (255, 156, 127),
(0, 127, 255), (255, 127, 77), (0, 77, 255), (255, 77, 36)]
elif format == 'mpii':
l_pair = [
(8, 9), (11, 12), (11, 10), (2, 1), (1, 0),
(13, 14), (14, 15), (3, 4), (4, 5),
(8, 7), (7, 6), (6, 2), (6, 3), (8, 12), (8, 13)
]
p_color = [PURPLE, BLUE, BLUE, RED, RED, BLUE, BLUE, RED, RED, PURPLE, PURPLE, PURPLE, RED, RED, BLUE, BLUE]
else:
NotImplementedError
im_name = im_res['imgname'].split('/')[-1]
img = frame
for human in im_res['result']:
part_line = {}
kp_preds = human['keypoints']
kp_scores = human['kp_score']
kp_preds = torch.cat((kp_preds, torch.unsqueeze((kp_preds[5, :] + kp_preds[6, :]) / 2, 0)))
kp_scores = torch.cat((kp_scores, torch.unsqueeze((kp_scores[5, :] + kp_scores[6, :]) / 2, 0)))
# Draw keypoints
for n in range(kp_scores.shape[0]):
if kp_scores[n] <= 0.05:
continue
cor_x, cor_y = int(kp_preds[n, 0]), int(kp_preds[n, 1])
part_line[n] = (cor_x, cor_y)
cv2.circle(img, (cor_x, cor_y), 4, p_color[n], -1)
# Draw limbs
for i, (start_p, end_p) in enumerate(l_pair):
if start_p in part_line and end_p in part_line:
start_xy = part_line[start_p]
end_xy = part_line[end_p]
cv2.line(img, start_xy, end_xy, line_color[i], 2 * (kp_scores[start_p] + kp_scores[end_p]) + 1)
return img
def vis_frame(frame, im_res, format='coco'):
'''
frame: frame image
im_res: im_res of predictions
format: coco or mpii
return rendered image
'''
if format == 'coco':
l_pair = [
(0, 1), (0, 2), (1, 3), (2, 4), # Head
(5, 6), (5, 7), (7, 9), (6, 8), (8, 10),
(17, 11), (17, 12), # Body
(11, 13), (12, 14), (13, 15), (14, 16)
]
p_color = [(0, 255, 255), (0, 191, 255), (0, 255, 102), (0, 77, 255), (0, 255, 0), # Nose, LEye, REye, LEar, REar
(77, 255, 255), (77, 255, 204), (77, 204, 255), (191, 255, 77), (77, 191, 255), (191, 255, 77),
# LShoulder, RShoulder, LElbow, RElbow, LWrist, RWrist
(204, 77, 255), (77, 255, 204), (191, 77, 255), (77, 255, 191), (127, 77, 255), (77, 255, 127),
(0, 255, 255)] # LHip, RHip, LKnee, Rknee, LAnkle, RAnkle, Neck
line_color = [(0, 215, 255), (0, 255, 204), (0, 134, 255), (0, 255, 50),
(77, 255, 222), (77, 196, 255), (77, 135, 255), (191, 255, 77), (77, 255, 77),
(77, 222, 255), (255, 156, 127),
(0, 127, 255), (255, 127, 77), (0, 77, 255), (255, 77, 36)]
elif format == 'mpii':
l_pair = [
(8, 9), (11, 12), (11, 10), (2, 1), (1, 0),
(13, 14), (14, 15), (3, 4), (4, 5),
(8, 7), (7, 6), (6, 2), (6, 3), (8, 12), (8, 13)
]
p_color = [PURPLE, BLUE, BLUE, RED, RED, BLUE, BLUE, RED, RED, PURPLE, PURPLE, PURPLE, RED, RED, BLUE, BLUE]
line_color = [PURPLE, BLUE, BLUE, RED, RED, BLUE, BLUE, RED, RED, PURPLE, PURPLE, RED, RED, BLUE, BLUE]
else:
raise NotImplementedError
im_name = im_res['imgname'].split('/')[-1]
img = frame
height, width = img.shape[:2]
img = cv2.resize(img, (int(width / 2), int(height / 2)))
for human in im_res['result']:
part_line = {}
kp_preds = human['keypoints']
kp_scores = human['kp_score']
kp_preds = torch.cat((kp_preds, torch.unsqueeze((kp_preds[5, :] + kp_preds[6, :]) / 2, 0)))
kp_scores = torch.cat((kp_scores, torch.unsqueeze((kp_scores[5, :] + kp_scores[6, :]) / 2, 0)))
# Draw keypoints
for n in range(kp_scores.shape[0]):
if kp_scores[n] <= 0.05:
continue
cor_x, cor_y = int(kp_preds[n, 0]), int(kp_preds[n, 1])
part_line[n] = (int(cor_x / 2), int(cor_y / 2))
bg = img.copy()
cv2.circle(bg, (int(cor_x / 2), int(cor_y / 2)), 2, p_color[n], -1)
# Now create a mask of logo and create its inverse mask also
transparency = max(0, min(1, kp_scores[n].item()))
img = cv2.addWeighted(bg, transparency, img, 1 - transparency, 0)
# Draw proposal score on the head
middle_eye = (kp_preds[1] + kp_preds[2]) / 4
middle_cor = int(middle_eye[0]) - 10, int(middle_eye[1]) - 12
cv2.putText(img, f"{human['proposal_score'].item():.2f}", middle_cor, cv2.FONT_HERSHEY_SIMPLEX, 0.3, (0, 0, 255))
# Draw limbs
for i, (start_p, end_p) in enumerate(l_pair):
if start_p in part_line and end_p in part_line:
start_xy = part_line[start_p]
end_xy = part_line[end_p]
bg = img.copy()
X = (start_xy[0], end_xy[0])
Y = (start_xy[1], end_xy[1])
mX = np.mean(X)
mY = np.mean(Y)
length = ((Y[0] - Y[1]) ** 2 + (X[0] - X[1]) ** 2) ** 0.5
angle = math.degrees(math.atan2(Y[0] - Y[1], X[0] - X[1]))
stickwidth = (kp_scores[start_p] + kp_scores[end_p]) + 1
polygon = cv2.ellipse2Poly((int(mX), int(mY)), (int(length / 2), int(stickwidth)), int(angle), 0, 360, 1)
cv2.fillConvexPoly(bg, polygon, line_color[i])
# cv2.line(bg, start_xy, end_xy, line_color[i], (2 * (kp_scores[start_p] + kp_scores[end_p])) + 1)
transparency = max(0, min(1, 0.5 * (kp_scores[start_p] + kp_scores[end_p]).item()))
img = cv2.addWeighted(bg, transparency, img, 1 - transparency, 0)
img = cv2.resize(img, (width, height), interpolation=cv2.INTER_CUBIC)
return img
def getTime(time1=0):
if not time1:
return time.time()
else:
interval = time.time() - time1
return time.time(), interval
|