in easycv/core/evaluation/top_down_eval.py [0:0]
def keypoints_from_heatmaps(heatmaps,
center,
scale,
unbiased=False,
post_process='default',
kernel=11,
valid_radius_factor=0.0546875,
use_udp=False,
target_type='GaussianHeatmap'):
"""Get final keypoint predictions from heatmaps and transform them back to
the image.
Note:
batch size: N
num keypoints: K
heatmap height: H
heatmap width: W
Args:
heatmaps (np.ndarray[N, K, H, W], dtype=float32): model predicted heatmaps.
center (np.ndarray[N, 2]): Center of the bounding box (x, y).
scale (np.ndarray[N, 2]): Scale of the bounding box
wrt height/width.
post_process (str/None): Choice of methods to post-process
heatmaps. Currently supported: None, 'default', 'unbiased',
'megvii'.
unbiased (bool): Option to use unbiased decoding. Mutually
exclusive with megvii.
Note: this arg is deprecated and unbiased=True can be replaced
by post_process='unbiased'
Paper ref: Zhang et al. Distribution-Aware Coordinate
Representation for Human Pose Estimation (CVPR 2020).
kernel (int): Gaussian kernel size (K) for modulation, which should
match the heatmap gaussian sigma when training.
K=17 for sigma=3 and k=11 for sigma=2.
valid_radius_factor (float): The radius factor of the positive area
in classification heatmap for UDP.
use_udp (bool): Use unbiased data processing.
target_type (str): 'GaussianHeatmap' or 'CombinedTarget'.
GaussianHeatmap: Classification target with gaussian distribution.
CombinedTarget: The combination of classification target
(response map) and regression target (offset map).
Paper ref: Huang et al. The Devil is in the Details: Delving into
Unbiased Data Processing for Human Pose Estimation (CVPR 2020).
Returns:
tuple: A tuple containing keypoint predictions and scores.
- preds (np.ndarray[N, K, 2]): Predicted keypoint location in images.
- maxvals (np.ndarray[N, K, 1]): Scores (confidence) of the keypoints.
"""
# Avoid being affected
if not np.issubsctype(heatmaps, np.float32):
heatmaps = heatmaps.astype(np.float32)
heatmaps = heatmaps.copy()
# detect conflicts
if unbiased:
assert post_process not in [False, None, 'megvii']
if post_process in ['megvii', 'unbiased']:
assert kernel > 0
if use_udp:
assert not post_process == 'megvii'
# normalize configs
if post_process is False:
warnings.warn(
'post_process=False is deprecated, '
'please use post_process=None instead', DeprecationWarning)
post_process = None
elif post_process is True:
if unbiased is True:
warnings.warn(
'post_process=True, unbiased=True is deprecated,'
" please use post_process='unbiased' instead",
DeprecationWarning)
post_process = 'unbiased'
else:
warnings.warn(
'post_process=True, unbiased=False is deprecated, '
"please use post_process='default' instead",
DeprecationWarning)
post_process = 'default'
elif post_process == 'default':
if unbiased is True:
warnings.warn(
'unbiased=True is deprecated, please use '
"post_process='unbiased' instead", DeprecationWarning)
post_process = 'unbiased'
# start processing
if post_process == 'megvii':
heatmaps = _gaussian_blur(heatmaps, kernel=kernel)
N, K, H, W = heatmaps.shape
if use_udp:
if target_type.lower() == 'GaussianHeatMap'.lower():
preds, maxvals = _get_max_preds(heatmaps)
preds = post_dark_udp(preds, heatmaps, kernel=kernel)
elif target_type.lower() == 'CombinedTarget'.lower():
for person_heatmaps in heatmaps:
for i, heatmap in enumerate(person_heatmaps):
kt = 2 * kernel + 1 if i % 3 == 0 else kernel
cv2.GaussianBlur(heatmap, (kt, kt), 0, heatmap)
# valid radius is in direct proportion to the height of heatmap.
valid_radius = valid_radius_factor * H
offset_x = heatmaps[:, 1::3, :].flatten() * valid_radius
offset_y = heatmaps[:, 2::3, :].flatten() * valid_radius
heatmaps = heatmaps[:, ::3, :]
preds, maxvals = _get_max_preds(heatmaps)
index = preds[..., 0] + preds[..., 1] * W
index += W * H * np.arange(0, N * K / 3)
index = index.astype(int).reshape(N, K // 3, 1)
preds += np.concatenate((offset_x[index], offset_y[index]), axis=2)
else:
raise ValueError('target_type should be either '
"'GaussianHeatmap' or 'CombinedTarget'")
else:
preds, maxvals = _get_max_preds(heatmaps)
if post_process == 'unbiased': # alleviate biased coordinate
# apply Gaussian distribution modulation.
heatmaps = np.log(
np.maximum(_gaussian_blur(heatmaps, kernel), 1e-10))
for n in range(N):
for k in range(K):
preds[n][k] = _taylor(heatmaps[n][k], preds[n][k])
elif post_process is not None:
# add +/-0.25 shift to the predicted locations for higher acc.
for n in range(N):
for k in range(K):
heatmap = heatmaps[n][k]
px = int(preds[n][k][0])
py = int(preds[n][k][1])
if 1 < px < W - 1 and 1 < py < H - 1:
diff = np.array([
heatmap[py][px + 1] - heatmap[py][px - 1],
heatmap[py + 1][px] - heatmap[py - 1][px]
])
preds[n][k] += np.sign(diff) * .25
if post_process == 'megvii':
preds[n][k] += 0.5
# Transform back to the image
for i in range(N):
preds[i] = transform_preds(
preds[i], center[i], scale[i], [W, H], use_udp=use_udp)
if post_process == 'megvii':
maxvals = maxvals / 255.0 + 0.5
return preds, maxvals