File size: 8,345 Bytes
970a7a2 |
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 |
# coding: utf-8
__author__ = 'ZFTurbo: https://kaggle.com/zfturbo'
import numpy as np
from numba import jit
def prepare_boxes(boxes, scores, labels):
result_boxes = boxes.copy()
cond = (result_boxes < 0)
cond_sum = cond.astype(np.int32).sum()
if cond_sum > 0:
print('Warning. Fixed {} boxes coordinates < 0'.format(cond_sum))
result_boxes[cond] = 0
cond = (result_boxes > 1)
cond_sum = cond.astype(np.int32).sum()
if cond_sum > 0:
print('Warning. Fixed {} boxes coordinates > 1. Check that your boxes was normalized at [0, 1]'.format(cond_sum))
result_boxes[cond] = 1
boxes1 = result_boxes.copy()
result_boxes[:, 0] = np.min(boxes1[:, [0, 2]], axis=1)
result_boxes[:, 2] = np.max(boxes1[:, [0, 2]], axis=1)
result_boxes[:, 1] = np.min(boxes1[:, [1, 3]], axis=1)
result_boxes[:, 3] = np.max(boxes1[:, [1, 3]], axis=1)
area = (result_boxes[:, 2] - result_boxes[:, 0]) * (result_boxes[:, 3] - result_boxes[:, 1])
cond = (area == 0)
cond_sum = cond.astype(np.int32).sum()
if cond_sum > 0:
print('Warning. Removed {} boxes with zero area!'.format(cond_sum))
result_boxes = result_boxes[area > 0]
scores = scores[area > 0]
labels = labels[area > 0]
return result_boxes, scores, labels
def cpu_soft_nms_float(dets, sc, Nt, sigma, thresh, method):
"""
Based on: https://github.com/DocF/Soft-NMS/blob/master/soft_nms.py
It's different from original soft-NMS because we have float coordinates on range [0; 1]
:param dets: boxes format [x1, y1, x2, y2]
:param sc: scores for boxes
:param Nt: required iou
:param sigma:
:param thresh:
:param method: 1 - linear soft-NMS, 2 - gaussian soft-NMS, 3 - standard NMS
:return: index of boxes to keep
"""
# indexes concatenate boxes with the last column
N = dets.shape[0]
indexes = np.array([np.arange(N)])
dets = np.concatenate((dets, indexes.T), axis=1)
# the order of boxes coordinate is [y1, x1, y2, x2]
y1 = dets[:, 1]
x1 = dets[:, 0]
y2 = dets[:, 3]
x2 = dets[:, 2]
scores = sc
areas = (x2 - x1) * (y2 - y1)
for i in range(N):
# intermediate parameters for later parameters exchange
tBD = dets[i, :].copy()
tscore = scores[i].copy()
tarea = areas[i].copy()
pos = i + 1
#
if i != N - 1:
maxscore = np.max(scores[pos:], axis=0)
maxpos = np.argmax(scores[pos:], axis=0)
else:
maxscore = scores[-1]
maxpos = 0
if tscore < maxscore:
dets[i, :] = dets[maxpos + i + 1, :]
dets[maxpos + i + 1, :] = tBD
tBD = dets[i, :]
scores[i] = scores[maxpos + i + 1]
scores[maxpos + i + 1] = tscore
tscore = scores[i]
areas[i] = areas[maxpos + i + 1]
areas[maxpos + i + 1] = tarea
tarea = areas[i]
# IoU calculate
xx1 = np.maximum(dets[i, 1], dets[pos:, 1])
yy1 = np.maximum(dets[i, 0], dets[pos:, 0])
xx2 = np.minimum(dets[i, 3], dets[pos:, 3])
yy2 = np.minimum(dets[i, 2], dets[pos:, 2])
w = np.maximum(0.0, xx2 - xx1)
h = np.maximum(0.0, yy2 - yy1)
inter = w * h
ovr = inter / (areas[i] + areas[pos:] - inter)
# Three methods: 1.linear 2.gaussian 3.original NMS
if method == 1: # linear
weight = np.ones(ovr.shape)
weight[ovr > Nt] = weight[ovr > Nt] - ovr[ovr > Nt]
elif method == 2: # gaussian
weight = np.exp(-(ovr * ovr) / sigma)
else: # original NMS
weight = np.ones(ovr.shape)
weight[ovr > Nt] = 0
scores[pos:] = weight * scores[pos:]
# select the boxes and keep the corresponding indexes
inds = dets[:, 4][scores > thresh]
keep = inds.astype(int)
return keep
@jit(nopython=True)
def nms_float_fast(dets, scores, thresh):
"""
# It's different from original nms because we have float coordinates on range [0; 1]
:param dets: numpy array of boxes with shape: (N, 5). Order: x1, y1, x2, y2, score. All variables in range [0; 1]
:param thresh: IoU value for boxes
:return: index of boxes to keep
"""
x1 = dets[:, 0]
y1 = dets[:, 1]
x2 = dets[:, 2]
y2 = dets[:, 3]
areas = (x2 - x1) * (y2 - y1)
order = scores.argsort()[::-1]
keep = []
while order.size > 0:
i = order[0]
keep.append(i)
xx1 = np.maximum(x1[i], x1[order[1:]])
yy1 = np.maximum(y1[i], y1[order[1:]])
xx2 = np.minimum(x2[i], x2[order[1:]])
yy2 = np.minimum(y2[i], y2[order[1:]])
w = np.maximum(0.0, xx2 - xx1)
h = np.maximum(0.0, yy2 - yy1)
inter = w * h
ovr = inter / (areas[i] + areas[order[1:]] - inter)
inds = np.where(ovr <= thresh)[0]
order = order[inds + 1]
return keep
def nms_method(boxes, scores, labels, method=3, iou_thr=0.5, sigma=0.5, thresh=0.001, weights=None):
"""
:param boxes: list of boxes predictions from each model, each box is 4 numbers.
It has 3 dimensions (models_number, model_preds, 4)
Order of boxes: x1, y1, x2, y2. We expect float normalized coordinates [0; 1]
:param scores: list of scores for each model
:param labels: list of labels for each model
:param method: 1 - linear soft-NMS, 2 - gaussian soft-NMS, 3 - standard NMS
:param iou_thr: IoU value for boxes to be a match
:param sigma: Sigma value for SoftNMS
:param thresh: threshold for boxes to keep (important for SoftNMS)
:param weights: list of weights for each model. Default: None, which means weight == 1 for each model
:return: boxes: boxes coordinates (Order of boxes: x1, y1, x2, y2).
:return: scores: confidence scores
:return: labels: boxes labels
"""
# If weights are specified
if weights is not None:
if len(boxes) != len(weights):
print('Incorrect number of weights: {}. Must be: {}. Skip it'.format(len(weights), len(boxes)))
else:
weights = np.array(weights)
for i in range(len(weights)):
scores[i] = (np.array(scores[i]) * weights[i]) / weights.sum()
# We concatenate everything
boxes = np.concatenate(boxes)
scores = np.concatenate(scores)
labels = np.concatenate(labels)
# Fix coordinates and removed zero area boxes
boxes, scores, labels = prepare_boxes(boxes, scores, labels)
# Run NMS independently for each label
unique_labels = np.unique(labels)
final_boxes = []
final_scores = []
final_labels = []
for l in unique_labels:
condition = (labels == l)
boxes_by_label = boxes[condition]
scores_by_label = scores[condition]
labels_by_label = np.array([l] * len(boxes_by_label))
if method != 3:
keep = cpu_soft_nms_float(boxes_by_label.copy(), scores_by_label.copy(), Nt=iou_thr, sigma=sigma, thresh=thresh, method=method)
else:
# Use faster function
keep = nms_float_fast(boxes_by_label, scores_by_label, thresh=iou_thr)
final_boxes.append(boxes_by_label[keep])
final_scores.append(scores_by_label[keep])
final_labels.append(labels_by_label[keep])
final_boxes = np.concatenate(final_boxes)
final_scores = np.concatenate(final_scores)
final_labels = np.concatenate(final_labels)
return final_boxes, final_scores, final_labels
def nms(boxes, scores, labels, iou_thr=0.5, weights=None):
"""
Short call for standard NMS
:param boxes:
:param scores:
:param labels:
:param iou_thr:
:param weights:
:return:
"""
return nms_method(boxes, scores, labels, method=3, iou_thr=iou_thr, weights=weights)
def soft_nms(boxes, scores, labels, method=2, iou_thr=0.5, sigma=0.5, thresh=0.001, weights=None):
"""
Short call for Soft-NMS
:param boxes:
:param scores:
:param labels:
:param method:
:param iou_thr:
:param sigma:
:param thresh:
:param weights:
:return:
"""
return nms_method(boxes, scores, labels, method=method, iou_thr=iou_thr, sigma=sigma, thresh=thresh, weights=weights) |