File size: 7,242 Bytes
26364eb |
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 |
import numpy as np
import pandas as pd
def box_iou_calc(boxes1, boxes2):
# https://github.com/pytorch/vision/blob/master/torchvision/ops/boxes.py
"""
Return intersection-over-union (Jaccard index) of boxes.
Both sets of boxes are expected to be in (x1, y1, x2, y2) format.
Arguments:
boxes1 (Array[N, 4])
boxes2 (Array[M, 4])
Returns:
iou (Array[N, M]): the NxM matrix containing the pairwise
IoU values for every element in boxes1 and boxes2
This implementation is taken from the above link and changed so that it only uses numpy.
"""
def box_area(box):
# box = 4xn
return (box[2] - box[0]) * (box[3] - box[1])
area1 = box_area(boxes1.T)
area2 = box_area(boxes2.T)
lt = np.maximum(boxes1[:, None, :2], boxes2[:, :2]) # [N,M,2]
rb = np.minimum(boxes1[:, None, 2:], boxes2[:, 2:]) # [N,M,2]
inter = np.prod(np.clip(rb - lt, a_min = 0, a_max = None), 2)
return inter / (area1[:, None] + area2 - inter) # iou = inter / (area1 + area2 - inter)
def mask_iou_calc(pred_masks, gt_masks):
"""Helper function calculate the IOU of masks
Args:
pred_masks (_type_): N x H x W, array of N masks
gt_masks (_type_): M x H x W, an array of M masks
Returns:
iou: an array of NxM of IOU ([0,1])
N rows - number of actual labels
M columns - number of preds
"""
if pred_masks.size == 0:
return np.array([])
# build function to take in two masks, compare them and see what their iou is.
# similar to above but in mask.
tp = np.sum(np.multiply(pred_masks[:, None], gt_masks), axis = (2,3))
fp = np.sum(np.where(pred_masks[:, None] > gt_masks, 1, 0), axis = (2,3))
fn = np.sum(np.where(pred_masks[:, None] < gt_masks, 1, 0), axis = (2,3))
# print (f"tp: {tp}")
# print (f"fp: {fp}")
# print (f"fn: {fn}")
iou = tp / (tp + fn + fp)
return iou.T
class ConfusionMatrix:
def __init__(self, num_classes, CONF_THRESHOLD = 0.2, IOU_THRESHOLD = 0.5):
self.matrix = np.zeros((num_classes + 1, num_classes + 1))
self.num_classes = num_classes
self.CONF_THRESHOLD = CONF_THRESHOLD
self.IOU_THRESHOLD = IOU_THRESHOLD
self.got_tpfpfn = False
def process_batch(self, detections, labels, return_matches=False, task = "det"):
'''
Return intersection-over-union (Jaccard index) of boxes.
Both sets of boxes are expected to be in (x1, y1, x2, y2) format.
Arguments:
detections (Array[N, 6]), x1, y1, x2, y2, conf, class
labels (Array[M, 5]), class, x1, y1, x2, y2
Returns:
None, updates confusion matrix accordingly
'''
if task == 'det':
detections = detections[detections[:, 4] > self.CONF_THRESHOLD]
gt_classes = labels[:, 0].astype(np.int16)
detection_classes = detections[:, 5].astype(np.int16)
all_ious = box_iou_calc(labels[:, 1:], detections[:, :4])
want_idx = np.where(all_ious > self.IOU_THRESHOLD)
elif task == 'seg':
detections = [detection for detection in detections if detection[1] > self.CONF_THRESHOLD]
gt_classes = np.array([label[0]for label in labels], dtype = np.int16)
detection_classes = np.array([detection[2] for detection in detections], dtype = np.int16)
all_ious = mask_iou_calc(np.array([detection[0] for detection in detections]), np.array([label[1] for label in labels]))
want_idx = np.where(all_ious > self.IOU_THRESHOLD)
all_matches = []
for i in range(want_idx[0].shape[0]):
all_matches.append([want_idx[0][i], want_idx[1][i], all_ious[want_idx[0][i], want_idx[1][i]]])
all_matches = np.array(all_matches)
if all_matches.shape[0] > 0: # if there is match
all_matches = all_matches[all_matches[:, 2].argsort()[::-1]]
all_matches = all_matches[np.unique(all_matches[:, 1], return_index = True)[1]]
all_matches = all_matches[all_matches[:, 2].argsort()[::-1]]
all_matches = all_matches[np.unique(all_matches[:, 0], return_index = True)[1]]
for i, label in enumerate(labels):
if all_matches.shape[0] > 0 and all_matches[all_matches[:, 0] == i].shape[0] == 1:
gt_class = gt_classes[i]
detection_class = detection_classes[int(all_matches[all_matches[:, 0] == i, 1][0])]
self.matrix[(gt_class), detection_class] += 1
else:
gt_class = gt_classes[i]
self.matrix[(gt_class), self.num_classes] += 1
for i, detection in enumerate(detections):
if all_matches.shape[0] and all_matches[all_matches[:, 1] == i].shape[0] == 0:
detection_class = detection_classes[i]
self.matrix[self.num_classes ,detection_class] += 1
if return_matches:
return all_matches
def get_tpfpfn(self):
self.tp = np.diag(self.matrix).sum()
fp = self.matrix.copy()
np.fill_diagonal(fp, 0)
self.fp = fp[:,:-1].sum()
self.fn = self.matrix[:-1, -1].sum()
self.got_tpfpfn = True
def get_PR(self):
if not self.got_tpfpfn:
self.get_tpfpfn()
# print (tp, fp, fn)
self.precision = self.tp / (self.tp+self.fp)
self.recall = self.tp/(self.tp+self.fn)
def return_matrix(self):
return self.matrix
def process_full_matrix(self):
"""method to process matrix to something more readable
"""
for idx, i in enumerate(self.matrix):
i[0] = idx
self.matrix = np.delete(self.matrix, 0, 0)
def print_matrix_as_df(self):
"""method to print out processed matrix
"""
df = pd.DataFrame(self.matrix)
print (df.to_string(index=False))
# def print_matrix(self):
# for i in range(self.num_classes + 1):
# print(' '.join(map(str, self.matrix[i])))
def return_as_csv(self, csv_file_path):
"""method to print out processed matrix
"""
df = pd.DataFrame(self.matrix)
df.to_csv(csv_file_path, index = False)
print (f"saved to: {csv_file_path}")
def return_as_df(self):
"""method to print out processed matrix
"""
df = pd.DataFrame(self.matrix)
# df = df.set_index(0)
# df.set_index(0)
# print(df.columns)
return df
if __name__ == '__main__':
# # test IOU for segmentation masks
gtMasks = np.array([[[1, 1, 0],
[0, 1, 0],
[0, 0, 0]],
[[1, 1, 0],
[0, 1, 1],
[0, 0, 0]]])
predMasks = np.array([[[1, 1, 0],
[0, 1, 1],
[0, 0, 0]],
[[1, 1, 0],
[0, 1, 0],
[0, 0, 0]]])
# IOU is 0.75
IOU = mask_iou_calc(predMasks, gtMasks)
print (IOU.shape)
|