File size: 5,262 Bytes
5a486d6 |
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 |
import cv2
import os
import numpy as np
from collections import OrderedDict
from PIL import Image as PILImage
from utils.transforms import transform_parsing
LABELS = ['Background', 'Hat', 'Hair', 'Glove', 'Sunglasses', 'Upper-clothes', 'Dress', 'Coat', \
'Socks', 'Pants', 'Jumpsuits', 'Scarf', 'Skirt', 'Face', 'Left-arm', 'Right-arm', 'Left-leg',
'Right-leg', 'Left-shoe', 'Right-shoe']
# LABELS = ['Background', 'Head', 'Torso', 'Upper Arms', 'Lower Arms', 'Upper Legs', 'Lower Legs']
def get_palette(num_cls):
""" Returns the color map for visualizing the segmentation mask.
Args:
num_cls: Number of classes
Returns:
The color map
"""
n = num_cls
palette = [0] * (n * 3)
for j in range(0, n):
lab = j
palette[j * 3 + 0] = 0
palette[j * 3 + 1] = 0
palette[j * 3 + 2] = 0
i = 0
while lab:
palette[j * 3 + 0] |= (((lab >> 0) & 1) << (7 - i))
palette[j * 3 + 1] |= (((lab >> 1) & 1) << (7 - i))
palette[j * 3 + 2] |= (((lab >> 2) & 1) << (7 - i))
i += 1
lab >>= 3
return palette
def get_confusion_matrix(gt_label, pred_label, num_classes):
"""
Calcute the confusion matrix by given label and pred
:param gt_label: the ground truth label
:param pred_label: the pred label
:param num_classes: the nunber of class
:return: the confusion matrix
"""
index = (gt_label * num_classes + pred_label).astype('int32')
label_count = np.bincount(index)
confusion_matrix = np.zeros((num_classes, num_classes))
for i_label in range(num_classes):
for i_pred_label in range(num_classes):
cur_index = i_label * num_classes + i_pred_label
if cur_index < len(label_count):
confusion_matrix[i_label, i_pred_label] = label_count[cur_index]
return confusion_matrix
def compute_mean_ioU(preds, scales, centers, num_classes, datadir, input_size=[473, 473], dataset='val'):
val_file = os.path.join(datadir, dataset + '_id.txt')
val_id = [i_id.strip() for i_id in open(val_file)]
confusion_matrix = np.zeros((num_classes, num_classes))
for i, pred_out in enumerate(preds):
im_name = val_id[i]
gt_path = os.path.join(datadir, dataset + '_segmentations', im_name + '.png')
gt = np.array(PILImage.open(gt_path))
h, w = gt.shape
s = scales[i]
c = centers[i]
pred = transform_parsing(pred_out, c, s, w, h, input_size)
gt = np.asarray(gt, dtype=np.int32)
pred = np.asarray(pred, dtype=np.int32)
ignore_index = gt != 255
gt = gt[ignore_index]
pred = pred[ignore_index]
confusion_matrix += get_confusion_matrix(gt, pred, num_classes)
pos = confusion_matrix.sum(1)
res = confusion_matrix.sum(0)
tp = np.diag(confusion_matrix)
pixel_accuracy = (tp.sum() / pos.sum()) * 100
mean_accuracy = ((tp / np.maximum(1.0, pos)).mean()) * 100
IoU_array = (tp / np.maximum(1.0, pos + res - tp))
IoU_array = IoU_array * 100
mean_IoU = IoU_array.mean()
print('Pixel accuracy: %f \n' % pixel_accuracy)
print('Mean accuracy: %f \n' % mean_accuracy)
print('Mean IU: %f \n' % mean_IoU)
name_value = []
for i, (label, iou) in enumerate(zip(LABELS, IoU_array)):
name_value.append((label, iou))
name_value.append(('Pixel accuracy', pixel_accuracy))
name_value.append(('Mean accuracy', mean_accuracy))
name_value.append(('Mean IU', mean_IoU))
name_value = OrderedDict(name_value)
return name_value
def compute_mean_ioU_file(preds_dir, num_classes, datadir, dataset='val'):
list_path = os.path.join(datadir, dataset + '_id.txt')
val_id = [i_id.strip() for i_id in open(list_path)]
confusion_matrix = np.zeros((num_classes, num_classes))
for i, im_name in enumerate(val_id):
gt_path = os.path.join(datadir, 'segmentations', im_name + '.png')
gt = cv2.imread(gt_path, cv2.IMREAD_GRAYSCALE)
pred_path = os.path.join(preds_dir, im_name + '.png')
pred = np.asarray(PILImage.open(pred_path))
gt = np.asarray(gt, dtype=np.int32)
pred = np.asarray(pred, dtype=np.int32)
ignore_index = gt != 255
gt = gt[ignore_index]
pred = pred[ignore_index]
confusion_matrix += get_confusion_matrix(gt, pred, num_classes)
pos = confusion_matrix.sum(1)
res = confusion_matrix.sum(0)
tp = np.diag(confusion_matrix)
pixel_accuracy = (tp.sum() / pos.sum()) * 100
mean_accuracy = ((tp / np.maximum(1.0, pos)).mean()) * 100
IoU_array = (tp / np.maximum(1.0, pos + res - tp))
IoU_array = IoU_array * 100
mean_IoU = IoU_array.mean()
print('Pixel accuracy: %f \n' % pixel_accuracy)
print('Mean accuracy: %f \n' % mean_accuracy)
print('Mean IU: %f \n' % mean_IoU)
name_value = []
for i, (label, iou) in enumerate(zip(LABELS, IoU_array)):
name_value.append((label, iou))
name_value.append(('Pixel accuracy', pixel_accuracy))
name_value.append(('Mean accuracy', mean_accuracy))
name_value.append(('Mean IU', mean_IoU))
name_value = OrderedDict(name_value)
return name_value
|