# load all the txt file except the classed.txt, test.txt, train.txt
label_file = glob('%s/[!classes, test, train]*.txt' % labels_txt)
print('label count: {}'.format(len(label_file)))
dataset = []
for label in label_file:
with open(os.path.join(labels_txt, label), 'r') as f:
txt_content = f.readlines()
for line in txt_content:
line_split = line.split(' ')
roi_width = float(line_split[-2])
roi_height = float(line_split[-1])
if roi_width == 0 or roi_height == 0:
continue
dataset.append([roi_width, roi_height])
# print([roi_with, roi_height])
return np.array(dataset)
data = load_dataset(ROOT_PATH)
out = kmeans(data, k=CLUSTERS)
print(out)
print("Accuracy: {:.2f}%".format(avg_iou(data, out) * 100))
print("Boxes:\n {}-{}".format(out[:, 0] * SIZE, out[:, 1] * SIZE))
ratios = np.around(out[:, 0] / out[:, 1], decimals=2).tolist()
print("Ratios:\n {}".format(sorted(ratios)))
ymin = int(obj.findtext("bndbox/ymin")) / height
xmax = int(obj.findtext("bndbox/xmax")) / width
ymax = int(obj.findtext("bndbox/ymax")) / height
dataset.append([xmax - xmin, ymax - ymin])
return np.array(dataset)
if __name__ == '__main__':
num = input('epoch:')
data = load_dataset(ANNOTATIONS_PATH)
# 论文中的大小 ACC：63.89%
yolov3_anchors = [[10,13],[16,30],[33,23],[30,61],[62,45],[59,119],[116,90],[156,198],[373,326]]
yolov3_anchors = np.array(yolov3_anchors)
print('YOLOV3 ACC:%.2f%%'%(avg_iou(data, yolov3_anchors/416)*100))
a = int(data.size/2)
print('dataset anchor num: %d'%a)
# 用于计算anchor平均大小
anchor_sum = np.ones((CLUSTERS, 2))*0
# 用于计算平均acc
acc_sum = np.ones((a,2))*0
# 迭代多次
for i in range(1,int(num)+1):
out,t = kmeans(data, k=CLUSTERS)
acc = avg_iou(data, out)
out = sorted(out, key=(lambda x: x[0]))
anchor_sum += out
acc_sum += acc
for s in [300, 512]:
print("Size: {}".format(str(s)))
if s == 512:
cfg = change_cfg_for_ssd512(cfg)
CLUSTERS = 36
anchor_num_dic = dict(zip(range(7), [4, 6, 6, 6, 6, 4, 4]))
out = kmeans(data, k=CLUSTERS)
areas = np.around(out[:, 0] * out[:, 1], decimals=6).tolist()
area_order = np.argsort(areas)
anchors = out[area_order]
print(anchors.shape)
print("Average IoU before clip: {:.2f}%".format(
avg_iou(val_data, anchors) * 100))
if cfg['clip']:
anchors = np.clip(anchors, 0, 1)
print("Average IoU after clip: {:.2f}%".format(
avg_iou(val_data, anchors) * 100))
anchors_loc = []
for k, f in enumerate(cfg['feature_maps']):
for i, j in product(range(f), repeat=2):
f_k = cfg['min_dim'] / cfg['steps'][k]
# unit center x,y
cx = (j + 0.5) / f_k
cy = (i + 0.5) / f_k
sumcum = 0
for m in range(k):
lab = 'claster' + str(i + 1)
plt.scatter(data[index == i, 0],
data[index == i, 1],
s=10,
c=color[i],
marker=mark[i],
label=lab)
plt.legend()
plt.grid()
plt.show()
if __name__ == '__main__':
ANNOTATIONS_PATH = '/home/yangna/yangna/code/object_detection/darknet_origin/scripts/VOCdevkit/VOC2013/Annotations'
CLUSTERS = 9
IMG_SIZE = 608
iteration = 10 #iterate multiple times,take take the best 'avg_iou' result
print('loading data...')
data = load_dataset(ANNOTATIONS_PATH)
print('calculating anchor clusters...')
for index in range(iteration):
out, iter_times = kmeans(data, k=CLUSTERS)
print('\n\niter %d' % (index + 1))
print('kmeans iterate %d times' % iter_times)
print('Accuracy avg_iou: {:.2f}%'.format(avg_iou(data, out) * 100))
#print('Boxes w, h:\n {}-{}'.format(out[:, 0]*IMG_SIZE, out[:, 1]*IMG_SIZE))
print('Boxes w, h:\n {}'.format(out * IMG_SIZE))
ratios = np.around(out[:, 0] / out[:, 1], decimals=2).tolist()
print('Ratios w/h:\n {}'.format(sorted(ratios)))
#plot_data(out, data, CLUSTERS)
def test_avg_iou_simple(self):
self.assertEqual(avg_iou(np.array([[200, 200]]), np.array([[200, 200]])), 1.)
self.assertEqual(avg_iou(np.array([[200, 200]]), np.array([[100, 200]])), .5)
self.assertEqual(avg_iou(np.array([[200, 200]]), np.array([[200, 100]])), .5)
def metric(k, wh): # compute metrics
# r = wh[:, None] / k[None]
# x = torch.min(r, 1. / r).min(2)[0] # ratio metric
# x = wh_iou(wh, torch.tensor(k)) # iou metric
x = avg_iou(wh, k)
return x # x, best_x
ANNOTATIONS_PATH = "/home/cy/集群数据/data/labels/train_data/"
SIZE = 608
CLUSTERS = 9
def load_dataset(path):
dataset = []
txt_file = os.listdir(path)
for txt in txt_file:
with open(path + txt, 'r') as f:
for annotation in f.readlines():
annotation = annotation.split('\t')
dataset.append(
[float(annotation[3]) * SIZE,
float(annotation[4]) * SIZE])
return np.array(dataset)
data = load_dataset(ANNOTATIONS_PATH)
out = kmeans(data, k=CLUSTERS)
# print(out)
original_anchor = [[10, 13], [16, 30], [33, 23], [30, 61], [62, 45], [59, 119],
[116, 90], [156, 198], [373, 326]]
original_anchor = np.array(original_anchor)
print("original accuracy: {:.2f}%".format(
avg_iou(data, original_anchor) * 100))
print("Accuracy: {:.2f}%".format(avg_iou(data, out) * 100))
print("Boxes:\n {}".format(out))
ratios = np.around(out[:, 0] / out[:, 1], decimals=2).tolist()
print("Ratios:\n {}".format(sorted(ratios)))
for i in range(10): ##### 可以修改，不要太大，否则时间很长
anchors_tmp = []
clusters = kmeans(train_boxes, k=CLUSTERS)
idx = clusters[:, 0].argsort()
clusters = clusters[idx]
# print(clusters)
for j in range(CLUSTERS):
anchor = [
round(clusters[j][0] * 640, 2),
round(clusters[j][1] * 640, 2)
]
anchors_tmp.append(anchor)
print(f"Anchors:{anchor}")
temp_accuracy = avg_iou(train_boxes, clusters) * 100
print("Train_Accuracy:{:.2f}%".format(temp_accuracy))
ratios = np.around(clusters[:, 0] / clusters[:, 1],
decimals=2).tolist()
ratios.sort()
print("Ratios:{}".format(ratios))
print(20 * "*" + " {} ".format(count) + 20 * "*")
count += 1
if temp_accuracy > best_accuracy:
best_accuracy = temp_accuracy
best_anchors = anchors_tmp
best_ratios = ratios
anchors.append([s_k, s_k])
# aspect_ratio: 1
# rel size: sqrt(s_k * s_(k+1))
s_k_prime = sqrt(s_k * (cfg['max_sizes'][k] / cfg['min_dim']))
anchors.append([s_k_prime, s_k_prime])
# rest of aspect ratios
for ar in cfg['aspect_ratios'][k]:
anchors.append([s_k * sqrt(ar), s_k / sqrt(ar)])
anchors.append([s_k / sqrt(ar), s_k * sqrt(ar)])
anchors = np.array(anchors)
print(anchors.shape)
print("Average IoU before clip: {:.2f}%".format(
avg_iou(data, anchors) * 100))
if cfg['clip']:
anchors = np.clip(anchors, 0, 1)
print("Average IoU after clip: {:.2f}%".format(
avg_iou(data, anchors) * 100))
anchors_loc = []
for k, f in enumerate(cfg['feature_maps']):
for i, j in product(range(f), repeat=2):
f_k = cfg['min_dim'] / cfg['steps'][k]
# unit center x,y
cx = (j + 0.5) / f_k
cy = (i + 0.5) / f_k
# aspect_ratio: 1
# rel size: min_size
ymax = int(obj.findtext("bndbox/ymax"))
if (xmax - xmin) == 0 or (ymax - ymin) == 0:
continue # to avoid divded by zero error.
dataset.append([xmax - xmin, ymax - ymin])
return np.array(dataset)
print("Start to load data annotations on: %s" % ANNOTATIONS_PATH)
data = load_dataset(ANNOTATIONS_PATH, normalized=BBOX_NORMALIZE)
print('{}'.format(type(data))) #<class 'numpy.ndarray'>,(144027, 2)
print("Start to do kmeans, please wait for a moment.")
out = kmeans(data, k=CLUSTERS) #out为由kmeans找到的聚类中心点
out_sorted = sort_cluster(out)
print('out_sorted', out_sorted)
print("Accuracy: {:.2f}%".format(
avg_iou(data, out) * 100)) #每个框与聚类中心点的最大IOU的平均值，可以用来表示所有框与聚类中心点的平均相似度
show_cluster(data, out, max_points=2000)
if out.dtype != np.float32:
out = out.astype(np.float32)
print("Recommanded aspect ratios(width/height)")
print("Width Height Height/Width")
for i in range(len(out_sorted)):
print("%.3f %.3f %.1f" %
(out_sorted[i, 0], out_sorted[i, 1], out_sorted[i, 2]))
show_width_height(data, out, bins=50)
