def load_dataset(dataset_path,filename):
'''
加载人脸数据库
:param dataset_path: embedding.npy文件（faceEmbedding.npy）
:param filename: labels文件路径路径（name.txt）
:return:
'''
embeddings=np.load(dataset_path)
names_list=file_processing.read_data(filename,split=None,convertNum=False)
return embeddings,names_list
def load_dataset(dataset_path, filename):
'''
加载人脸数据库
:param dataset_path: embedding.npy文件（faceEmbedding.npy）
:param filename: labels文件路径路径（name.txt）
:return:
'''
compare_emb = np.load(dataset_path)
names_list = file_processing.read_data(filename, split=False)
return compare_emb, names_list
def label_test(image_dir, filename, class_names):
basename = os.path.basename(filename)[:-len('.txt')] + ".bmp"
image_path = os.path.join(image_dir, basename)
image = image_processing.read_image_gbk(image_path)
data = file_processing.read_data(filename, split=" ")
label_list, rect_list = file_processing.split_list(data, split_index=1)
label_list = [l[0] for l in label_list]
name_list = file_processing.decode_label(label_list, class_names)
image_processing.show_image_rects_text("object2", image, rect_list,
name_list)
def read_pair_data(filename, split=True):
content_list = file_processing.read_data(filename)
if split:
content_list = np.asarray(content_list)
faces_list1 = content_list[:, :1].reshape(-1)
faces_list2 = content_list[:, 1:2].reshape(-1)
# convert to 0/1
issames_data = np.asarray(content_list[:, 2:3].reshape(-1),
dtype=np.int)
issames_data = np.where(issames_data > 0, 1, 0)
faces_list1 = faces_list1.tolist()
faces_list2 = faces_list2.tolist()
issames_data = issames_data.tolist()
return faces_list1, faces_list2, issames_data
return content_list
def label_test(image_dir, filename, class_names=None):
basename = os.path.basename(filename)[:-len('.txt')] + ".jpg"
image_path = os.path.join(image_dir, basename)
image = image_processing.read_image(image_path)
data = file_processing.read_data(filename, split=" ")
label_list, rect_list = file_processing.split_list(data, split_index=1)
label_list = [l[0] for l in label_list]
if class_names:
name_list = file_processing.decode_label(label_list, class_names)
else:
name_list = label_list
show_info = ["id:" + str(n) for n in name_list]
rgb_image = image_processing.show_image_rects_text("object2",
image,
rect_list,
show_info,
color=(0, 0, 255),
drawType="custom",
waitKey=1)
rgb_image = image_processing.resize_image(rgb_image, 900)
image_processing.cv_show_image("object2", rgb_image)
import os.path as osp
import hashlib
import os
md5sum = hashlib.md5
from utils import file_processing
def create_md5sum(image_dir, totle, md5sum_file):
with open(md5sum_file, 'w') as f:
for line in totle:
image_name = line[0]
image_path = os.path.join(image_dir, image_name)
if not os.path.exists(image_path):
print("no path:{}".format(image_path))
img = open(image_path, 'rb').read()
md5 = md5sum(img).hexdigest()
f.write(image_name + ' ' + str(md5) + '\n')
print(image_name + ' ' + str(md5))
if __name__ == "__main__":
filename = "/media/dm/dm/project/dataset/COCO/HumanPose/teacher_2D_pose_estimator/list/val.txt"
image_dir = "/media/dm/dm/project/dataset/COCO/HumanPose/teacher_2D_pose_estimator/list/val"
md5sum_file = "val_md5sum.txt"
data = file_processing.read_data(filename)
create_md5sum(image_dir, data, md5sum_file)
def read_label(filename):
boxes_label_lists = file_processing.read_data(filename)
return boxes_label_lists
images_list = glob.glob(os.path.join(image_dir, '*.jpg'))
for image_path in images_list:
im = image_processing.read_image(image_path,
image_height,
image_width,
normalization=True)
im = im[np.newaxis, :]
# pred = sess.run(f_cls, feed_dict={x:im, keep_prob:1.0})
pre_id, predict_, max_score_ = sess.run(
[max_idx_p, predict, max_score], feed_dict={X: im})
print("{}:pre_id:{},predict:{},max_score:{}".format(
image_path, pre_id, predict_, max_score_))
sess.close()
if __name__ == '__main__':
# 载入字符集
label_filename = './dataset/label_char_set.txt'
char_set = file_processing.read_data(label_filename)
# #
batch_size = 64
image_height = 60
image_width = 160
depth = 3
captcha_size = 4
models_path = 'models/model-4500'
image_dir = './dataset/test'
predict(models_path, image_dir, image_height, image_width, depth, char_set,
captcha_size)
def load_dataset(dataset_path, filename):
# dataset_path: 特征向量文件之路径（faceEmbedding.npy）
# filename: 标签组文件之路径（name.txt）
compare_emb = np.load(dataset_path)
names_list = file_processing.read_data(filename)
return compare_emb, names_list
