def us(self, face_crop): # face_crop
# person1_feature = net.encode(person1[None, ...])
# print(person1.shape) # torch.Size([3, 112, 112])
# print(torch.unsqueeze(person1, 0).shape) # torch.Size([1, 3, 112, 112])
# print(person1[None, ...].shape) # torch.Size([1, 3, 112, 112])
# print(np.shape(face_crop))
person2 = tf(face_crop).to(self.device)
# person2 = tf(Image.open("Contrast_data/1/pic1_0.jpg")).to(self.device) # 需要辨认的人脸图片
person2_feature = self.net.encode(person2[None, ...])
# data_path = r"D:\PycharmProjects(2)\arcloss-pytorch\test_img" # # 人脸数据库
main_dir = r"D:\PycharmProjects\MTCNN_data\Rocog_face\Contrast_data"
dicts = {"0": "周杰伦", "1": "迪丽热巴", "2": "黄晓明", "3": "Liu Hui", "4": "目标未识别"}
lists = []
lists2 = []
for face_dir in os.listdir(main_dir):
for face_filename in os.listdir(os.path.join(main_dir, face_dir)):
img = Image.open(os.path.join(main_dir, face_dir, face_filename))
img = img.convert("RGB")
person1 = tf(img).to(self.device)
person1_feature = self.net.encode(torch.unsqueeze(person1, 0))
# 改进： 改为并行比较，或查找方法，提高对比速度
siam = compare(person1_feature, person2_feature) # 将数据库中的人脸和需要辨认的人脸做比较
# print("余弦相似度值：", max(siam.item(), 0)) # 余弦相似度 tensor([[0.9988]])
# x = "周杰伦" if round(siam.item()) == 1 else "其他人"
# x = "迪丽热巴" if round(siam.item()) == 1 else "其他人"
# print(face_filename)
# font = ImageFont.truetype("simhei.ttf", 20)
if siam.item() > 0.8: # 人脸相似度大于某个阈值，否则被pass掉。
print("余弦相似度值：", max(siam.item(), 0))
print(face_dir) # 找到类别文件夹
value = dicts[str(face_dir)] # 根据类别取到类别的值
lists.append(value)
# print(value) # 将字典里的值取出来
print(lists)
else:
pass
# print(lists1) # 每比较完一类人脸图片，打印一次列表
return lists
def face_detector(self,img):
if torch.cuda.is_available():
device = torch.device('cuda')
else:
device = torch.device('cpu')
max_threshold = 0
threshold = 0.7
max_threshold_feature = 0
person1 = tf(img).to(device)
person1_feature = self.net.encode(torch.unsqueeze(person1, 0))
kys = self.face_dict.keys()
kys = list(kys)
# print(kys[0].shape)
# a = torch.randn([len(kys),kys[0].shape[0],kys[0].shape[1]])
# print(a.shape)
# print(a[0].shape)
# exit()
for person_feature in kys:
# print(person_feature.shape)
siam = compare(person1_feature, person_feature)
# print(self.face_dict[person_feature], siam)
if siam > threshold and siam > max_threshold:
max_threshold = siam
max_threshold_feature = person_feature
print('----------完美分割线----------------')
if max_threshold > 0:
name = self.face_dict[max_threshold_feature]
y = time.time()
# print(y - x)
return name,max_threshold.item()
return '','0.0'
def __init__(self):
self.device = torch.device(
"cuda" if torch.cuda.is_available() else "cpu")
self.save_path = r"D:\PycharmProjects\MTCNN_data\Rocog_face\params\1.pth"
self.net = FaceNet().to(self.device)
self.net.load_state_dict(torch.load(self.save_path))
self.net.eval()
self.face_dict = {}
x = time.time()
main_dir = r"D:\PycharmProjects\MTCNN_data\Rocog_face\Contrast_data2"
for face_dir in os.listdir(main_dir):
for face_filename in os.listdir(os.path.join(main_dir, face_dir)):
img = Image.open(
os.path.join(main_dir, face_dir, face_filename))
img = trans_square(img)
# 将拿到的图片转成正方形112*112
person1 = tf(img).to(self.device)
person1_feature = self.net.encode(torch.unsqueeze(person1, 0))
self.face_dict[person1_feature] = face_dir # 将人脸特征向量作为键，类别名作为值
# print(self.face_dict[person1_feature]) # 人脸特征向量对应类别名 0
# exit()
# lists3.extend(person1_feature)
# lists3.append([person1_feature, face_dir]) # 方便将人脸数据库转成特征向量进行打包。
# 改进： 改为并行比较，或查找方法，提高对比速度
# print(person1_feature.shape) # torch.Size([1, 512])
# print(person2_feature.shape) # torch.Size([1, 512])
y = time.time()
print(y - x)
def us(self, face_crop): # face_crop
# data_path = r"D:\PycharmProjects(2)\arcloss-pytorch\test_img" # # 人脸数据库
# dicts = {"0": "周杰伦", "1": "迪丽热巴", "2": "黄晓明", "3": "刘辉", "4": "目标未识别", "5": "小红", "6": "小花"}
# print(np.shape(face_crop)) # (342, 258, 3)
face_crop = trans_square(face_crop)
# print(np.shape(face_crop)) # (342, 342, 3)
# 将裁剪出来的图片转成正方形112*112
person2 = tf(face_crop).to(self.device)
# print(np.shape(face_crop)) # (342, 342, 3)
# person2 = tf(Image.open("Contrast_data/1/pic1_0.jpg")).to(self.device)
person2_feature = self.net.encode(person2[None, ...]) # 传进来的人脸图片
kys = self.face_dict.keys() # 拿到人脸数据库里面的键（即人脸特征向量）
# print(self.face_dict)
# print(kys)
kys = list(kys) # 将人脸特征向量放在一个列表中
# print(kys)
# siam = compare(person1_feature, person2_feature) # 将数据库中的人脸和需要辨认的人脸做比较
# print("余弦相似度值：", max(siam.item(), 0)) # 余弦相似度 tensor([[0.9988]])
# x = "周杰伦" if round(siam.item()) == 1 else "其他人"
# x = "迪丽热巴" if round(siam.item()) == 1 else "其他人"
# print(face_filename)
# font = ImageFont.truetype("simhei.ttf", 20)
max_threshold = 0
threshold = 0.7
max_threshold_feature = 0
for person1_feature_ in kys: # 遍历数据库里面的人脸特征向量
# print(person1_feature_)
siam = compare(person1_feature_, person2_feature)
if siam > threshold and siam > max_threshold:
max_threshold = siam # 如果余弦相似度大于所设置阈值，就赋值给最大阈值。同时能够更新所设置的最大阈值。因为最后只需要拿到余弦相似度最大的哪个值。
max_threshold_feature = person1_feature_ # 这时也拿到相应的人脸特征向量
if max_threshold > 0:
cls = self.face_dict[
max_threshold_feature] # 拿到余弦相似度最大时的人脸特征向量对应的类别名
# print(max_threshold_feature) # 拿到余弦相似度最大时的人脸特征向量
return cls, max_threshold_feature
return '', '0.0' # 如果上面返回的是空值， 此时要设置默认值占位。
def us(self, face_crop): # face_crop
data_path = r"D:\PycharmProjects\MTCNN_data\Rocog_face\face_images\database_face_1.jpg" # # 人脸数据库
img = Image.open(data_path)
img = img.convert("RGB")
person1 = tf(img).to(self.device)
person1_feature = self.net.encode(torch.unsqueeze(person1, 0))
# person1_feature = net.encode(person1[None, ...])
# print(person1.shape) # torch.Size([3, 112, 112])
# print(torch.unsqueeze(person1, 0).shape) # torch.Size([1, 3, 112, 112])
# print(person1[None, ...].shape) # torch.Size([1, 3, 112, 112])
person2 = tf(face_crop).to(self.device)
# person2 = tf(Image.open("./face_images/recog_face_1.jpg")).to(self.device) # 需要辨认的人脸图片
person2_feature = self.net.encode(person2[None, ...])
siam = compare(person1_feature, person2_feature)
print("余弦相似度值：", siam.item()) # 余弦相似度 tensor([[0.9988]])
# x = "周杰伦" if round(siam.item()) == 1 else "其他人"
# x = "迪丽热巴" if round(siam.item()) == 1 else "其他人"
x = "Liu Hui" if siam.item() >= 0.8 else "other people"
return x
def face_detector(self, img):
if torch.cuda.is_available():
device = torch.device('cuda')
else:
device = torch.device('cpu')
max_threshold = 0
threshold = 0.7
max_threshold_feature = 0
person1 = tf(img).to(device)
person1_feature = self.net.encode(torch.unsqueeze(person1, 0))
kys = self.face_dict.keys()
kys = list(kys)
# print(kys[0].shape)
# a = torch.randn([len(kys),kys[0].shape[0],kys[0].shape[1]])
# print(a.shape)
# print(a[0].shape)
# exit()
for person_feature in kys: # 原始载入人脸特征向量
# print(person_feature.shape)
siam = compare(person1_feature,
person_feature) # 将裁剪下来的人脸和数据库的人脸做比较
# print(self.face_dict[person_feature], siam)
# print("余弦相似度", siam)
if siam > threshold and siam > max_threshold:
max_threshold = siam # 如果余弦相似度大于所设置阈值，就赋值给最大阈值。同时能够更新所设置的最大阈值。因为最后只需要拿到余弦相似度最大的哪个值。
max_threshold_feature = person_feature # 这时也拿到相应的人脸特征向量
# print('----------完美分割线----------------')
if max_threshold > 0:
# print(max_threshold_feature)
name = self.face_dict[
max_threshold_feature] # 拿到余弦相似度最大时的人脸特征向量对应的类别名
# print(max_threshold_feature) # 拿到余弦相似度最大时的人脸特征向量
return name, max_threshold.item()
return '', '0.0'
def __init__(self):
path = r"Contrast_data"
# self.save_path = r"D:\PycharmProjects\MTCNN_data\Rocog_face\params\1.pth"
net_path = r"D:\PycharmProjects\MTCNN_data\Rocog_face\params\1.pth"
if torch.cuda.is_available():
device = torch.device('cuda')
else:
device = torch.device('cpu')
self.net = FaceNet().to(device)
self.net.load_state_dict(torch.load(net_path))
self.net.eval()
self.face_dict = {}
for face_dir in os.listdir(path):
for face_filename in os.listdir(os.path.join(path, face_dir)):
person_path = os.path.join(path, face_dir, face_filename)
img = Image.open(person_path)
img = img.convert("RGB")
img = img.resize((112, 112))
person1 = tf(img).to(device)
person1_feature = self.net.encode(torch.unsqueeze(person1, 0))
self.face_dict[person1_feature] = face_dir
def face_detector(self, img):
if torch.cuda.is_available():
device = torch.device('cuda')
else:
device = torch.device('cpu')
max_threshold = 0
threshold = 0.7
max_threshold_feature = 0
name = 0
person1 = tf(img).to(device) # 需要辨认的人脸
person1_feature = self.net.encode(torch.unsqueeze(person1, 0))
# 载入np人脸特征向量包
np_path = r"D:\PycharmProjects\MTCNN_data\Rocog_face\list_data.npz"
list_o = npz2list(np_path) # 载入numpy保存的人脸数据库文件
# print(np.shape(list_o))
for x in list_o: # 遍历数据库中的人脸特征
# print(x)
siam = compare(x[0], person1_feature) # 将数据库中的人脸和需要辨认的人脸做比较
# print("余弦相似度值：", max(siam.item(), 0)) # 余弦相似度 tensor([[0.9988]])
if siam > threshold and siam > max_threshold:
max_threshold = siam # 如果余弦相似度大于所设置阈值，就赋值给最大阈值。同时能够更新所设置的最大阈值。因为最后只需要拿到余弦相似度最大的哪个值。
max_threshold_feature = x[0]
name = x[1]
# print('----------完美分割线----------------')
# if max_threshold > 0:
# print(max_threshold_feature)
# name = self.face_dict[max_threshold_feature] # 拿到余弦相似度最大时的人脸特征向量对应的类别名
# print(max_threshold_feature) # 拿到余弦相似度最大时的人脸特征向量
# print(name)
# print(max_threshold_feature)
return name, max_threshold_feature
def __init__(self):
path = r"D:\PycharmProjects\MTCNN_data\Rocog_face\Contrast_data"
# self.save_path = r"D:\PycharmProjects\MTCNN_data\Rocog_face\params\1.pth"
net_path = r"D:\PycharmProjects\MTCNN_data\Rocog_face\params\1.pth"
if torch.cuda.is_available():
device = torch.device('cuda')
else:
device = torch.device('cpu')
self.net = FaceNet().to(device)
self.net.load_state_dict(torch.load(net_path))
self.net.eval()
self.face_dict = {}
self.lists3 = []
for face_dir in os.listdir(path):
for face_filename in os.listdir(os.path.join(path, face_dir)):
img = Image.open(os.path.join(path, face_dir, face_filename))
img = trans_square(img)
person1 = tf(img).to(device)
person1_feature = self.net.encode(torch.unsqueeze(person1, 0))
self.face_dict[person1_feature] = face_dir # 将人脸特征向量作为键，类别名作为值
# print(self.face_dict[person1_feature]) # 人脸特征向量对应类别名 0
self.lists3.append([person1_feature, face_dir]) # 将人脸特征向量保存下来
def us(self, face_crop): # face_crop
# person1_feature = net.encode(person1[None, ...])
# print(person1.shape) # torch.Size([3, 112, 112])
# print(torch.unsqueeze(person1, 0).shape) # torch.Size([1, 3, 112, 112])
# print(person1[None, ...].shape) # torch.Size([1, 3, 112, 112])
start = time.time()
# print(np.shape(face_crop)) # (342, 258, 3)
face_crop = trans_square(face_crop)
# print(np.shape(face_crop)) # (342, 342, 3)
# 将裁剪出来的图片转成正方形112*112
person2 = tf(face_crop).to(self.device)
# print(np.shape(face_crop)) # (342, 342, 3)
# person2 = tf(Image.open("Contrast_data/1/pic1_0.jpg")).to(self.device) # 需要辨认的人脸图片
person2_feature = self.net.encode(person2[None, ...])
# data_path = r"D:\PycharmProjects(2)\arcloss-pytorch\test_img" # # 人脸数据库
main_dir = r"D:\PycharmProjects\MTCNN_data\Rocog_face\Contrast_data"
dicts = {"0": "周杰伦", "1": "迪丽热巴", "2": "黄晓明", "3": "刘辉", "4": "吴晓斌"}
lists = []
lists2 = []
lists3 = []
# for face_dir in os.listdir(main_dir):
# for face_filename in os.listdir(os.path.join(main_dir, face_dir)):
# img = Image.open(os.path.join(main_dir, face_dir, face_filename))
# img = trans_square(img)
#
# # 将拿到的图片转成正方形112*112
# person1 = tf(img).to(self.device)
# person1_feature = self.net.encode(torch.unsqueeze(person1, 0))
# lists3.append([person1_feature, face_dir])
# 改进： 改为并行比较，或查找方法，提高对比速度
path = r"D:\PycharmProjects\MTCNN_data\Rocog_face\list_data.npz"
list_o = npz2list(path) # 载入numpy保存的人脸数据库文件
# print(np.shape(list_o))
for x in list_o: # 遍历数据库中的人脸特征
# print(x)
# print(x[1]) # 0
# print(x[0].shape) # torch.Size([1, 512])
siam = compare(x[0], person2_feature) # 将数据库中的人脸和需要辨认的人脸做比较
print("余弦相似度值：", max(siam.item(), 0)) # 余弦相似度 tensor([[0.9988]])
# x = "周杰伦" if round(siam.item()) == 1 else "其他人"
# x = "迪丽热巴" if round(siam.item()) == 1 else "其他人"
# print(face_filename)
# font = ImageFont.truetype("simhei.ttf", 20)
if siam.item() > 0.8: # 人脸相似度大于某个阈值，否则被pass掉。
# print(x[1]) # 类别文件夹
value = dicts[str(x[1])]
lists.append(value)
# print(lists) # ['黄晓明', '黄晓明', '黄晓明', '黄晓明', '刘辉', '刘辉']
# print(value) # 将字典里的值取出来
# print("*" * 100)
else:
pass
end = time.time()
print("对比完所有图片所用时间：", end - start) # 0.75s
# np.savez('list_data', lists3)
# print(lists1) # 每比较完一类图片，打印一次列表
# print(lists3)
return lists