使用facenet_keras.h5开发人脸识别遇TensorFlow相关问题求助

我正在开发人脸识别程序，需要通过TensorFlow调用facenet_keras.h5模型，但运行代码时出现三个问题：numpy dtype弃用警告、AVX指令提示以及模型未编译的警告，求解决方法。

运行代码 #

import os
from os import listdir
from PIL import Image as Img
from numpy import asarray
from numpy import expand_dims
from keras.models import load_model
import numpy as np

import pickle
import cv2

# 加载分类器与facenet_keras模型
HaarCascade = cv2.CascadeClassifier(cv2.samples.findFile(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml'))
MyFaceNet = load_model("facenet_keras.h5")


folder = 'photos/' # 照片文件夹路径
database = {}

for filename in listdir(folder):

    path = folder + filename
    gbr1 = cv2.imread(path)

    visage = HaarCascade.detectMultiScale(gbr1, 1.1, 4)

    if len(visage) > 0:
        x1, y1, width, height = visage[0]
    else:
        x1, y1, width, height = 1, 1, 10, 10

    x1, y1 = abs(x1), abs(y1)
    x2, y2 = x1 + width, y1 + height

    gbr = cv2.cvtColor(gbr1, cv2.COLOR_BGR2RGB)
    gbr = Img.fromarray(gbr)  # OpenCV格式转PIL格式
    gbr_array = asarray(gbr)  # 转为数组

    face = gbr_array[y1:y2, x1:x2]  # 提取面部区域

    face = Img.fromarray(face)  # 转回图像格式
    face = face.resize((160, 160))
    face = asarray(face)

    # 归一化输入
    face = face.astype('float32')
    mean, std = face.mean(), face.std() # 计算均值与标准差
    face = (face - mean) / std

    # 输入到facenet模型
    face = expand_dims(face, axis=0)
    signature = MyFaceNet.predict(face)

    database[os.path.splitext(filename)[0]] = signature

myfile = open("data.pkl", "wb")
pickle.dump(database, myfile)
myfile.close()

myfile = open("data.pkl", "rb")
database = pickle.load(myfile)
myfile.close()

错误信息 #

Using TensorFlow backend.
C:\Users\Zouzou\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\framework\dtypes.py:458: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint8 = np.dtype([("qint8", np.int8, 1)])
C:\Users\Zouzou\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\framework\dtypes.py:459: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint8 = np.dtype([("quint8", np.uint8, 1)])
C:\Users\Zouzou\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\framework\dtypes.py:460: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint16 = np.dtype([("qint16", np.int16, 1)])
C:\Users\Zouzou\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\framework\dtypes.py:461: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint16 = np.dtype([("quint16", np.uint16, 1)])
C:\Users\Zouzou\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\framework\dtypes.py:462: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint32 = np.dtype([("qint32", np.int32, 1)])
C:\Users\Zouzou\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\framework\dtypes.py:465: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  np_resource = np.dtype([("resource", np.ubyte, 1)])
2022-10-12 15:26:25.360069: W C:\tf_jenkins\home\workspace\rel-win\M\windows\PY\36\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
C:\Users\Zouzou\AppData\Local\Programs\Python\Python36\lib\site-packages\keras\models.py:252: UserWarning: No training configuration found in save file: the model was *not* compiled. Compile it manually.
  warnings.warn('No training configuration found in save file: '

解决方案 #

1. numpy dtype弃用警告 #

• 原因：适配Python3.6的旧版TensorFlow与当前numpy版本不兼容，旧TensorFlow的dtype定义方式在新版numpy中被标记为弃用。
• 解决方式：
  • 降级numpy到兼容版本，执行命令：pip install numpy==1.16.6
  • 或者在代码开头添加警告过滤，暂时屏蔽该类警告：

    import warnings
    warnings.filterwarnings("ignore", category=FutureWarning)
    

2. AVX指令提示 #

• 原因：你安装的TensorFlow预编译包未启用AVX指令集优化，但你的CPU支持该指令集，因此提示可提升计算速度。
• 解决方式：
  • 该提示仅影响性能，不干扰程序运行，可直接忽略。
  • 若要利用AVX加速，需从TensorFlow源码编译并开启AVX编译选项，操作复杂，普通使用无需折腾。
  • 也可在代码开头添加日志设置屏蔽警告：

    import tensorflow as tf
    tf.compat.v1.logging.set_verbosity(tf.compat.v1.logging.ERROR)
    

3. 模型未编译警告 #

• 原因：facenet_keras.h5是预训练特征提取模型，保存时未包含训练配置（仅用于预测，无需训练），因此加载时触发警告。
• 解决方式：
  • 仅做预测的话，该警告不影响功能，可直接忽略。
  • 若要消除警告，可在加载模型后手动编译（无需实际训练，随便选优化器和损失函数即可）：

    MyFaceNet = load_model("facenet_keras.h5")
    # 添加以下编译代码
    MyFaceNet.compile(optimizer='adam', loss='categorical_crossentropy')
    

内容的提问来源于stack exchange，提问作者h81 edrick