基于ResNet50的人脸表情识别实战（数据集fer2013、CK+）

CK+数据集共七种表情，分别如下：

共981张图片；

fer2013数据集较大，也是共七种面部表情，如下：

分别存放在如下三个文件夹中：

共35887张图片；

采用基于resnet50的人脸表情识别方法，在CK+数据集准确率达98%，在fer2013数据集准确率达90%。

代码如下：

import os

import numpy as np

import matplotlib.image as mpimg

import random

import matplotlib.pyplot as plt

import plotly.graph_objects as go

from tensorflow.keras.applications import ResNet50

from tensorflow.keras.models import Sequential

from tensorflow.keras.layers import Dense, GlobalAveragePooling2D, Dropout

from tensorflow.keras.optimizers import Adam

from tensorflow.keras.callbacks import ModelCheckpoint, ReduceLROnPlateau, EarlyStopping

from sklearn.utils import shuffle

from sklearn.model_selection import train_test_split

# from sklearn.preprocessing import LabelEncoder

# from skimage.transform import resize

# from keras.utils import to_categorical

from sklearn.metrics import confusion_matrix

from sklearn.metrics import classification_report

from sklearn.preprocessing import LabelEncoder

from tensorflow.keras.preprocessing.image import load_img, img_to_array

dataset_path = './ck/CK+48'

def count_images_and_classes(path):

    class_counts = {}

    total_count = 0

    for class_name in os.listdir(path):

        class_path = os.path.join(path, class_name)

        if os.path.isdir(class_path):

            # Count the number of images in each subfolder

            count = len(os.listdir(class_path))

            total_count += count

            class_counts[class_name] = count

    return total_count, class_counts

total_count, class_counts = count_images_and_classes(dataset_path)

print("Total number of images:", total_count)

print("Number of images in each class:")

for class_name, count in class_counts.items():

    print(f