深度学习人脸表情识别代码

以下是一个基于深度学习的人脸表情识别的Python代码示例：

import numpy as np
import pandas as pd
import cv2
import keras
from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout
from keras.preprocessing.image import ImageDataGenerator

# 加载数据集
train_data = pd.read_csv("fer2013/fer2013_train.csv")
test_data = pd.read_csv("fer2013/fer2013_test.csv")

# 数据预处理
train_pixels = train_data["pixels"].tolist()
train_images = []
for i in range(len(train_pixels)):
    pixels = np.array(train_pixels[i].split())
    image = pixels.reshape(48, 48, 1).astype("float32")
    train_images.append(image)
train_images = np.array(train_images)
train_labels = keras.utils.to_categorical(train_data["emotion"], num_classes=7)

test_pixels = test_data["pixels"].tolist()
test_images = []
for i in range(len(test_pixels)):
    pixels = np.array(test_pixels[i].split())
    image = pixels.reshape(48, 48, 1).astype("float32")
    test_images.append(image)
test_images = np.array(test_images)
test_labels = keras.utils.to_categorical(test_data["emotion"], num_classes=7)

# 构建模型
model = Sequential()
model.add(Conv2D(32, (3,3), activation="relu", input_shape=(48, 48, 1)))
model.add(Conv2D(64, (3,3), activation="relu"))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Dropout(0.25))

model.add(Conv2D(128, (3,3), activation="relu"))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Conv2D(128, (3,3), activation="relu"))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Dropout(0.25))

model.add(Flatten())
model.add(Dense(1024, activation="relu"))
model.add(Dropout(0.5))
model.add(Dense(7, activation="softmax"))

# 编译模型
model.compile(optimizer="adam", loss="categorical_crossentropy", metrics=["accuracy"])

# 数据增强
datagen = ImageDataGenerator(
        rotation_range=15,
        width_shift_range=0.1,
        height_shift_range=0.1,
        shear_range=0.1,
        zoom_range=0.1,
        horizontal_flip=True,
        vertical_flip=False)
datagen.fit(train_images)

# 训练模型
history = model.fit_generator(datagen.flow(train_images, train_labels, batch_size=32),
                    steps_per_epoch=len(train_images) / 32, epochs=50, validation_data=(test_images, test_labels))

# 测试模型
test_loss, test_acc = model.evaluate(test_images, test_labels)
print("Test accuracy: ", test_acc)

# 保存模型
model.save("emotion_detection_model.h5")

这个示例代码使用Keras库搭建了一个卷积神经网络的模型，并使用FER2013数据集进行训练和测试，同时使用数据增强技术来提高模型的鲁棒性。最后，将模型保存到了本地文件中。