python|python训练一个简单的感知机用于手写数据集识别

import keras from keras import layers import matplotlib.pyplot as plt import joblib import keras.datasets.mnist as mnist import pandas as pd import numpy as np(train_image, train_label), (test_image, test_label) = mnist.load_data()#建立感知机 model = keras.Sequential() model.add(layers.Flatten())#Flatten层可以将数据展平成1维的 model.add(layers.Dense(64, activation='relu'))#全连接层 model.add(layers.Dense(10, activation='softmax'))#全连接层,0-10手写数字,所以10个输出model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['acc'])model.fit(train_image, train_label, epochs=50, batch_size=512, validation_data=https://www.it610.com/article/(test_image, test_label))#np.argmax(model_mnist.predict(test_image[:10], axis=1)) y = model.predict(test_image)print(y)

【python|python训练一个简单的感知机用于手写数据集识别】python|python训练一个简单的感知机用于手写数据集识别
文章图片

    推荐阅读