前提条件:
- dataset 里面有数字图片数据集
- sample_weight.pkl 学习训练后的权重W及偏置b,假设已学习训练完成,学习参数保存在该文件
neuralnet_mnist.py:
import io
import sys,os
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8')
sys.path.append(os.pardir)
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.image import imread
import pickle
from dataset.mnist import load_mnist
from common.functions import sigmoid, softmax
print('_hello,inited!')
## 假设学习训练已完成,学习的参数保存在sample_weiht.pkl中,测试数据10000个
def get_data():
(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True, flatten=True, one_hot_label=False)
return x_test, t_test
## 加载权重W及偏置b,利用pickle功能,高效地完成MNIST数据的准备工作
def init_network():
with open('resource/sample_weight.pkl', 'rb') as f:
network = pickle.load(f)
return