（02）pynq 简易图像识别（2GraphicRecognition）

# numpy provides arrays and useful functions for working with them
import numpy
# scipy.special for the sigmoid function expit()
import scipy.special
# scipy.ndimage for rotating image arrays
import scipy.ndimage
import matplotlib.pyplot
# ensure the plots are inside this notebook, not an external window
%matplotlib inline
import imageio

#########################
#########################
#########################
# （一）引入神经网络
# （1）定义神经网络
# neuralNetwork输入参数：
# inputnodes, hiddennodes,outputnodes, learningrate
# wih == 输入层权重     who == 输出层权重
# activation function == sigmoid函数(S激活函数)
# inverse_activation_function == sigmoid的反函数
class neuralNetwork:
    def __init__(self, inputnodes, hiddennodes, outputnodes, learningrate):
        self.inodes = inputnodes
        self.hnodes = hiddennodes
        self.onodes = outputnodes        
        self.wih = numpy.random.normal(0.0, pow(self.inodes, -0.5), (self.hnodes, self.inodes))
        self.who = numpy.random.normal(0.0, pow(self.hnodes, -0.5), (self.onodes, self.hnodes))
        self.lr = learningrate
        self.activation_function = lambda x: scipy.special.expit(x)
        self.inverse_activation_function = lambda x: scipy.special.logit(x)
        pass
#########################
#（2）训练神经网络 
# neuralNetwork.train输入：
# inputs_list, targets_list
# 更新权重
    def train(self, inputs_list, targets_list):
        # convert inputs list to 2d array
        inputs = numpy.array(inputs_list, ndmin=2).T
        targets = numpy.array(targets_list, ndmin=2).T
        # calculate signals into hidden layer
        hidden_inputs = numpy.dot(self.wih, inputs)
        # calculate the signals emerging from hidden layer
        hidden_outputs = self.activation_function(hi