#parameter setting

import numpy as np
from mnist import load_mnist

np.random.seed(5)

(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True ,one_hot_label=True)
<br>
/*mnist save <br><br> */



X = x_train[0:100] /* Test data */ <br>
W = {} <br>

W['W1'] = np.random.randn(784, 30)

W['W2'] = np.random.randn(30, 20)

W['W3'] = np.random.randn(20, 10) /*set weight */


S = {}
A = {}
Y = t_train[0:100]

dA ={}
dS ={}
dW ={}

---

#function setting

### def Softmax(ScoreMatrix):

    if ScoreMatrix.ndim == 2:
        temp = ScoreMatrix
        temp = temp - np.max(temp, axis=1, keepdims= True)
        y_predict = np.exp(temp) / np.sum(np.exp(temp), axis=1, keepdims=True)
        return y_predict
    temp = ScoreMatrix - np.max(ScoreMatrix, axis=0)
    expX = np.exp(temp)
    y_predict = expX / np.sum(expX)
    return y_predict

### def relu(Score):

    A = np.maximum(0, Score)
    return A

### def forward(X):

    A['A0'] = X
    S['S1'] = np.dot(X, W['W1'])
    A['A1'] = relu(S['S1'])
    S['S2'] = np.dot(A['A1'], W['W2'])
    A['A2'] = relu(S['S2'])
    S['S3'] = np.dot(A['A2'], W['W3'])
    Y_predict = Softmax(S['S3'])
    Loss = -(np.sum(Y*np.log(Y_predict+1e-7))) / Y.shape[0]
    print(Loss)
    return Y_predict

### def Backward(Y_predict):

    mask ={}
    dS['S3'] = (Y_predict - Y) / Y.shape[0]
    dW['W3'] = np.dot(A['A2'].T, dS['S3'])
    dA['A2'] = np.dot(dS['S3'], W['W3'].T)
    mask['R2'] = (A['A2'] > 0)
    dS['S2'] = dA['A2']*mask['R2']
    dW['W2'] = np.dot(A['A1'].T, dS['S2'])
    dA['A1'] = np.dot(dS['S2'], W['W2'].T)
    mask['R1'] = (A['A1'] > 0)
    dS['S1'] = dA['A1'] * mask['R1']
    dW['W1'] = np.dot(A['A0'].T, dS['S1'])

### def Gradient():

    W['W1'] -= 0.1*dW['W1']
    W['W2'] -= 0.1*dW['W2']
    W['W3'] -= 0.1*dW['W3']


### def Optimizer():

    for i in range(10000):
        Y_predict = forward(X)
        Backward(Y_predict)
        Gradient()






Y_predict = forward(x_train[100:200])
Y_predict.shape


Last = (Y_predict - Y) / Y.shape[0]








Optimizer()   /* optimizer call


y_predict =forward(x_train[0:100])<br>
print(y_predict[10].shape) <br>
count=0 <br>
it is checked y_predict[i] checked [0.1 0.1 0.1 0.1 0.1 0.1 0.1 0.1 0.1 0.1]

for i in range(100):
        if(np.array_equal(y_predict[i], np.ones(10)*0.1)):
        print(i)
        print(y_predict[i])
        count+=1

print('count ', count)

'''


## result is :

y_predict[i]
41
[0.1 0.1 0.1 0.1 0.1 0.1 0.1 0.1 0.1 0.1]
45
[0.1 0.1 0.1 0.1 0.1 0.1 0.1 0.1 0.1 0.1]
54
[0.1 0.1 0.1 0.1 0.1 0.1 0.1 0.1 0.1 0.1]
67
[0.1 0.1 0.1 0.1 0.1 0.1 0.1 0.1 0.1 0.1]
72
[0.1 0.1 0.1 0.1 0.1 0.1 0.1 0.1 0.1 0.1]
76
[0.1 0.1 0.1 0.1 0.1 0.1 0.1 0.1 0.1 0.1]
82
[0.1 0.1 0.1 0.1 0.1 0.1 0.1 0.1 0.1 0.1]

count 7

Why did this result come out?