[밑바닥부터 시작하는 딥러닝] Part_1/CHAPTER 5 오차역전파법

import numpy as np

In [1]:

class Relu:
    def __init__(self):
        self.mask = None

    def forward(self, x):
        self.mask = (x <= 0)
        out = x.copy()
        out[self.mask] = 0

        return out

    def backward(self, dout):
        dout[self.mask] = 0
        dx = dout

        return dx

In [4]:

x = np.array([[1.0, -0.5], [-2.0, 3.0]])

In [5]:

print(x)

[[ 1.  -0.5]
 [-2.   3. ]]

In [6]:

mask = (x <= 0)

In [7]:

print(mask)

[[False  True]
 [ True False]]

In [8]:

# coding: utf-8
import sys, os
sys.path.append(os.pardir)  # 부모 디렉토리의 파일을 가져올 수 있도록 설정
import numpy as np
from dataset.mnist import load_mnist
from two_layer_net import TwoLayerNet

# 데이터읽기
(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True, one_hot_label=True)

network = TwoLayerNet(input_size=784, hidden_size=50, output_size=10)

x_batch = x_train[:3]
t_batch = t_train[:3]

grad_numerical = network.numerical_gradient(x_batch, t_batch)
grad_backprop = network.gradient(x_batch, t_batch)
# 각 가중치의 절대 오차의 평균을 구한다.
for key in grad_numerical.keys():
    diff = np.average( np.abs(grad_backprop[key] - grad_numerical[key]) )
    print(key + ":" + str(diff))

---------------------------------------------------------------------------
ModuleNotFoundError                       Traceback (most recent call last)
<ipython-input-8-1485d1831192> in <module>
      3 sys.path.append(os.pardir)  # 부모 디렉토리의 파일을 가져올 수 있도록 설정
      4 import numpy as np
----> 5 from dataset.mnist import load_mnist
      6 from two_layer_net import TwoLayerNet
      7 

ModuleNotFoundError: No module named 'dataset.mnist'

In [ ]: