반응형 cnn2 [CNN]tensorflow 없이 numpy로만 convolution 날코딩 하기 import numpy as np from matplotlib import pyplot as plt class NN: def __init__(self,n_i,n_h,n_y): self.w1 = np.random.rand(n_i,n_h) self.w2 = np.random.rand(n_h,n_y) def sigmoid(self,z): return 1./(1.+np.exp(-z)) def dsigmoid(self,z): # sigmoid 미분 return z*(1. - z) def layer(self,inputs): print('self.sigmoid(np.dot(inputs,self.w1))') self.hidden = self.sigmoid(np.dot(inputs,self.w1)) print(self... 2020. 11. 10. global local - 3.1 Convolutional Neural Networks 3.1 Convolutional Neural Networks Our approach is based on Convolutional Neural Networks [Fukushima 1988; LeCun et al. 1989]. These are a special variant of neural network based on using convolution operators that conserve the spatial structure of the input, generally consisting of images. These networks are formed by layers in which a bank of filters is convoluted with the input map to produce .. 2020. 11. 5. 이전 1 다음 반응형
