【pythonでCNN#4】Convolutional層(順伝播)
記事の目的
pythonでCNN(畳み込みニューラルネットワーク)を実装する上で必要になるConvolutional層の順伝播を実装していきます。ここにある全てのコードは、コピペで再現することが可能です。
目次
1 畳み込み演算
2 im2col関数
# In[1] import numpy as np # In[2] def im2col(x, fil_size, y_size, stride, pad): x_b, x_c, x_h, x_w = x.shape fil_h, fil_w = fil_size, fil_size y_h, y_w = y_size, y_size index = -1 x_pad = np.pad(x, [(0, 0), (0, 0), (pad, pad), (pad, pad)], "constant") x_col = np.zeros((fil_h*fil_w, x_b, x_c, y_h, y_w)) for h in range(fil_h): h2 = h + y_h*stride for w in range(fil_w): index += 1 w2 = w + y_w*stride x_col[index,:,:,:,:] = x_pad[:,:,h:h2:stride,w:w2:stride] x_col = x_col.transpose(2,0,1,3,4).reshape(x_c*fil_h*fil_w, x_b*y_h*y_w) return x_col # In[3] x = np.arange(144).reshape(3,3,4,4) x_col = im2col(x,3,2,1,0) x_col.shape # In[4] w = np.arange(54).reshape(2,3,3,3) w_col = w.reshape(2,-1) w_col # In[5] b = np.ones((1,2)) b # In[6] y = np.dot(w_col, x_col) y # In[7] y = y.T + b y # In[8] y.reshape(3,2,2,2).transpose(0,3,1,2)
3 Convolutional層
# In[9] class Conv: def __init__(self, x_c, y_c, fil_size, stride, pad): self.x_c, self.y_c = x_c, y_c self.fil_h, self.fil_w = fil_size, fil_size self.stride, self.pad = stride, pad self.w = np.arange(54).reshape(2,3,3,3) self.b = np.zeros((1,self.y_c)) #self.w = np.random.randn(self.y_c, self.x_c, self.fil_h, self.fil_w) #self.b = np.random.randn(1, self.y_c) def forward(self, x): self.x_b, self.x_c, self.x_h, self.x_w = x.shape self.y_h = (self.x_h - self.fil_h + 2*self.pad) // self.stride + 1 self.y_w = (self.x_w - self.fil_w + 2*self.pad) // self.stride + 1 self.x_col = im2col(x, self.fil_h, self.y_h, self.stride, self.pad) self.w_col = self.w.reshape(self.y_c, self.x_c*self.fil_h*self.fil_w) y = np.dot(self.w_col, self.x_col).T + self.b self.y = y.reshape(self.x_b, self.y_h, self.y_w, self.y_c).transpose(0,3,1,2) return self.y # In[10] conv = Conv(3,2,3,1,0) conv.forward(x)