def pooling_simple(x, kernel_size, stride=1, pad=0):
x = as_variable(x)
N, C, H, W = x.shape
KH, KW = pair(kernel_size)
PH, PW = pair(pad)
SH, SW = pair(stride)
OH = get_conv_outsize(H, KH, SH, PH)
OW = get_conv_outsize(W, KW, SW, PW)
col = im2col(x, kernel_size, stride, pad, to_matrix=True)
col = col.reshape(-1, KH * KW)
y = col.max(axis=1)
y = y.reshape(N, OH, OW, C).transpose(0, 3, 1, 2)
return y
def conv2d_simple(x, W, b=None, stride=1, pad=0):
x, W = as_variable(x), as_variable(W)
Weight = W # Width의 'W'와 헷깔리지 않기 위함
N, C, H, W = x.shape
OC, C, KH, KW = Weight.shape
SH, SW = pair(stride)
PH, PW = pair(pad)
OH = get_conv_outsize(H, KH, SH, PH)
OW = get_conv_outsize(W, KW, SW, PW)
col = im2col(x, (KH, KW), stride, pad, to_matrix=True)
Weight = Weight.reshape(OC, -1).transpose()
t = linear(col, Weight, b)
y = t.reshape(N, OH, OW, OC).transpose(0, 3, 1, 2)
return y
def col2im_array(col, img_shape, kernel_size, stride, pad, to_matrix=True):
N, C, H, W = img_shape
KH, KW = pair(kernel_size)
SH, SW = pair(stride)
PH, PW = pair(pad)
OH = get_conv_outsize(H, KH, SH, PH)
OW = get_conv_outsize(W, KW, SW, PW)
if to_matrix:
col = col.reshape(N, OH, OW, C, KH, KW).transpose(0, 3, 4, 5, 1, 2)
img = np.zeros((N, C, H + 2 * PH + SH - 1, W + 2 * PW + SW - 1),
dtype=col.dtype)
for j in range(KH):
j_lim = j + SH * OH
for i in range(KW):
i_lim = i + SW * OW
img[:, :, j:j_lim:SH, i:i_lim:SW] += col[:, :, j, i, :, :]
return img[:, :, PH:H + PH, PW:W + PW]
def im2col_array(img, kernel_size, stride, pad, to_matrix=True):
N, C, H, W = img.shape
KH, KW = pair(kernel_size)
SH, SW = pair(stride)
PH, PW = pair(pad)
OH = get_conv_outsize(H, KH, SH, PH)
OW = get_conv_outsize(W, KW, SW, PW)
img = np.pad(img,
((0, 0), (0, 0), (PH, PH + SH - 1), (PW, PW + SW - 1)),
mode='constant', constant_values=(0,))
col = np.ndarray((N, C, KH, KW, OH, OW), dtype=img.dtype)
for j in range(KH):
j_lim = j + SH * OH
for i in range(KW):
i_lim = i + SW * OW
col[:, :, j, i, :, :] = img[:, :, j:j_lim:SH, i:i_lim:SW]
if to_matrix:
col = col.transpose((0, 4, 5, 1, 2, 3)).reshape((N * OH * OW, -1))
return col
def _init_W(self):
C, OC = self.in_channels, self.out_channels
KH, KW = pair(self.kernel_size)
scale = np.sqrt(1 / (C(KH * KW)))
W_data = np.random.randn(OC, C, KH, KW).astype(self.dtype) * scale
self.W.data = W_data