def _forward_grouped_convolution(self, x, gy):
# G: group count
# N: batch size
# kH, kW: kernel height, kernel width
# iC, iH, iW: input channels, input height, input width
# oC, oH, oW: output channels, output height, output width
G = self.groups
N, iC, iH, iW = x.shape
_, oC, oH, oW = gy.shape # _ == N
kH = self.kh
kW = self.kw
iCg = iC // G
oCg = oC // G
# (N, iC, kH, kW, oH, oW)
x = conv.im2col(x, kH, kW, self.sy, self.sx, self.ph, self.pw,
cover_all=self.cover_all, dy=self.dy, dx=self.dx)
x = x.transpose(1, 2, 3, 0, 4, 5) # (iC, kH, kW, N, oH, oW)
x = x.reshape(G, iCg * kH * kW, N * oH * oW)
x = x.transpose(0, 2, 1) # (G, N*oH*oW, iCg*kH*kW)
gy = gy.transpose(1, 0, 2, 3) # (oC, N, oH, oW)
gy = gy.reshape(G, oCg, N * oH * oW)
# (G, oCg, iCg*kH*kW) = (G, oCg, N*oH*oW) @ (G, N*oH*oW, iCg*kH*kW)
gW = _matmul(gy, x).astype(self.W_dtype, copy=False)
gW = gW.reshape(oC, iCg, kH, kW)
return gW,
def _forward_grouped_convolution(self, x, W, b):
# G: group count
# N: batch size
# kH, kW: kernel height, kernel width
# iC, iH, iW: input channels, input height, input width
# oC, oH, oW: output channels, output height, output width
G = self.groups
N, iC, iH, iW = x.shape
oC, _, kH, kW = W.shape # _ == iCg
iCg = iC // G
oCg = oC // G
# (N, iC, kW, kW, oH, oW)
x = conv.im2col(x, kH, kW, self.sy, self.sx, self.ph, self.pw,
cover_all=self.cover_all, dy=self.dy, dx=self.dx)
oH, oW = x.shape[-2:]
x = x.transpose(1, 2, 3, 0, 4, 5) # (iC, kH, kW, N, oH, oW)
x = x.reshape(G, iCg * kH * kW, N * oH * oW)
W = W.reshape(G, oCg, iCg * kH * kW)
# (G, oCg, N*oH*oW) = (G, oCg, iCg*kH*kW) @ (G, iCg*kH*kW, N*oH*oW)
y = _matmul(W, x).astype(x.dtype, copy=False)
y = y.reshape(oC, N, oH, oW)
y = y.transpose(1, 0, 2, 3) # (N, oC, oH, oW)
if b is not None:
y += b.reshape(1, b.size, 1, 1)
return y,
def _forward_grouped_convolution(self, x, gy):
# G: group count
# N: batch size
# kH, kW: kernel height, kernel width
# iC, iH, iW: input channels, input height, input width
# oC, oH, oW: output channels, output height, output width
G = self.groups
N, iC, iH, iW = x.shape
_, oC, oH, oW = gy.shape # _ == N
kH = self.kh
kW = self.kw
iCg = iC // G
oCg = oC // G
# (N, iC, kH, kW, oH, oW)
x = conv.im2col(x, kH, kW, self.sy, self.sx, self.ph, self.pw,
cover_all=self.cover_all, dy=self.dy, dx=self.dx)
x = x.transpose(1, 2, 3, 0, 4, 5) # (iC, kH, kW, N, oH, oW)
x = x.reshape(G, iCg * kH * kW, N * oH * oW)
x = x.transpose(0, 2, 1) # (G, N*oH*oW, iCg*kH*kW)
gy = gy.transpose(1, 0, 2, 3) # (oC, N, oH, oW)
gy = gy.reshape(G, oCg, N * oH * oW)
# (G, oCg, iCg*kH*kW) = (G, oCg, N*oH*oW) @ (G, N*oH*oW, iCg*kH*kW)
gW = _matmul(gy, x).astype(self.W_dtype, copy=False)
gW = gW.reshape(oC, iCg, kH, kW)
return gW,
def _forward_grouped_convolution(self, x, W, b):
# G: group count
# N: batch size
# kH, kW: kernel height, kernel width
# iC, iH, iW: input channels, input height, input width
# oC, oH, oW: output channels, output height, output width
G = self.groups
N, iC, iH, iW = x.shape
oC, _, kH, kW = W.shape # _ == iCg
iCg = iC // G
oCg = oC // G
# (N, iC, kW, kW, oH, oW)
x = conv.im2col(x, kH, kW, self.sy, self.sx, self.ph, self.pw,
cover_all=self.cover_all, dy=self.dy, dx=self.dx)
oH, oW = x.shape[-2:]
x = x.transpose(1, 2, 3, 0, 4, 5) # (iC, kH, kW, N, oH, oW)
x = x.reshape(G, iCg * kH * kW, N * oH * oW)
W = W.reshape(G, oCg, iCg * kH * kW)
# (G, oCg, N*oH*oW) = (G, oCg, iCg*kH*kW) @ (G, iCg*kH*kW, N*oH*oW)
y = _matmul(W, x).astype(x.dtype, copy=False)
y = y.reshape(oC, N, oH, oW)
y = y.transpose(1, 0, 2, 3) # (N, oC, oH, oW)
if b is not None:
y += b.reshape(1, b.size, 1, 1)
return y,
def check_im2col(self, kh, kw, sy, sx, ph, pw, dy, dx, gpu):
if gpu:
img = cuda.to_gpu(self.img)
else:
img = self.img
col = conv.im2col(img, kh, kw, sy, sx, ph, pw, dy=dy, dx=dx)
col_h = conv.get_conv_outsize(self.h, kh, sy, ph, d=dy)
col_w = conv.get_conv_outsize(self.w, kw, sx, pw, d=dx)
self.assertEqual(col.shape, (2, 3, kh, kw, col_h, col_w))
col = cuda.to_cpu(col)
for y in moves.range(col_h):
for x in moves.range(col_w):
for ky in moves.range(kh):
for kx in moves.range(kw):
oy = y * sy - ph + ky * dy
ox = x * sx - pw + kx * dx
if 0 <= oy < self.h and 0 <= ox < self.w:
testing.assert_allclose(
col[:, :, ky, kx, y, x],
self.img[:, :, oy, ox])
else:
testing.assert_allclose(
col[:, :, ky, kx, y, x],
numpy.zeros((2, 3), self.dtype))
def check_im2col(self, kh, kw, sy, sx, ph, pw, dy, dx, gpu):
if gpu:
img = cuda.to_gpu(self.img)
else:
img = self.img
col = conv.im2col(img, kh, kw, sy, sx, ph, pw, dy=dy, dx=dx)
col_h = conv.get_conv_outsize(self.h, kh, sy, ph, d=dy)
col_w = conv.get_conv_outsize(self.w, kw, sx, pw, d=dx)
self.assertEqual(col.shape, (2, 3, kh, kw, col_h, col_w))
col = cuda.to_cpu(col)
for y in moves.range(col_h):
for x in moves.range(col_w):
for ky in moves.range(kh):
for kx in moves.range(kw):
oy = y * sy - ph + ky * dy
ox = x * sx - pw + kx * dx
if 0 <= oy < self.h and 0 <= ox < self.w:
testing.assert_allclose(col[:, :, ky, kx, y, x],
self.img[:, :, oy, ox])
else:
testing.assert_allclose(
col[:, :, ky, kx, y, x],
numpy.zeros((2, 3), self.dtype))
