def calc_pad_dim(cls, node, expected_len):
if "auto_pad" not in node.attrs or node.attrs["auto_pad"] == "NOTSET":
pad_dim = PadDim(*cls.mix_pads(node.attrs.get("pads", [])))
elif node.attrs["auto_pad"] == "VALID":
pad_dim = PadDim.valid()
elif node.attrs["auto_pad"] == "SAME_UPPER":
pad_dim = PadDim.same(same_type="balanced_left")
elif node.attrs["auto_pad"] == "SAME_LOWER":
pad_dim = PadDim.same(same_type="balanced_right")
else:
raise ValueError("bad pad type")
return pad_dim
def calc_pad_dim(cls, node, spatial_size):
pads = cls.pad_start_with(node.attrs.get("pads", [0, 0] * spatial_size), [0, 0], 2)
if "auto_pad" not in node.attrs or node.attrs["auto_pad"] == "NOTSET":
pad_dim = PadDim(*pads)
elif node.attrs["auto_pad"] == "VALID":
pad_dim = PadDim.valid()
elif node.attrs["auto_pad"] == "SAME_UPPER":
pad_dim = PadDim.same(same_type="balanced_left")
elif node.attrs["auto_pad"] == "SAME_LOWER":
pad_dim = PadDim.same(same_type="balanced_right")
else:
raise ValueError("bad pad type")
return pad_dim
def test_paddim():
dim1 = PadDim(1)
assert not dim1.is_same
assert dim1.h == 2 and dim1.w == 2
assert dim1.l == 1 and dim1.r == 1 and dim1.t == 1 and dim1.b == 1
assert dim1.numpy_pad_shape(Dim.named_ordered(w=10, h=10)) == [(1, 1), (1, 1)]
stride_dim = StrideDim(1)
filt_dim = Conv2DFilterDim(5, 5, 1, 1)
in_dim = Dim.named_ordered(c=1, h=20, w=20)
dim1 = PadDim.same()
dim1.calculate_same(in_dim, filt_dim, stride_dim)
assert dim1.shape == [2, 2, 2, 2]
def test_conf2d_pad_dilate():
weights = np.arange(9).reshape([1, 1, 3, 3])
filt = Conv2DFilterDim(3, 3, 1, 1)
stride = StrideDim(1)
pad = PadDim.same()
dilation = DilationDim(2)
params = Conv2DParameters("test",
filt=filt,
stride=stride,
padding=pad,
dilation=dilation,
in_dims_hint=[['c', 'h', 'w']],
out_dims_hint=[['c', 'h', 'w']])
input_ = np.arange(16).reshape([1, 4, 4])
in_dims = Dim.named(c=1, h=4, w=4).impose_order(['c', 'h', 'w'])
out_dims = params.get_output_size([in_dims])
output_ = conv2d(params, in_dims, out_dims[0], input_, weights, None, None)
assert np.array_equal(output_, [[[266., 206.], [98., 66.]]])
def test_conf2d_pad():
weights = np.arange(9).reshape([1, 1, 3, 3])
filt = Conv2DFilterDim(3, 3, 1, 1)
stride = StrideDim(1)
pad = PadDim.same()
dilation = DilationDim(1)
params = Conv2DParameters("test",
filt=filt,
stride=stride,
padding=pad,
dilation=dilation,
in_dims_hint=[['c', 'h', 'w']],
out_dims_hint=[['c', 'h', 'w']])
input_ = np.arange(16).reshape([1, 4, 4])
in_dims = Dim.named(c=1, h=4, w=4).impose_order(['c', 'h', 'w'])
out_dims = params.get_output_size([in_dims])
output_ = conv2d(params, in_dims, out_dims[0], input_, weights, None)
assert np.array_equal(output_, [[[73, 121, 154, 103], [171, 258, 294, 186],\
[279, 402, 438, 270], [139, 187, 202, 113]]])
def get_tf_padding(padding):
if padding == Padding.Padding.SAME:
return PadDim.same()
if padding == Padding.Padding.VALID:
return PadDim.valid()
raise ValueError("Strange padding type")
