def _convert_conv2d(converter: KerasConverter, k_op: "keras.layers.Conv2D"):
x = converter.get_variable(converter.get_input_tensor(k_op)[0])
check_data_format(x, k_op.data_format)
w = converter.convert_to_constant_variable(
k_op.kernel, Order([Axis.KH, Axis.KW, Axis.C, Axis.N]))
ksize = tuple(k_op.kernel_size)
stride = tuple(k_op.strides)
dilation_rate = tuple(k_op.dilation_rate)
padding = (parse_padding(k_op.padding, ksize[0], dilation_rate[0]),
parse_padding(k_op.padding, ksize[1], dilation_rate[1]))
y, = Convolution2D(None,
ksize=ksize,
stride=stride,
padding=padding,
dilation_rate=dilation_rate)(x, w)
if k_op.use_bias:
b = converter.convert_to_constant_variable(k_op.bias, OrderC)
y = y + b
y = do_activation(k_op.activation, y)
converter.set_variable(converter.get_output_tensor(k_op)[0], y)
def _convert_conv2d_transpose(converter: KerasConverter,
k_op: "keras.layers.Conv2DTranspose"):
x = converter.get_variable(converter.get_input_tensor(k_op)[0])
check_data_format(x, k_op.data_format)
w = converter.convert_to_constant_variable(
k_op.kernel, Order([Axis.KH, Axis.KW, Axis.N, Axis.C]))
ksize = tuple(k_op.kernel_size)
stride = tuple(k_op.strides)
dilation_rate = tuple(k_op.dilation_rate)
if dilation_rate != (1, 1):
raise NotImplementedError(
"[KerasConverter] keras.layers.Convolution2DTranspose with large dilation_rate is not supported"
)
padding = (parse_padding(k_op.padding, ksize[0], dilation_rate[0]),
parse_padding(k_op.padding, ksize[1], dilation_rate[1]))
y, = Deconvolution2D(None, ksize=ksize, stride=stride, padding=padding)(x,
w)
if k_op.use_bias:
b = converter.convert_to_constant_variable(k_op.bias, OrderC)
y = y + b
y = do_activation(k_op.activation, y)
converter.set_variable(converter.get_output_tensor(k_op)[0], y)
def _convert_max_pooling2d(converter: KerasConverter,
k_op: "keras.layers.MaxPooling2D"):
x = converter.get_variable(converter.get_input_tensor(k_op)[0])
check_data_format(x, k_op.data_format)
ksize = tuple(k_op.pool_size)
stride = tuple(k_op.strides)
padding = (parse_padding(k_op.padding, ksize[0],
1), parse_padding(k_op.padding, ksize[1], 1))
y, = MaxPooling2D(None, ksize=ksize, stride=stride, padding=padding)(x)
converter.set_variable(converter.get_output_tensor(k_op)[0], y)
def _convert_global_max_pooling2d(converter: KerasConverter,
k_op: "keras.layers.GlobalMaxPooling2D"):
x = converter.get_variable(converter.get_input_tensor(k_op)[0])
check_data_format(x, k_op.data_format)
y, = MaxPooling2D(None,
ksize=(x.shape_dict[Axis.H], x.shape_dict[Axis.W]),
stride=(1, 1),
padding=(0, 0))(x)
# flatten without changing memory layout
z = y.reshape([y.shape[0], mul(y.shape[1:])], OrderNC)
converter.set_variable(converter.get_output_tensor(k_op)[0], z)
def _convert_max_pooling2d(converter: KerasConverter,
k_op: "keras.layers.AveragePooling2D"):
x = converter.get_variable(converter.get_input_tensor(k_op)[0])
check_data_format(x, k_op.data_format)
ksize = tuple(k_op.pool_size)
stride = tuple(k_op.strides)
padding = (parse_padding(k_op.padding, ksize[0],
1), parse_padding(k_op.padding, ksize[1], 1))
if k_op.padding == "same":
console.warning(
"[KerasConverter] keras.layers.AveragePooling computes average by dividing number of valid elements in window "
"(without padding element), but WebDNN divides it by the number of elements including padding element, so different "
"result will be generated on the edge.")
y, = AveragePooling2D(None, ksize=ksize, stride=stride, padding=padding)(x)
converter.set_variable(converter.get_output_tensor(k_op)[0], y)
def _convert_zero_padding2d(converter: KerasConverter,
k_op: "keras.layers.ZeroPadding2D"):
x = converter.get_variable(converter.get_input_tensor(k_op)[0])
check_data_format(x, k_op.data_format)
padding = k_op.padding
top = padding[0][0]
if top != padding[0][1]:
# FIXME: This condition should be checked in each backend
raise NotImplementedError(
"[KerasConverter] In current implementation, Padding size of top and bottom must be same."
)
left = padding[1][0]
if left != padding[1][1]:
# FIXME: This condition should be checked in each backend
raise NotImplementedError(
"[KerasConverter] In current implementation, Padding size of left and right must be same."
)
y, = ZeroPadding2D(None, (top, left))(x)
converter.set_variable(converter.get_output_tensor(k_op)[0], y)
def _convert_separable_conv2d(converter: KerasConverter,
k_op: "keras.layers.SeparableConv2D"):
x = converter.get_variable(converter.get_input_tensor(k_op)[0])
check_data_format(x, k_op.data_format)
axis_c_in = Axis.C
axis_c_out = Axis()
axis_depth_multiplier = Axis()
w_depthwise = converter.convert_to_constant_variable(
k_op.depthwise_kernel,
Order([Axis.KH, Axis.KW, axis_c_in, axis_depth_multiplier]))
w_pointwise = converter.convert_to_constant_variable(
k_op.pointwise_kernel, Order([Axis.KH, Axis.KW, axis_c_in,
axis_c_out]))
w_pointwise = w_pointwise.reshape(
shape=[
x.shape_dict[axis_c_in], k_op.depth_multiplier,
w_pointwise.shape_dict[axis_c_out]
],
order=Order([axis_c_in, axis_depth_multiplier, axis_c_out]))
ksize = tuple(k_op.kernel_size)
stride = tuple(k_op.strides)
dilation_rate = tuple(k_op.dilation_rate)
padding = (parse_padding(k_op.padding, ksize[0], dilation_rate[0]),
parse_padding(k_op.padding, ksize[1], dilation_rate[1]))
h, = Im2Col(None,
ksize=ksize,
stride=stride,
padding=padding,
dilation_rate=dilation_rate)(x)
# TODO: Support depth-wise convolution natively
# Currently, depth-wise convolution is not supported natively, and emulated by composition of small convolution operations.
ys = []
for i in range(h.shape_dict[axis_c_in]):
# 1. Depthwise convolution
#
# Ideal | Current implementation
# ----------------------------------+----------------------------------------------------
# h.axes=[N, H, W, KH, KW, C_in] | g_sub.axes=[N, H, W, KH, KW]
# w.axes=[KH, KW, C_in, DM] | w_sub.axes=[KH, KW, DM]
# g.axes=[N, H, W, C_in, DM] | g_sub.axes=[N, H, W, DM]
h_sub, = Slice(
None,
indices=AxisKeyDict(
h.order.axes,
[i if a == axis_c_in else slice(None)
for a in h.order.axes]))(h)
w_depthwise_sub = w_depthwise[:, :, i, :]
g_sub, = Tensordot(None, axes=((Axis.KH, Axis.KW),
(Axis.KH, Axis.KW)))(h_sub,
w_depthwise_sub)
# 2. Pointwise (projection) convolution
#
# Ideal | Current implementation
# ----------------------------------+----------------------------------------------------
# g.axes=[N, H, W, C_in, DM] | g_sub.axes=[N, H, W, DM]
# w.axes=[DM, Cin, C_out] | w_sub.axes=[DM, C_out]
# y.axes=[N, H, W, C_out] | y_sub.axes=[N, H, W, C_out]
w_pointwise_sub = w_pointwise[i, :, :]
y_sub, = Tensordot(None,
axes=((axis_depth_multiplier, ),
(axis_depth_multiplier, )))(g_sub,
w_pointwise_sub)
ys.append(y_sub)
# Sum up all sub convolution results to one
while len(ys) > 1:
ys.append(ys.pop(0) + ys.pop(0))
y = ys[0]
# reinterpret axis "C_out" as C
axes = list(y.order.axes)
i = axes.index(axis_c_out)
axes.pop(i)
axes.insert(i, Axis.C)
y = y.reinterpret_axes(Order(axes))
if k_op.data_format == "channels_last":
y = y.transpose(OrderNHWC)
elif k_op.data_format == "channels_first":
y = y.transpose(OrderNCHW)
else:
raise NotImplementedError(
f"[KerasConverter] Unknown data format: {data_format}")
if k_op.use_bias:
b = converter.convert_to_constant_variable(k_op.bias, OrderC)
y = y + b
y = do_activation(k_op.activation, y)
converter.set_variable(converter.get_output_tensor(k_op)[0], y)