def _common(cls, node: TFLiteNode, **kwargs):
custom_opts = node.get_custom_options()
G = kwargs['G']
opts = kwargs['opts']
all_nodes = kwargs['all_nodes']
importer = kwargs['importer']
inputs = [all_nodes[t] for t in node.input]
outputs = [
all_nodes.get(node.output[idx]) if idx < len(node.output) else None
for idx in range(4)
]
# inp_shapes = [input[2].shape for input in inputs]
if 'max_bb_before_nms' not in custom_opts:
custom_opts['max_bb_before_nms'] = 300
params = SSDDetectorParameters(node.name, parameters=custom_opts)
overriden_outputs = []
for idx, output in enumerate(outputs):
if output:
overriden_outputs.append(node.output[idx])
continue
oparams = G.add_output()
otensor = TensorBase("Detect_%s" % idx)
overriden_outputs.append(otensor)
importer.provisional_outputs[otensor] = (oparams, 0, None)
# covers the case where not all outputs are generated by the conversion tool
node.override_outputs(overriden_outputs)
for idx, inp in enumerate(inputs):
G.add_edge(
NNEdge(from_node=inp[0],
to_node=params,
from_idx=inp[1],
to_idx=idx))
if opts.get('load_quantization'):
in_qtypes = [
QType.from_min_max_sq(tensor.qtype.min_val,
tensor.qtype.max_val) if
(tensor.qtype.is_asymmetric
or not tensor.qtype.signed) else tensor.qtype
for tensor in node.input
]
o_boxes_qtype = QType(min_val=-2,
max_val=2,
dtype=np.int16,
scale=2**(-14))
o_scores_qtype = node.input[1].qtype
o_class_qtype = QType(scale=1, dtype=np.int8)
qrec = QRec.scaled(in_qs=in_qtypes,
out_qs=[
o_boxes_qtype, o_class_qtype,
o_scores_qtype, o_class_qtype
])
G.quantization[NodeId(params)] = qrec
return params
def _common(cls, node: TFLiteNode, **kwargs):
node_opts = node.get_options(ReshapeOptions)
G = kwargs['G']
opts = kwargs['opts']
all_nodes = kwargs['all_nodes']
inputs = [all_nodes[t] for t in node.input]
x = inputs[0]
x_shape = x[2].shape
# TF2 seems to use the second input whereas TF1 uses the opts
new_shape = None
if node_opts:
new_shape = list(node_opts.NewShapeAsNumpy())
elif len(inputs) > 1:
set_shape_tensor = list(cls._verify_constant(inputs[1]))
node.input[1].used = True
new_shape = list(set_shape_tensor)
else:
ValueError(
f"Cannot asses new_shape for Reshape Parameter: {node.name}")
if -1 in new_shape:
new_shape_size = reduce(lambda x, y: x * 1
if y == -1 else x * y, new_shape, 1)
inp_size = reduce(lambda x, y: x * y
if y is not None else x, x_shape, 1)
new_shape[new_shape.index(-1)] = inp_size // new_shape_size
if None in x_shape:
if 1 in new_shape:
old_batch_dim = x_shape.index(None)
new_batch_dim = new_shape.index(1)
if old_batch_dim != new_batch_dim:
LOG.info(
"node %s moved batch dimension for axis %s to axis %s",
node.name, old_batch_dim, new_batch_dim)
new_shape[new_batch_dim] = None
else:
raise ValueError(
"unable to determine movement of unspcified axis in node %s"
% node.name)
pnew_shape = ProvisionalDim(new_shape)
old_shape = Dim.unnamed(cls.remove_unspecified_dim(x_shape),
is_ordered=True)
new_shape = Dim.unnamed(cls.remove_unspecified_dim(new_shape),
is_ordered=True)
params = ReshapeParameters(node.name,
old_shape=old_shape,
shape=new_shape)
if opts.get('load_quantization'):
G.quantization[NodeId(params)] = cls.load_tf_quantization(
[node.input[0]], node.output)
G.add_edge(
NNEdge(from_node=x[0], to_node=params, from_idx=x[1], to_idx=0))
all_nodes[node.output[0]] = (params, 0, pnew_shape)
return params
def _common(cls, node: TFLiteNode, **kwargs):
node_opts = node.get_options(CastOptions)
G = kwargs['G']
all_nodes = kwargs['all_nodes']
inputs = [all_nodes[t] for t in node.input]
x = inputs[0]
if node_opts:
in_dtype = TFLiteTensorWrapper.TF_TO_NUMPY_TYPE[
node_opts.InDataType()]
out_dtype = TFLiteTensorWrapper.TF_TO_NUMPY_TYPE[
node_opts.OutDataType()]
else:
in_dtype = out_dtype = None
if cls.is_constant(x):
LOG.info("reducing %s to a constant", node.name)
val = cls.get_constant(x)
if out_dtype:
val = val.astype(out_dtype)
params = ConstantInputParameters(node.name, value=val)
else:
params = CastParameters(node.name,
in_dtype=in_dtype,
out_dtype=out_dtype)
G.add_edge(
NNEdge(from_node=x[0], to_node=params, from_idx=x[1],
to_idx=0))
all_nodes[node.output[0]] = (params, 0, deepcopy(x[2]))
return params
def version_1(cls, node: TFLiteNode, **kwargs):
node_opts = node.get_options(TransposeConvOptions)
G = kwargs['G']
opts = kwargs['opts']
all_nodes = kwargs['all_nodes']
inputs = [all_nodes[t] for t in node.input]
x = inputs[2]
x_shape = x[2].shape
in_b, in_h, in_w, in_c = tuple(x_shape)
pout_shape = [
dim if x_shape[idx] is not None else None
for idx, dim in enumerate(cls.get_constant(inputs[0]))
]
out_b, out_h, out_w, out_c = tuple(pout_shape)
filt = inputs[1]
weights_node = filt[0]
filt_shape = filt[2].shape
# # ['in_c', 'h', 'w', 'out_c']
filt_out_c, filt_h, filt_w, filt_in_c = tuple(filt_shape)
filt_dim = Conv2DFilterDim(filt_h, filt_w, filt_out_c, in_c=filt_in_c)
filt_dim = filt_dim.impose_order(cls.TF_LITE_FILTER_ORDER)
stride_w = node_opts.StrideW()
stride_h = node_opts.StrideH()
# compute padding
pad = node_opts.Padding()
if pad == Padding.SAME:
pad_h = ((in_h - 1) * stride_h + filt_h - out_h)
pad_w = ((in_w - 1) * stride_w + filt_w - out_w)
pad_top = pad_h // 2
pad_left = pad_w // 2
pad = PadDim(pad_top,
pad_h - pad_top,
pad_left,
pad_w - pad_left,
same_type='balanced_right')
else:
pad = PadDim(0)
params = TransposeConv2DParameters(
node.name,
filt=filt_dim,
stride=StrideDim(stride_h, stride_w),
padding=pad,
in_dims_hint=[['h', 'w', 'c'],
cls.TF_LITE_FILTER_ORDER.copy()],
out_dims_hint=[['h', 'w', 'c']])
G.add_edge(
NNEdge(from_node=x[0], to_node=params, from_idx=x[1], to_idx=0))
G.add_edge(NNEdge(from_node=weights_node, to_node=params, to_idx=1))
pout_dims = ProvisionalDim(pout_shape)
all_nodes[node.output[0]] = (params, 0, pout_dims)
return params
def _common(cls, node: TFLiteNode, **kwargs):
node_opts = node.get_options(StridedSliceOptions)
G = kwargs['G']
opts = kwargs['opts']
all_nodes = kwargs['all_nodes']
inputs = [all_nodes[t] for t in node.input]
x = inputs[0]
x_shape = x[2].shape
# begin end stride
vec_begin = list(cls._verify_constant(inputs[1]))
vec_end = list(cls._verify_constant(inputs[2]))
vec_stride = list(cls._verify_constant(inputs[3]))
for i in range(1, 4):
node.input[i].used = True
if any([vec is None for vec in [vec_begin, vec_end, vec_stride]]):
raise NotImplementedError(
"strided slice with variable begin end or stride is not supported")
spec = zip(vec_begin, vec_end, vec_stride)
begin_mask = node_opts.BeginMask()
ellipsis_mask = node_opts.EllipsisMask()
end_mask = node_opts.EndMask()
new_axis_mask = node_opts.NewAxisMask()
shrink_axis_mask = node_opts.ShrinkAxisMask()
act_slice, out_shape, can_reshape = StridedSliceParameters.get_slice(
x_shape, spec,
begin_mask,
end_mask, ellipsis_mask,
new_axis_mask, shrink_axis_mask)
if cls.is_constant(x):
LOG.info("reducing %s to a constant", node.name)
x_val = cls.get_constant(x)
params = StridedSliceParameters(node.name, act_slice=act_slice, out_shape=out_shape)
x_val = params.numpy_slice(x_val)
params = ConstantInputParameters(node.name, value=x_val)
else:
if can_reshape:
if list(x_shape) == list(out_shape):
LOG.info("converting strided slice %s to a noop", node.name)
params = NoOPParameters(node.name)
else:
LOG.info("converting strided slice %s to a reshape", node.name)
in_shape = Dim.unnamed(x[2].known_shape, is_ordered=True)
out_shape = Dim.unnamed(out_shape, is_ordered=True)
params = ReshapeParameters(node.name, old_shape=in_shape, shape=out_shape)
else:
params = StridedSliceParameters(node.name, act_slice=act_slice, out_shape=out_shape)
G.add_edge(NNEdge(from_node=x[0], to_node=params, from_idx=x[1], to_idx=0))
if opts.get('load_quantization'):
G.quantization[NodeId(params)] = cls.load_tf_quantization([node.input[0]], node.output)
all_nodes[node.output[0]] = (params, 0, x[2].infer_mapping(out_shape, allow_bad_length=True))
return params
def _common(cls, node: TFLiteNode, **kwargs):
node_opts = node.get_options(ConcatenationOptions)
G = kwargs['G']
opts = kwargs['opts']
all_nodes = kwargs['all_nodes']
inputs = [all_nodes[t] for t in node.input]
inp_shapes = [input[2].shape for input in inputs]
buffer_idxes = [tensor.buffer_idx for tensor in node.input]
non_zero_idxes = [idx for idx in buffer_idxes if idx != 0]
if len(set(non_zero_idxes)) != len(non_zero_idxes):
raise NotImplementedError(
"concats with multiple versions of the same input are not supported. "
"This is normally a graph design problem.")
axis = node_opts.Axis()
if any(inp_shape[axis] is None for inp_shape in inp_shapes):
raise ValueError("concat on undefined axis in node %s" % node.name)
def red_func(x, y):
return y.copy() if x is None else [
(elem if y[idx] is not None and elem is not None else None)
if idx != axis else elem + y[axis]
for idx, elem in enumerate(x)
]
pout_shape = reduce(red_func, inp_shapes)
if all(cls.is_constant(inp) for inp in inputs):
# cls.remove_none_from_constants(inputs, pout_shape)
LOG.info("reducing %s to a constant", node.name)
value = np.concatenate([cls.get_constant(inp) for inp in inputs],
axis=axis)
params = ConstantInputParameters(node.name,
value=value,
constant_store=G.constant_store)
else:
axis -= sum(1 if dim is None else 0 for dim in pout_shape[:axis:])
params = ConcatParameters(node.name, axis=axis, axis_hint=None)
for idx, inp in enumerate(inputs):
inp_node, inp_idx = cls._maybe_insert_reshape(
G, inp, inp_shapes[idx], pout_shape)
G.add_edge(
NNEdge(from_node=inp_node,
to_node=params,
from_idx=inp_idx,
to_idx=idx))
if opts.get('load_quantization'):
G.quantization[NodeId(params)] = cls.load_tf_quantization(
node.input, node.output)
cls.fuse_activation(node_opts, node.name, params, **kwargs)
all_nodes[node.output[0]] = (params, 0, ProvisionalDim(pout_shape))
return params
def __init__(self, model: Model, subgraph: SubGraph,
subgraph_idx: int) -> None:
self._model = model
self._subgraph = subgraph
self._subgraph_idx = subgraph_idx
self._tensors = [
TFLiteTensorWrapper(self._subgraph.Tensors(idx), self._model)
for idx in range(self._subgraph.TensorsLength())
]
self._nodes = [
TFLiteNode(self._subgraph.Operators(idx), idx, self._model, self)
for idx in range(self._subgraph.OperatorsLength())
]
def _common(cls, node: TFLiteNode, **kwargs):
node_opts = node.get_options(GatherOptions)
G = kwargs['G']
opts = kwargs['opts']
all_nodes = kwargs['all_nodes']
inputs = [all_nodes[t] for t in node.input]
x = inputs[0]
x_shape = x[2].shape
gather_tensor = list(cls._verify_constant(inputs[1]))
axis = node_opts.Axis()
if cls._is_constant(x):
inp = cls._get_constant(x)
inp = np.take(inp, gather_tensor, axis=axis)
pout_shape = inp.shape
LOG.info("reducing %s to a constant", node.name)
params = ConstantInputParameters(node.name,
value=inp,
dims=pout_shape)
else:
if x_shape[axis] is None:
raise ValueError(
f'GATHER {node.name} on batch axis not supported')
slices = [sequence_to_slice(elem) for elem in gather_tensor]
strides = set([
slices[idx + 1][0] - slice[0]
for idx, slice in enumerate(slices[:-1:])
])
lengths = set([abs(slice[1] - slice[0]) for slice in slices])
if len(strides) != 1 or len(lengths) != 1:
raise ValueError(f'Irregular GATHER {node.name} not supported')
out_len = sum(len(slice) for slice in slices)
pout_shape = x_shape.copy()
pout_shape[axis] = out_len
axis -= sum(1 if dim is None else 0 for dim in x_shape[:axis:])
LOG.info("reducing %s to an overlapped copy", node.name)
params = GatherParameters(node.name,
indices=gather_tensor,
axis=axis)
if opts.get('load_quantization'):
G.quantization[NodeId(params)] = cls.load_tf_quantization(
node.input, node.output)
all_nodes[node.output[0]] = (params, 0, ProvisionalDim(pout_shape))
return params
def _common(cls, node: TFLiteNode, **kwargs):
node_opts = node.get_options(CastOptions)
G = kwargs['G']
all_nodes = kwargs['all_nodes']
inputs = [all_nodes[t] for t in node.input]
x = inputs[0]
if node_opts:
in_qtype = QType(dtype=TFLiteTensorWrapper.TF_TO_NUMPY_TYPE[node_opts.InDataType()])
out_qtype = QType(dtype=TFLiteTensorWrapper.TF_TO_NUMPY_TYPE[node_opts.OutDataType()])
return cls.common_quantize(in_qtype, out_qtype, node, **kwargs)
params = NoOPParameters(node.name, desc='cast with no type information')
G.add_edge(NNEdge(from_node=x[0], to_node=params, from_idx=x[1], to_idx=0))
all_nodes[node.output[0]] = (params, 0, deepcopy(x[2]))
return params
def _common(cls, node: TFLiteNode, **kwargs):
node_opts = node.get_options(SqueezeOptions)
G = kwargs['G']
opts = kwargs['opts']
all_nodes = kwargs['all_nodes']
inputs = [all_nodes[t] for t in node.input]
x = inputs[0]
x_shape = x[2].shape
if node_opts.SqueezeDimsIsNone():
new_shape = [dim for dim in x_shape if dim != 1]
else:
axes = node_opts.SqueezeDimsAsNumpy()
axes = np.where(axes < 0, axes + len(x_shape), axes)
if np.any(np.array(x_shape)[axes] not in [None, 1]):
raise ValueError(f'invalid expand dims > 1 {node.name}')
new_shape = [
dim for idx, dim in enumerate(x_shape) if idx not in axes
]
if cls.is_constant(x):
LOG.info("reducing %s to a constant", node.name)
val = np.reshape(cls.get_constant(x), new_shape)
params = ConstantInputParameters(node.name,
value=val,
dims=Dim.unnamed(val.shape))
else:
pnew_shape = ProvisionalDim(new_shape)
old_shape = Dim.unnamed(cls.remove_unspecified_dim(x_shape),
is_ordered=True)
new_shape = Dim.unnamed(cls.remove_unspecified_dim(new_shape),
is_ordered=True)
params = ReshapeParameters(node.name,
old_shape=old_shape,
shape=new_shape)
if opts.get('load_quantization'):
G.quantization[NodeId(params)] = cls.load_tf_quantization(
[node.input[0]], node.output)
G.add_edge(
NNEdge(from_node=x[0], to_node=params, from_idx=x[1], to_idx=0))
all_nodes[node.output[0]] = (params, 0, pnew_shape)
return params
def __init__(self,
model: Model,
subgraph: SubGraph,
subgraph_idx: int,
name_cache=None,
anonymise=False) -> None:
self._model = model
self._subgraph = subgraph
self._subgraph_idx = subgraph_idx
self._tensors = [
TFLiteTensorWrapper(self._subgraph.Tensors(idx), self._model)
for idx in range(self._subgraph.TensorsLength())
]
self._nodes = [
TFLiteNode(self._subgraph.Operators(idx),
idx,
self._model,
self,
name_cache=name_cache,
anonymise=anonymise)
for idx in range(self._subgraph.OperatorsLength())
]
def _common(cls, node: TFLiteNode, **kwargs):
node_opts = node.get_options(DepthwiseConv2DOptions)
G = kwargs['G']
opts = kwargs['opts']
all_nodes = kwargs['all_nodes']
inputs = [all_nodes[t] for t in node.input]
x = inputs[0]
x = cls.remove_known_batch_dimension(G, x, node)
x_shape = x[2].shape
in_b, h, w, in_c = tuple(x_shape)
filt = inputs[1]
weights_node = filt[0]
filt_shape = filt[2].shape
# ['in_c', 'h', 'w', 'out_c']
filt_in_c, filt_h, filt_w, filt_out_c = tuple(filt_shape)
# get filter dimensions
if filt_h > h or filt_w > w:
LOG.warning(
"Filter %s of shape [%dx%d] is bigger than input of shape [%dx%d]",
node.name, filt_h, filt_w, h, w)
filt_dim = Conv2DFilterDim(filt_h, filt_w, filt_out_c, in_c=filt_in_c)
filt_dim = filt_dim.impose_order(cls.TF_LITE_DW_FILTER_ORDER)
# multiplier should match filter
check(filt_dim.out_c == node_opts.DepthMultiplier() * in_c,
"invalid multiplier")
groups = filt_dim.out_c // node_opts.DepthMultiplier()
# compute padding
pad = cls.get_tf_padding(node_opts.Padding())
# does it have biases
if len(inputs) > 2:
bias = inputs[2]
bias_node = bias[0]
else:
bias_node = ConstantInputParameters(
f'{node.name}_bias',
dims=Dim.unnamed([filt_out_c]),
value=np.zeros([filt_out_c], dtype=np.float32)) # TODO - check
# TFLITE produces single channel input DW convolutions with the
# multiplier equal to the number of out channels. This is just
# a normal convolution and since we don't handle the channel
# multiplier at present (but can) just convert them to normal
# convolutions
convert_to_conv = in_c == 1 and groups == 1
if convert_to_conv:
filt_dim.impose_order(cls.TF_LITE_FILTER_ORDER)
params = Conv2DParameters(
node.name,
filt=filt_dim,
stride=StrideDim(node_opts.StrideH(), node_opts.StrideW()),
dilation=DilationDim(node_opts.DilationHFactor(),
node_opts.DilationWFactor()),
padding=pad,
has_bias=True,
in_dims_hint=[['h', 'w', 'c'],
cls.TF_LITE_FILTER_ORDER.copy(), ['out_c']],
out_dims_hint=[['h', 'w', 'c']])
else:
filt_dim.impose_order(cls.TF_LITE_DW_FILTER_ORDER)
params = Conv2DParameters(
node.name,
filt=filt_dim,
stride=StrideDim(node_opts.StrideH(), node_opts.StrideW()),
dilation=DilationDim(node_opts.DilationHFactor(),
node_opts.DilationWFactor()),
padding=pad,
groups=groups,
multiplier=node_opts.DepthMultiplier(),
has_bias=True,
tf_depthwise=True,
in_dims_hint=[['h', 'w', 'c'],
cls.TF_LITE_DW_FILTER_ORDER.copy(), ['out_c']],
out_dims_hint=[['h', 'w', 'c']])
G.add_edge(NNEdge(from_node=weights_node, to_node=params, to_idx=1))
G.add_edge(NNEdge(from_node=bias_node, to_node=params, to_idx=2))
cls.new_load_filter_parameters(G,
params,
params.filter.actual_shape,
params.filter.get_order_idx('out_c'),
node.input[0],
weights_node,
bias_node,
node.output[0],
opts,
dw_to_pw=convert_to_conv)
in_dim = Dim.named_ordered(h=h, w=w, c=in_c)
out_dims = params.get_output_size(
[in_dim,
Dim.unnamed(filt_dim.shape),
Dim.unnamed([filt_out_c])])
pout_dims = ProvisionalDim([in_b] + out_dims[0].shape)
G.add_edge(
NNEdge(from_node=x[0], to_node=params, from_idx=x[1], to_idx=0))
params = cls.fuse_activation(node_opts, node.name, params, **kwargs)
all_nodes[node.output[0]] = (params, 0, pout_dims)
return params
def _common(cls, node: TFLiteNode, **kwargs):
node_opts = node.get_options(PackOptions)
G = kwargs['G']
opts = kwargs['opts']
all_nodes = kwargs['all_nodes']
inputs = [all_nodes[t] for t in node.input]
inp_shapes = [input[2].shape for input in inputs]
values_count = node_opts.ValuesCount()
check(
len(inputs) == values_count,
"invalid tflite file - values count not equal to inputs")
buffer_idxes = [tensor.buffer_idx for tensor in node.input]
check(
len(set(buffer_idxes)) == len(buffer_idxes),
"packs with multiple versions of the same input are not supported. This is normally a graph design problem."
)
axis = node_opts.Axis()
dimension_size = len(inp_shapes)
if axis < 0:
axis += dimension_size
check(all(shape == inp_shapes[0] for shape in inp_shapes[1::]),
"invalid tflite file - pack inputs not the same")
# prepare shapes of all tensors
pconcat_out_shape = inp_shapes[0].copy()
pconcat_out_shape.insert(axis, values_count)
pconcat_in_shape = inp_shapes[0].copy()
pconcat_in_shape.insert(axis, 1)
preshape_in_shape = inp_shapes[0].copy()
# remove nones from constants
cls.remove_none_from_constants(inputs, preshape_in_shape)
# remove nones from reshape shapes
reshape_in_shape = cls.remove_unspecified_dim(preshape_in_shape)
concat_in_shape = cls.remove_unspecified_dim(pconcat_in_shape)
if all(cls.is_constant(inp) for inp in inputs):
LOG.info("reducing %s to a constant", node.name)
value = np.stack([cls.get_constant(inp) for inp in inputs],
axis=axis)
params = ConstantInputParameters(node.name,
value=value,
constant_store=G.constant_store)
else:
axis -= sum(1 if dim is None else 0
for dim in pconcat_out_shape[:axis:])
params = ConcatParameters(node.name, axis=axis, axis_hint=None)
# insert reshapes on each input to add concat axis
for idx, inp in enumerate(inputs):
rparams = ReshapeParameters(node.name + "_%s" % idx,
old_shape=reshape_in_shape,
shape=concat_in_shape)
G.add_edge(
NNEdge(from_node=inp[0], to_node=rparams, from_idx=inp[1]))
G.add_edge(NNEdge(from_node=rparams, to_node=params))
if opts.get('load_quantization'):
G.quantization[NodeId(rparams)] = cls.load_tf_quantization(
[node.input[idx]], [node.input[idx]])
if opts.get('load_quantization'):
G.quantization[NodeId(params)] = cls.load_tf_quantization(
node.input, node.output)
all_nodes[node.output[0]] = (params, 0,
ProvisionalDim(pconcat_out_shape))
return params
def version_1(cls, node: TFLiteNode, **kwargs):
node_opts = node.get_options(Conv2DOptions)
G = kwargs['G']
opts = kwargs['opts']
all_nodes = kwargs['all_nodes']
inputs = [all_nodes[t] for t in node.input]
x = inputs[0]
x_shape = x[2].shape
in_b, h, w, in_c = tuple(x_shape)
filt = inputs[1]
weights_node = filt[0]
filt_shape = filt[2].shape
# ['in_c', 'h', 'w', 'out_c']
filt_out_c, filt_h, filt_w, filt_in_c = tuple(filt_shape)
# get filter dimensions
if filt_h > h or filt_w > w:
LOG.warning(
"Filter %s of shape [%dx%d] is bigger than input of shape [%dx%d]",
node.name, filt_h, filt_w, h, w)
filt_dim = Conv2DFilterDim(filt_h, filt_w, filt_out_c, in_c=filt_in_c)
filt_dim = filt_dim.impose_order(cls.TF_LITE_FILTER_ORDER)
# compute padding
pad = cls.get_tf_padding(node_opts.Padding())
# does it have biases
if len(inputs) > 2:
bias = inputs[2]
bias_node = bias[0]
else:
bias_node = ConstantInputParameters(
f'{node.name}_bias',
dims=Dim.unnamed([filt_out_c]),
value=np.zeros([filt_out_c], dtype=np.float32)) # TODO - check
params = Conv2DParameters(
node.name,
filt=filt_dim,
stride=StrideDim(node_opts.StrideH(), node_opts.StrideW()),
dilation=DilationDim(node_opts.DilationHFactor(),
node_opts.DilationWFactor()),
padding=pad,
has_bias=True,
in_dims_hint=SparseList([['h', 'w', 'c'],
cls.TF_LITE_FILTER_ORDER.copy(),
['out_c']]),
out_dims_hint=SparseList([['h', 'w', 'c']]),
constant_store=G.constant_store)
G.add_edge(NNEdge(from_node=weights_node, to_node=params, to_idx=1))
G.add_edge(NNEdge(from_node=bias_node, to_node=params, to_idx=2))
cls.new_load_filter_parameters(G, params, node.input[0], weights_node,
bias_node, node.output[0], opts)
# if opts.get('load_dequantized'):
# weights_node.value, bias_node.value = cls.load_dequantized_filter_parameters(
# node.input, bias_node.value)
# else:
# qrec, weights_node.value, bias_node.value = cls.load_filter_parameters(G, params, node.input, bias_node.value,
# node.output, opts)
# if qrec:
# G.quantization[NodeId(weights_node)].out_qs[0] = qrec.in_qs[1]
# G.quantization[NodeId(bias_node)].out_qs[0] = qrec.in_qs[2]
in_dim = Dim.named_ordered(h=h, w=w, c=in_c)
out_dims = params.get_output_size(
[in_dim,
Dim.unnamed(filt_dim.shape),
Dim.unnamed([filt_out_c])])
pout_dims = ProvisionalDim([in_b] + out_dims[0].shape)
G.add_edge(
NNEdge(from_node=x[0], to_node=params, from_idx=x[1], to_idx=0))
params = cls.fuse_activation(node_opts, node.name, params, **kwargs)
all_nodes[node.output[0]] = (params, 0, pout_dims)
return params
def _common(cls, node: TFLiteNode, **kwargs):
node_opts = node.get_options(DepthwiseConv2DOptions)
G = kwargs['G']
opts = kwargs['opts']
all_nodes = kwargs['all_nodes']
inputs = [all_nodes[t] for t in node.input]
x = inputs[0]
x_shape = x[2].shape
in_b, h, w, in_c = tuple(x_shape)
filt = inputs[1]
filt_tensor = node.input[1]
filt_shape = filt[2].shape
# ['in_c', 'h', 'w', 'out_c']
filt_in_c, filt_h, filt_w, filt_out_c = tuple(filt_shape)
# get filter dimensions
filt_tensor.used = True
if filt_h > h or filt_w > w:
LOG.warning(
"Filter %s of shape [%dx%d] is bigger than input of shape [%dx%d]",
node.name, filt_h, filt_w, h, w)
filt_dim = Conv2DFilterDim(filt_h, filt_w, filt_out_c, in_c=filt_in_c)
filt_dim = filt_dim.impose_order(cls.TF_LITE_DW_FILTER_ORDER)
# multiplier should match filter
check(filt_dim.out_c == node_opts.DepthMultiplier() * in_c,
"invalid multiplier")
groups = filt_dim.out_c // node_opts.DepthMultiplier()
# compute padding
pad = cls.get_tf_padding(node_opts.Padding())
# does it have biases
has_bias = len(inputs) > 2
if has_bias:
node.input[2].used = True
# TFLITE produces single channel input DW convolutions with the
# multiplier equal to the number of out channels. This is just
# a normal convolution and since we don't handle the channel
# multiplier at present (but can) just convert them to normal
# convolutions
convert_to_conv = in_c == 1 and groups == 1
if convert_to_conv:
filt_dim.impose_order(cls.TF_LITE_FILTER_ORDER)
params = Conv2DParameters(
node.name,
filt=filt_dim,
stride=StrideDim(node_opts.StrideH(), node_opts.StrideW()),
dilation=DilationDim(node_opts.DilationHFactor(),
node_opts.DilationWFactor()),
padding=pad,
has_bias=has_bias,
in_dims_hint=SparseList([['h', 'w', 'c']]),
out_dims_hint=SparseList([['h', 'w', 'c']]),
constant_store=G.constant_store)
else:
filt_dim.impose_order(cls.TF_LITE_DW_FILTER_ORDER)
params = Conv2DParameters(
node.name,
filt=filt_dim,
stride=StrideDim(node_opts.StrideH(), node_opts.StrideW()),
dilation=DilationDim(node_opts.DilationHFactor(),
node_opts.DilationWFactor()),
padding=pad,
groups=groups,
multiplier=node_opts.DepthMultiplier(),
has_bias=has_bias,
tf_depthwise=True,
in_dims_hint=SparseList([['h', 'w', 'c']]),
out_dims_hint=SparseList([['h', 'w', 'c']]),
constant_store=G.constant_store)
if opts.get('load_dequantized'):
cls.load_dequantized_filter_parameters(params,
node.input,
convert_to_conv,
is_dw=True)
else:
cls.load_filter_parameters(G,
params,
node.input,
node.output,
opts,
converted_to_conv=convert_to_conv)
in_dim = Dim.named_ordered(h=h, w=w, c=in_c)
out_dims = params.get_output_size([in_dim])
pout_dims = ProvisionalDim([in_b] + out_dims[0].shape)
G.add_edge(
NNEdge(from_node=x[0], to_node=params, from_idx=x[1], to_idx=0))
params = cls.fuse_activation(node_opts, node.name, params, **kwargs)
all_nodes[node.output[0]] = (params, 0, pout_dims)
return params
def _common(cls, node: TFLiteNode, **kwargs):
node_opts = node.get_options(ConcatenationOptions)
G = kwargs['G']
opts = kwargs['opts']
all_nodes = kwargs['all_nodes']
inputs = [all_nodes[t] for t in node.input]
inp_shapes = [input[2].shape for input in inputs]
buffer_idxes = [tensor.buffer_idx for tensor in node.input]
non_zero_idxes = [idx for idx in buffer_idxes if idx != 0]
duplicates = [
idx for idx, count in Counter(non_zero_idxes).items() if count > 1
]
if duplicates:
LOG.warning(
f'concat {node.name} has duplicate inputs. Inserting copies but this is not very efficient.'
)
for idx in duplicates:
dup_idxes = [i for i, x in enumerate(buffer_idxes) if x == idx]
for dup_idx in dup_idxes[1:]:
cparams = CopyParameters(
G.unique_name(
f'{node.name}_dup_{dup_idxes[0]}_{dup_idx}'))
dup_inp = inputs[dup_idx]
G.add_edge(
NNEdge(from_node=dup_inp[0],
from_idx=dup_inp[1],
to_node=cparams))
inputs[dup_idx] = tuple([cparams, 0] + list(dup_inp[2:]))
axis = node_opts.Axis()
if any(inp_shape[axis] is None for inp_shape in inp_shapes):
raise ValueError("concat on undefined axis in node %s" % node.name)
def red_func(x, y):
return y.copy() if x is None else [
(elem if y[idx] is not None and elem is not None else None)
if idx != axis else elem + y[axis]
for idx, elem in enumerate(x)
]
pout_shape = reduce(red_func, inp_shapes)
if all(cls.is_constant(inp) for inp in inputs):
# cls.remove_none_from_constants(inputs, pout_shape)
LOG.info("reducing %s to a constant", node.name)
value = np.concatenate([cls.get_constant(inp) for inp in inputs],
axis=axis)
params = ConstantInputParameters(node.name, value=value)
else:
axis -= sum(1 if dim is None else 0 for dim in pout_shape[:axis:])
params = ConcatParameters(node.name, axis=axis, axis_hint=None)
for idx, inp in enumerate(inputs):
inp_node, inp_idx = cls._maybe_insert_reshape(
G, inp, inp_shapes[idx], pout_shape)
G.add_edge(
NNEdge(from_node=inp_node,
to_node=params,
from_idx=inp_idx,
to_idx=idx))
if opts.get('load_quantization'):
G.quantization[NodeId(params)] = cls.load_tf_quantization(
node.input, node.output)
cls.fuse_activation(node_opts, node.name, params, **kwargs)
all_nodes[node.output[0]] = (params, 0, ProvisionalDim(pout_shape))
return params
def version_1(cls, node: TFLiteNode, **kwargs):
node_opts = node.get_options(Conv2DOptions)
G = kwargs['G']
opts = kwargs['opts']
all_nodes = kwargs['all_nodes']
inputs = [all_nodes[t] for t in node.input]
x = inputs[0]
x_shape = x[2].shape
in_b, h, w, in_c = tuple(x_shape)
filt = inputs[1]
filt_tensor = node.input[1]
filt_shape = filt[2].shape
# ['in_c', 'h', 'w', 'out_c']
filt_out_c, filt_h, filt_w, filt_in_c = tuple(filt_shape)
# get filter dimensions
filt_tensor.used = True
if filt_h > h or filt_w > w:
LOG.warning(
"Filter %s of shape [%dx%d] is bigger than input of shape [%dx%d]",
node.name, filt_h, filt_w, h, w)
filt_dim = Conv2DFilterDim(filt_h, filt_w, filt_out_c, in_c=filt_in_c)
filt_dim = filt_dim.impose_order(cls.TF_LITE_FILTER_ORDER)
# compute padding
pad = cls.get_tf_padding(node_opts.Padding())
# does it have biases
has_bias = len(inputs) > 2
if has_bias:
node.input[2].used = True
params = Conv2DParameters(node.name,
filt=filt_dim,
stride=StrideDim(node_opts.StrideH(),
node_opts.StrideW()),
dilation=DilationDim(
node_opts.DilationHFactor(),
node_opts.DilationWFactor()),
padding=pad,
has_bias=has_bias,
in_dims_hint=SparseList([['h', 'w', 'c']]),
out_dims_hint=SparseList([['h', 'w', 'c']]),
constant_store=G.constant_store)
if opts.get('load_dequantized'):
cls.load_dequantized_filter_parameters(params, node.input)
else:
cls.load_filter_parameters(G, params, node.input, node.output,
opts)
in_dim = Dim.named_ordered(h=h, w=w, c=in_c)
out_dims = params.get_output_size([in_dim])
pout_dims = ProvisionalDim([in_b] + out_dims[0].shape)
G.add_edge(
NNEdge(from_node=x[0], to_node=params, from_idx=x[1], to_idx=0))
params = cls.fuse_activation(node_opts, node.name, params, **kwargs)
all_nodes[node.output[0]] = (params, 0, pout_dims)
return params
def version_1(cls, node: TFLiteNode, **kwargs):
node_opts = node.get_options(Conv2DOptions)
G = kwargs['G']
opts = kwargs['opts']
all_nodes = kwargs['all_nodes']
inputs = [all_nodes[t] for t in node.input]
x = inputs[0]
x = cls.remove_known_batch_dimension(G, x, node)
x_shape = x[2].shape
in_b, h, w, in_c = tuple(x_shape)
filt = inputs[1]
weights_node = filt[0]
filt_shape = filt[2].shape
# ['in_c', 'h', 'w', 'out_c']
filt_out_c, filt_h, filt_w, filt_in_c = tuple(filt_shape)
# get filter dimensions
if filt_h > h or filt_w > w:
LOG.warning(
"Filter %s of shape [%dx%d] is bigger than input of shape [%dx%d]",
node.name, filt_h, filt_w, h, w)
filt_dim = Conv2DFilterDim(filt_h, filt_w, filt_out_c, in_c=filt_in_c)
filt_dim = filt_dim.impose_order(cls.TF_LITE_FILTER_ORDER)
# compute padding
pad = cls.get_tf_padding(node_opts.Padding())
# does it have biases
if len(inputs) > 2:
bias = inputs[2]
bias_node = bias[0]
else:
bias_node = ConstantInputParameters(
f'{node.name}_bias',
dims=Dim.unnamed([filt_out_c]),
value=np.zeros([filt_out_c], dtype=np.float32)) # TODO - check
groups = in_c // filt_in_c
params = Conv2DParameters(
node.name,
filt=filt_dim,
stride=StrideDim(node_opts.StrideH(), node_opts.StrideW()),
dilation=DilationDim(node_opts.DilationHFactor(),
node_opts.DilationWFactor()),
groups=groups,
padding=pad,
has_bias=True,
in_dims_hint=[['h', 'w', 'c'],
cls.TF_LITE_FILTER_ORDER.copy(), ['out_c']],
out_dims_hint=[['h', 'w', 'c']])
G.add_edge(NNEdge(from_node=weights_node, to_node=params, to_idx=1))
G.add_edge(NNEdge(from_node=bias_node, to_node=params, to_idx=2))
cls.new_load_filter_parameters(G, params, params.filter.actual_shape,
params.filter.get_order_idx('out_c'),
node.input[0], weights_node, bias_node,
node.output[0], opts)
in_dim = Dim.named_ordered(h=h, w=w, c=in_c)
out_dims = params.get_output_size(
[in_dim,
Dim.unnamed(filt_dim.shape),
Dim.unnamed([filt_out_c])])
pout_dims = ProvisionalDim([None] + out_dims[0].shape)
G.add_edge(
NNEdge(from_node=x[0], to_node=params, from_idx=x[1], to_idx=0))
oparams = cls.fuse_activation(node_opts, node.name, params, **kwargs)
all_nodes[node.output[0]] = (oparams, 0, pout_dims)
return oparams
