MLBEDSW-2372: Failing assert for ResizeBilinear with upscale != 2x
This commit fixes the failing assert by removing it
and instead placing unsupported ResizeBilinear
operators on the CPU.
It introduces a new graph optimisation function
which adds the necessary attributes as well as
new operator restrictions for ResizeBilinear.
Signed-off-by: Dwight Lidman <dwight.lidman@arm.com>
Change-Id: I2feffd0b5a2169ebffbe4f165e450b3f2d140380
diff --git a/ethosu/vela/graph_optimiser.py b/ethosu/vela/graph_optimiser.py
index 72bb486..758b51a 100644
--- a/ethosu/vela/graph_optimiser.py
+++ b/ethosu/vela/graph_optimiser.py
@@ -23,6 +23,7 @@
from . import rewrite_graph
from .data_type import DataType
from .errors import UnsupportedFeatureError
+from .ethos_u55_regs.ethos_u55_regs import resampling_mode
from .operation import NpuBlockType
from .operation import Operation
from .tensor import Tensor
@@ -483,6 +484,30 @@
return op
+def add_attrs_to_resizebilinear(op, arch):
+ if op.type == 'ResizeBilinear' and op.run_on_npu:
+ input_tensor = op.inputs[0]
+ upscaled_shape = [input_tensor.shape[1] * 2, input_tensor.shape[2] * 2]
+ out_shape = op.outputs[0].shape[1:3]
+ if not op.attrs["align_corners"] and out_shape == upscaled_shape:
+ # this means the output is supposed to be a x2 upscale,
+ # so we need to do SAME padding
+ op.attrs["padding"] = b"SAME"
+ elif op.attrs["align_corners"] and out_shape == [upscaled_shape[0] - 1, upscaled_shape[1] - 1]:
+ # here we can just run the avg pool without padding and
+ # produce a (M * 2 - 1, N * 2 - 1) sized output
+ op.attrs["padding"] = b"VALID"
+ else:
+ # If this exception is raised, something is wrong with the supported op check
+ raise UnsupportedFeatureError("Unsupported upscaling factor")
+ input_tensor.resampling_mode = resampling_mode.NEAREST
+ op.attrs.update({
+ 'strides': (1, 1, 1, 1),
+ 'ksize': (1, 2, 2, 1),
+ })
+ return op
+
+
def supported_operator_check(op, arch):
op.run_on_npu = arch.supported_operators.is_operator_supported(op)
return op
@@ -503,6 +528,7 @@
fixup_pack_input,
fixup_conv2d_backprop,
fixup_act_reorder,
+ add_attrs_to_resizebilinear,
add_padding_fields,
mark_npu_block_type,
fixup_elementwise_with_scalars,
diff --git a/ethosu/vela/supported_operators.py b/ethosu/vela/supported_operators.py
index ce3fa60..729d435 100644
--- a/ethosu/vela/supported_operators.py
+++ b/ethosu/vela/supported_operators.py
@@ -29,6 +29,7 @@
self.max_pooling_ops = set(("QuantizedMaxPool", "MaxPool", "MaxPoolAct"))
self.avg_pooling_ops = set(("QuantizedAvgPool", "AvgPool", "AvgPoolAct"))
self.pooling_ops = self.max_pooling_ops | self.avg_pooling_ops
+ self.resizing_ops = set(("ResizeBilinear",))
self.fc_vector_products = set(("QuantizedMatMul", "MatMul", "FullyConnectedAct"))
self.mac_main_ops = (
# convolutions
@@ -37,12 +38,12 @@
| self.depthwise_convolution_ops
# pooling
| self.pooling_ops
+ # resizing/upscaling
+ | self.resizing_ops
# FC layers
| self.fc_vector_products
# RNN/LSTM/GRU
| set(("BlockLSTM"))
- # deconvolution
- | set(("ResizeBilinear",))
)
self.unary_elem_wise_main_ops = set(("LeakyRelu", "Abs"))
self.binary_elem_wise_min_max_ops = set(("Minimum", "Maximum"))
@@ -90,6 +91,7 @@
{op: self.check_depthwise_convolution_restrictions for op in self.depthwise_convolution_ops}
)
self.supported_operator_restrictions.update({op: self.check_pooling_restrictions for op in self.pooling_ops})
+ self.supported_operator_restrictions.update({op: self.check_resize_restrictions for op in self.resizing_ops})
self.supported_operator_restrictions.update(
{op: self.check_vector_product_restrictions for op in self.fc_vector_products}
)
@@ -206,6 +208,17 @@
return False
return True
+ def check_resize_restrictions(self, op):
+ # check unsupported upscaling factor
+ if op.type == "ResizeBilinear":
+ upscaled_shape = [op.inputs[0].shape[1] * 2, op.inputs[0].shape[2] * 2]
+ out_shape = op.outputs[0].shape[1:3]
+ if not op.attrs["align_corners"] and out_shape != upscaled_shape:
+ return False
+ elif op.attrs["align_corners"] and out_shape != [upscaled_shape[0] - 1, upscaled_shape[1] - 1]:
+ return False
+ return True
+
def check_vector_product_restrictions(self, op):
# check data type
ifm_tensor, _, weight_tensor, _ = op.get_ifm_ifm2_weights_ofm()
diff --git a/ethosu/vela/tflite_reader.py b/ethosu/vela/tflite_reader.py
index 4ee3963..109ae0e 100644
--- a/ethosu/vela/tflite_reader.py
+++ b/ethosu/vela/tflite_reader.py
@@ -20,7 +20,6 @@
import numpy as np
from .errors import UnsupportedFeatureError
-from .ethos_u55_regs.ethos_u55_regs import resampling_mode
from .nn_graph import Graph
from .nn_graph import Subgraph
from .operation import Operation
@@ -146,24 +145,6 @@
if opt_serializer is not None:
op.attrs = opt_serializer.deserialize(op_data.BuiltinOptions(), op_data.CustomOptionsAsNumpy())
- if op_type.startswith("ResizeBilinear"):
- input_tensor = op.inputs[0]
- upscaled_shape = [input_tensor.shape[1] * 2, input_tensor.shape[2] * 2]
- out_shape = op.outputs[0].shape[1:3]
- if not op.attrs["align_corners"] and out_shape == upscaled_shape:
- # this means the output is supposed to be a x2 upscale,
- # so we need to do SAME padding
- op.attrs.update({"padding": b"SAME"})
- elif op.attrs["align_corners"] and out_shape == [upscaled_shape[0] - 1, upscaled_shape[1] - 1]:
- # here we can just run the avg pool without padding and
- # produce a (M * 2 - 1, N * 2 - 1) sized output
- op.attrs.update({"padding": b"VALID"})
- else:
- raise UnsupportedFeatureError("ResizeBilinear: Only 2x upscaling is supported")
- op.attrs.update({"filter_width": 2, "filter_height": 2, "stride_w": 1, "stride_h": 1})
-
- input_tensor.resampling_mode = resampling_mode.NEAREST
-
if "stride_w" in op.attrs:
op.attrs["strides"] = (1, op.attrs["stride_h"], op.attrs["stride_w"], 1)
if "filter_width" in op.attrs: