MLBEDSW-2868 Refactor separation of scale + bias tensors
Changed so that there is an option to set if Tensor clone should be
seen as unique or not.
Signed-off-by: Patrik Gustavsson <patrik.gustavsson@arm.com>
Change-Id: Ie51c1a5e84b535380d498b105aa18ccba1c8b27c
diff --git a/ethosu/vela/tensor.py b/ethosu/vela/tensor.py
index 8786d36..49f93cd 100644
--- a/ethosu/vela/tensor.py
+++ b/ethosu/vela/tensor.py
@@ -15,6 +15,7 @@
# limitations under the License.
# Description:
# Internal representation of a Neural Network Tensor.
+import copy
import enum
import uuid
from collections import defaultdict
@@ -392,34 +393,25 @@
return self.dtype.size_in_bits() / 8
return self.element_size_bytes
- def clone(self, suffix="_clone"):
- res = Tensor(self.shape, self.dtype, self.name + suffix)
- res.storage_shape = list(self.storage_shape)
- res.bandwidth_shape = list(self.bandwidth_shape)
+ # Returns a copy, renamed to self.name + suffix
+ # The references to Operators will be empty when returned
+ # Depending on set_unique, the copy is shallow, or deep
+ # For set_unique==True, a new equivalence_id will be set
+ def clone(self, suffix="_clone", set_unique=False):
+ if set_unique:
+ res = copy.deepcopy(self)
+ res.equivalence_id = uuid.uuid4()
+ else:
+ res = copy.copy(self)
+ res.storage_shape = list(self.storage_shape)
+ res.bandwidth_shape = list(self.bandwidth_shape)
+ if self.quantization is not None:
+ res.quantization = self.quantization.clone()
+ res.name = res.name + suffix
res.ops = []
res.consumer_list = []
- res.values = self.values
- res.quant_values = self.quant_values
- res.mem_area = self.mem_area
- res.mem_type = self.mem_type
- res.format = self.format
- res.purpose = self.purpose
- res.sub_purpose = self.sub_purpose
- res.alignment = self.alignment
- res.bandwidth_compression_scale = self.bandwidth_compression_scale
- res.storage_rounding_quantum = self.storage_rounding_quantum
-
- if self.quantization is not None:
- res.quantization = self.quantization.clone()
- else:
- res.quantization = None
-
- res.resampling_mode = self.resampling_mode
-
- res.copy_compressed_weight_info(self)
- res.avoid_NHCWB16 = self.avoid_NHCWB16
return res
def clone_into_fast_storage(self, arch):
@@ -806,9 +798,6 @@
return True
- def set_random_equivalence_id(self):
- self.equivalence_id = uuid.uuid4()
-
def __str__(self):
return "<nng.Tensor '%s' shape=%s dtype=%s>" % (self.name, self.shape, self.dtype)
diff --git a/ethosu/vela/tflite_reader.py b/ethosu/vela/tflite_reader.py
index 82feddd..24f9f87 100644
--- a/ethosu/vela/tflite_reader.py
+++ b/ethosu/vela/tflite_reader.py
@@ -41,9 +41,8 @@
return s.decode("utf-8")
-def clone_and_reshape_tensor(src_tens, reorder):
-
- tens = src_tens.clone("_reshape")
+def clone_and_reshape_tensor(src_tens, reorder, set_unique):
+ tens = src_tens.clone("_reshape", set_unique)
tens.shape = [src_tens.shape[idx] for idx in reorder]
tens.bandwidth_shape = tens.shape
tens.storage_shape = tens.shape
@@ -153,17 +152,16 @@
if op.type.is_depthwise_conv2d_op() or op.type.is_conv2d_op() or op.type == Op.FullyConnected:
if inputs[1].values is not None:
if op.type == Op.FullyConnected:
- inputs[1] = clone_and_reshape_tensor(inputs[1], (1, 0))
+ inputs[1] = clone_and_reshape_tensor(inputs[1], (1, 0), False)
else:
- inputs[1] = clone_and_reshape_tensor(inputs[1], (1, 2, 3, 0))
+ inputs[1] = clone_and_reshape_tensor(inputs[1], (1, 2, 3, 0), False)
if op.type.needs_bias() and len(inputs) <= op_type.info.indices.biases[0]:
# No Bias tensor
inputs.append(None)
if inputs[-1] and inputs[-1].values is not None:
- inputs[-1] = clone_and_reshape_tensor(inputs[-1], (0,))
# Since bias tensor is used for both bias and scale,
- # set different equivalence_id for all bias tensors
- inputs[-1].set_random_equivalence_id()
+ # a clone with a unique equivalence_id is needed
+ inputs[-1] = clone_and_reshape_tensor(inputs[-1], (0,), True)
if opt_serializer is not None:
op.attrs = opt_serializer.deserialize(op_data)