MLBEDSW-8620: Fix MirrorPad supported ops check
Change-Id: I1458009f4b92c1a599efa3a63d6768148e55606d
Signed-off-by: Rickard Bolin <rickard.bolin@arm.com>
diff --git a/SUPPORTED_OPS.md b/SUPPORTED_OPS.md
index b2bd096..43f087f 100644
--- a/SUPPORTED_OPS.md
+++ b/SUPPORTED_OPS.md
@@ -1,5 +1,5 @@
<!--
-SPDX-FileCopyrightText: Copyright 2020-2023 Arm Limited and/or its affiliates <open-source-office@arm.com>
+SPDX-FileCopyrightText: Copyright 2020-2024 Arm Limited and/or its affiliates <open-source-office@arm.com>
SPDX-License-Identifier: Apache-2.0
@@ -19,7 +19,7 @@
# Supported Ops
This file was automatically generated by Vela using the `--supported-ops-report` parameter.
-Vela version: `3.11.0.`
+Vela version: `3.11.0`
This file complies with
[**Gitiles Markdown syntax**](https://gerrit.googlesource.com/gitiles/+/HEAD/Documentation/markdown.md)
@@ -53,6 +53,7 @@
| MAX_POOL_2D | [Generic](#tflite-generic-constraints), [Specific](#tflite-max_pool_2d-constraints) |
| MEAN | [Generic](#tflite-generic-constraints), [Specific](#tflite-mean-constraints) |
| MINIMUM | [Generic](#tflite-generic-constraints), [Specific](#tflite-minimum-constraints) |
+| MIRROR_PAD | [Generic](#tflite-generic-constraints), [Specific](#tflite-mirror_pad-constraints) |
| MUL | [Generic](#tflite-generic-constraints), [Specific](#tflite-mul-constraints) |
| PACK | [Generic](#tflite-generic-constraints) |
| PAD | [Generic](#tflite-generic-constraints), [Specific](#tflite-pad-constraints) |
@@ -91,12 +92,12 @@
- Output tensors cannot be scalar - [QUANTIZE]
- Scalar Input tensors are only valid for op type: ADD, ARG_MAX, EXPAND_DIMS, MAXIMUM, MEAN, MINIMUM, MUL, QUANTIZE, SPLIT, SPLIT_V, SUB
- Input(s) and Output tensors must not be greater than 4D
-- Input(s), Output and Weight tensors must have quantization parameters - [ARG_MAX, SHAPE, TRANSPOSE]
+- Input(s), Output and Weight tensors must have quantization parameters - [ARG_MAX, MIRROR_PAD, SHAPE, TRANSPOSE]
- Input(s), Output and Weight tensors with quantization scales must be finite
- Input and Output tensors must have quantization scales that fit within float32 precision
- Constant tensors should not have NoneType-values
- Tensors must be of type: int16, int32, int8, uint8 - [ARG_MAX]
-- Tensors which are int32 are only valid when op type is: ADD, ARG_MAX, MUL, SHAPE, SUB, TRANSPOSE
+- Tensors which are int32 are only valid when op type is: ADD, ARG_MAX, MIRROR_PAD, MUL, SHAPE, SUB, TRANSPOSE
- Tensor dimensions must be in the range [1, 65535]
- Per-axis quantization is only supported for the following op types: CONV_2D, DEPTHWISE_CONV_2D, TRANSPOSE_CONV
- IFM Tensor batch size must be 1 - [FULLY_CONNECTED, RESHAPE, SHAPE, SLICE, SOFTMAX, SPLIT, SPLIT_V, SQUEEZE, STRIDED_SLICE, UNPACK]
@@ -285,6 +286,15 @@
- Both Input quantization parameters must match OFM quantization parameters
- Broadcasting is only allowed for rank indices with dimension 1, from either IFM1 or IFM2
+### TFLite MIRROR_PAD Constraints
+
+This is a list of constraints that the MIRROR_PAD operator must satisfy in order to be scheduled on the NPU.
+
+- The padding tensor must have the shape [3,2] or [4,2]
+- The pad tensor can only pad width and height
+- Pad tensor must be of type: int32, int64
+- The number of pad values for each direction must not be larger than the ifm size in that dimension
+
### TFLite MUL Constraints
This is a list of constraints that the MUL operator must satisfy in order to be scheduled on the NPU.
diff --git a/ethosu/vela/tflite_supported_operators.py b/ethosu/vela/tflite_supported_operators.py
index ad61fca..91a3ee8 100644
--- a/ethosu/vela/tflite_supported_operators.py
+++ b/ethosu/vela/tflite_supported_operators.py
@@ -831,10 +831,11 @@
@staticmethod
def constraint_mirror_pad_padding_values(op):
"The number of pad values for each direction must not be larger than the ifm size in that dimension"
+ valid = True
pad_tensor = op.inputs[1].values
ifm_shape = op.inputs[0].shape
- for dim_padding, ifm_dim_shape in enumerate(pad_tensor, ifm_shape):
- if any(dim_padding > ifm_dim_shape):
+ for dim_padding, ifm_dim_shape in zip(pad_tensor, ifm_shape):
+ if any([pad_val > ifm_dim_shape for pad_val in dim_padding]):
valid = False
return valid, f"IFM shape: {ifm_shape}, number of padding values per dimension: {pad_tensor}"
diff --git a/ethosu/vela/vela.py b/ethosu/vela/vela.py
index 66a2104..a4b93f1 100644
--- a/ethosu/vela/vela.py
+++ b/ethosu/vela/vela.py
@@ -1,4 +1,4 @@
-# SPDX-FileCopyrightText: Copyright 2020-2023 Arm Limited and/or its affiliates <open-source-office@arm.com>
+# SPDX-FileCopyrightText: Copyright 2020-2024 Arm Limited and/or its affiliates <open-source-office@arm.com>
#
# SPDX-License-Identifier: Apache-2.0
#
@@ -178,7 +178,7 @@
def generate_license():
lines = [
"<!--",
- "SPDX-FileCopyrightText: Copyright 2020-2023 Arm Limited and/or its affiliates <open-source-office@arm.com>",
+ "SPDX-FileCopyrightText: Copyright 2020-2024 Arm Limited and/or its affiliates <open-source-office@arm.com>",
"",
"SPDX-License-Identifier: Apache-2.0",
"",