From 6986a079020ab6344c9191aa67af13beeb475593 Mon Sep 17 00:00:00 2001 From: Rickard Bolin Date: Mon, 19 Dec 2022 12:33:40 +0000 Subject: MLBEDSW-6435: Implement support for ArgMax along depth dimension - Add support for ArgMax along depth dimension with a depth limit of 127. - Only supports 8-bit input and 32-bit output Signed-off-by: Rickard Bolin Change-Id: I5f6f0503135bebabbb1ca637f9729587b7c60740 --- SUPPORTED_OPS.md | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) (limited to 'SUPPORTED_OPS.md') diff --git a/SUPPORTED_OPS.md b/SUPPORTED_OPS.md index 860d1fe6..6f6167d2 100644 --- a/SUPPORTED_OPS.md +++ b/SUPPORTED_OPS.md @@ -1,7 +1,7 @@ # Supported Ops This file was automatically generated by Vela using the `--supported-ops-report` parameter. -Vela version: `3.7.1.dev2+g19f8967.d20230301` +Vela version: `3.7.1.dev8+ga182a70.d20230322` This file complies with [**Gitiles Markdown syntax**](https://github.com/google/gitiles/blob/master/Documentation/markdown.md) @@ -20,6 +20,7 @@ Please check the supported operator list for your chosen runtime for further inf | --- | --- | | ABS | [Generic](#tflite-generic-constraints), [Specific](#tflite-abs-constraints) | | ADD | [Generic](#tflite-generic-constraints), [Specific](#tflite-add-constraints) | +| ARG_MAX | [Generic](#tflite-generic-constraints), [Specific](#tflite-arg_max-constraints) | | AVERAGE_POOL_2D | [Generic](#tflite-generic-constraints), [Specific](#tflite-average_pool_2d-constraints) | | CONCATENATION | [Generic](#tflite-generic-constraints), [Specific](#tflite-concatenation-constraints) | | CONV_2D | [Generic](#tflite-generic-constraints), [Specific](#tflite-conv_2d-constraints) | @@ -64,14 +65,14 @@ This is a list of constraints most NPU operators must satisfy in order to be sch - Input(s) and Output tensors must not be dynamic - [QUANTIZE] - Input(s) and Output tensors must have a defined shape - Output tensors cannot be scalar - [QUANTIZE] -- Scalar Input tensors are only valid for op type: ADD, EXPAND_DIMS, MAXIMUM, MEAN, MINIMUM, MUL, QUANTIZE, SPLIT, SPLIT_V, SUB +- 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 - [SHAPE] +- Input(s), Output and Weight tensors must have quantization parameters - [ARG_MAX, SHAPE] - 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 -- Tensors which are int32 are only valid when op type is: ADD, MUL, SHAPE, SUB +- Tensors which are int32 are only valid when op type is: ADD, ARG_MAX, MUL, SHAPE, SUB - 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] @@ -95,6 +96,15 @@ This is a list of constraints that the ADD operator must satisfy in order to be - For IFM that are unsigned, OFM must either be the same type or int32 - Broadcasting is only allowed for rank indices with dimension 1, from either IFM1 or IFM2 +### TFLite ARG_MAX Constraints + +This is a list of constraints that the ARG_MAX operator must satisfy in order to be scheduled on the NPU. + +- IFM must be int8 or uint8 +- Number of input dimensions must be 4 +- Operation must be performed along the depth axis +- IFM depth must be no greater than 127 + ### TFLite AVERAGE_POOL_2D Constraints This is a list of constraints that the AVERAGE_POOL_2D operator must satisfy in order to be scheduled on the NPU. -- cgit v1.2.1