From fea1516f94cfcbd801124e3fdc4b5f5c4526e15b Mon Sep 17 00:00:00 2001 From: Rickard Bolin Date: Mon, 4 Jul 2022 16:19:16 +0000 Subject: MLBEDSW-6686: Resize bilinear HPC with tile padding - Added support for Resize Bilinear with half pixel centers for int8 and uint8. - Utilizes the new "TILE" padding mode. - Utilizes ofm stride multipliers and modified tile base offsets to write OFMs interleaved. Signed-off-by: Rickard Bolin Change-Id: I37fa77c022a368f05fda0ead75d8696c9205f833 --- SUPPORTED_OPS.md | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) (limited to 'SUPPORTED_OPS.md') diff --git a/SUPPORTED_OPS.md b/SUPPORTED_OPS.md index 6a92e829..36b403ad 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: `3.5.0` +Vela version: `3.5.1.dev14+gc22ad76.d20220921` This file complies with [**Gitiles Markdown syntax**](https://github.com/google/gitiles/blob/master/Documentation/markdown.md) @@ -36,6 +36,7 @@ Please check the supported operator list for your chosen runtime for further inf | MUL | [Generic](#tflite-generic-constraints), [Specific](#tflite-mul-constraints) | | PACK | [Generic](#tflite-generic-constraints) | | PAD | [Generic](#tflite-generic-constraints), [Specific](#tflite-pad-constraints) | +| PRELU | [Generic](#tflite-generic-constraints) | | QUANTIZE | [Generic](#tflite-generic-constraints) | | RELU | [Generic](#tflite-generic-constraints) | | RELU6 | [Generic](#tflite-generic-constraints) | @@ -116,7 +117,6 @@ This is a list of constraints that the CONCATENATION operator must satisfy in or - Axis attribute must be in the range [0, ) - All Input dimensionalities must match OFM dimensionality - All Input dimensions must match OFM dimension in all axes except the one defined by the axis attribute -- All Input dimensions must match OFM dimension in all axes except the one defined by the axis attribute - The size of the OFM axis must match the sum of all IFM axis defined by the axis attribute ### TFLite CONV_2D Constraints @@ -184,7 +184,6 @@ This is a list of constraints that the LEAKY_RELU operator must satisfy in order - At least one Input's shape must match the OFM's shape - IFM and OFM data types must match -- Alpha only allowed to be negative if IFM is int8 or uint8 - Batch size must be 1 for Input tensors with more than 2 dimensions ### TFLite MAXIMUM Constraints @@ -268,6 +267,7 @@ This is a list of constraints that the RESHAPE operator must satisfy in order to - Input and output quantisation must match. - Shape must be constant +- Reshape on NPU not supported before MEAN operator ### TFLite RESIZE_BILINEAR Constraints @@ -276,11 +276,12 @@ This is a list of constraints that the RESIZE_BILINEAR operator must satisfy in - The width and height of the IFM and OFM must match one of the following criteria: IFM W and H must both be 1 IFM must match OFM - OFM W and H must be equal and OFM W-1 and H-1 must be 2x/4x/8x IFM W-1 and H-1, if align_corners is True - OFM W and H must be equal and OFM W and H must be 2x/4x/8x IFM W and H, if align_corners is False + W and H scaling must be equal and OFM W-1 and H-1 must be 2x/4x/8x IFM W-1 and H-1, if align_corners is True + W and H scaling must be equal and OFM W and H must be 2x/4x/8x IFM W and H, if align_corners is False - The size tensor must match the output tensor shape - Both align_corners and half_pixel_centers can't be True -- half_pixel_centers are not supported +- Half_pixel_centers are only supported for resize bilinear with IFM dtype int8 or uint8 +- Half_pixel_centers for resize bilinear requires that OFM W and H is 2x IFM W and H ### TFLite RESIZE_NEAREST_NEIGHBOR Constraints @@ -289,11 +290,11 @@ This is a list of constraints that the RESIZE_NEAREST_NEIGHBOR operator must sat - The width and height of the IFM and OFM must match one of the following criteria: IFM W and H must both be 1 IFM must match OFM - OFM W and H must be equal and OFM W-1 and H-1 must be 2x/4x/8x IFM W-1 and H-1, if align_corners is True - OFM W and H must be equal and OFM W and H must be 2x/4x/8x IFM W and H, if align_corners is False + W and H scaling must be equal and OFM W-1 and H-1 must be 2x/4x/8x IFM W-1 and H-1, if align_corners is True + W and H scaling must be equal and OFM W and H must be 2x/4x/8x IFM W and H, if align_corners is False - The size tensor must match the output tensor shape - Both align_corners and half_pixel_centers can't be True -- half_pixel_centers are not supported +- Half_pixel_centers are only supported for resize bilinear with IFM dtype int8 or uint8 ### TFLite SOFTMAX Constraints -- cgit v1.2.1