From 8682331c3703ddad98a64a35f2cfb3861a437fff Mon Sep 17 00:00:00 2001 From: James Peet Date: Thu, 10 Feb 2022 09:20:27 +0000 Subject: MLBEDSW-6036: Regenerate SUPPORTED_OPS.md Updated constraints affect: - Constant tensors - MEAN operations - RESIZE_BILINEAR operations Signed-off-by: James Peet Change-Id: I2a041fa2300a9ba6da048cc61e164f34897b2f50 --- SUPPORTED_OPS.md | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) diff --git a/SUPPORTED_OPS.md b/SUPPORTED_OPS.md index c20391cc..f1e59aa5 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: `3.2.0` +Vela version: `3.2.1.dev26+gd13cd94.d20220215` This file complies with [**Gitiles Markdown syntax**](https://github.com/google/gitiles/blob/master/Documentation/markdown.md) @@ -65,6 +65,7 @@ This is a list of constraints that all NPU operators must satisfy in order to be - Input(s), Output and Weight tensors must have quantization parameters - 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, SUB - Tensor dimensions must be in the range [1, 65535] @@ -211,14 +212,19 @@ This is a list of constraints that the MEAN operator must satisfy in order to be - Input tensor must be at least 2D - Axis indices must correspond to height and width axes - IFM Tensor batch size must be 1 -- Product of height and width can be at most 65536 -- Product of height and width can be at most 4096 when IFM and OFM have different scale or zero point, - or keep_dims is True -- Product of IFM height and width can be at most 256 when the following are true: - IFM dimensions are 4, - Axis indices are 1 and 2, - keep_dims is set to True and +- Product of height and width must be no greater than 65536 +- Product of height and width must be no greater than 4096 when: + IFM and OFM have different scale or zero point; or + 'keep_dims' is True +- Product of IFM height and width must be no greater than 256 when: + The IFM shape has 4 dimensions; and + The axis indices specify reduction across 2 dimensions; and + The axis indices correspond to the width and height dimensions of the IFM; and + 'keep_dims' is True; and IFM datatype is int8 +- For single axis averages across the height dimension: + IFM height must be no greater than 256 if the IFM and OFM scale and zero point match; otherwise + IFM height must be no greater than 64 if the IFM and OFM scale or zero point do not match ### TFLite MINIMUM Constraints @@ -265,8 +271,8 @@ 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 2x IFM -1, if align_corners is True - OFM W and H must be 2x IFM, if align_corners is False + OFM W and H must be equal and 2/4/8x IFM -1, if align_corners is True + OFM W and H must be equal and 2/4/8x IFM, if align_corners is False - half_pixel_centers are not supported ### TFLite SOFTMAX Constraints -- cgit v1.2.1