From 3b64f068db4ea8e954a1b472de169dd423b8c049 Mon Sep 17 00:00:00 2001 From: Raul Farkas Date: Tue, 16 May 2023 17:18:31 +0100 Subject: MLBEDSW-7648: Fix bug with filter padding in conv2d * Fix bug that caused filter padding to not be added proportionally compared to the hardware padding added to IFM. * Update needed_total_padding function that calculates hardware padding to also account for the cases in which IFM width is not divisible by the stride width. * Update supported ops constraint on strides for conv2d to mark ops with stride width > 3 and IFM width that is not divisible by the optimization resize factor as not supported. * Update unit tests that verify correct functionality when checking whether ops are supported or not. Change-Id: I62f14cca890b779ca787a9603fa37c873ad522f8 Signed-off-by: Raul Farkas --- SUPPORTED_OPS.md | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'SUPPORTED_OPS.md') diff --git a/SUPPORTED_OPS.md b/SUPPORTED_OPS.md index 0d42d9c1..947b585a 100644 --- a/SUPPORTED_OPS.md +++ b/SUPPORTED_OPS.md @@ -19,7 +19,7 @@ limitations under the License. # Supported Ops This file was automatically generated by Vela using the `--supported-ops-report` parameter. -Vela version: `3.8.1.dev3+gc66541d.d20230613` +Vela version: `3.8.1.dev3+gc66541d` This file complies with [**Gitiles Markdown syntax**](https://github.com/google/gitiles/blob/master/Documentation/markdown.md) @@ -155,7 +155,9 @@ This is a list of constraints that the CONV_2D operator must satisfy in order to - Stride values for both width and height must be integer types - Dilation factor values for both width and height must be integer types -- Stride width must be greater than or equal to 1 and stride height must be between 1 and 3 +- Stride width must be greater than or equal to 1. + For stride widths greater than 3, the post-optimization stride needs to be less than or equal to 3. + Stride height must be between 1 and 3. - Dilated kernel height must be in the range [1, 64] - Product of dilated kernel width and height must be in the range [1, 4096] - Weight tensor must be 8-bit -- cgit v1.2.1