diff options
Diffstat (limited to 'SUPPORTED_OPS.md')
-rw-r--r-- | SUPPORTED_OPS.md | 8 |
1 files changed, 2 insertions, 6 deletions
diff --git a/SUPPORTED_OPS.md b/SUPPORTED_OPS.md index e48ebf58..3c90e20c 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: `2.1.0` +Vela version: `2.1.2.dev0+g41c006a.d20210309` This file complies with [**Gitiles Markdown syntax**](https://github.com/google/gitiles/blob/master/Documentation/markdown.md) @@ -239,15 +239,11 @@ This is a list of constraints that the MUL operator must satisfy in order to be This is a list of constraints that the PAD operator must satisfy in order to be scheduled on the NPU. -- IFM and OFM data types must match -- Both Input quantization parameters must match OFM quantization parameters - Number of input tensors must be exactly 2 -- The padding tensor must have the shape [4,2] +- 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 padding tensor must be constant -- Must be followed by one of the following operator types: AVERAGE_POOL_2D, CONV_2D, DEPTHWISE_CONV_2D, MAX_POOL_2D -- Padding must be at most kernel size divided by 2 ## RESIZE_BILINEAR Constraints |