Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

dialects: (onnx) add onnx.MaxPoolSingleOut #2072

Merged
merged 8 commits into from
Feb 1, 2024
Merged

Conversation

kayode-gif
Copy link
Collaborator

resolves #2068

@kayode-gif kayode-gif added the dialects Changes on the dialects label Feb 1, 2024
@kayode-gif kayode-gif self-assigned this Feb 1, 2024
Copy link

codecov bot commented Feb 1, 2024

Codecov Report

Attention: 3 lines in your changes are missing coverage. Please review.

Comparison is base (9a4b28c) 90.04% compared to head (4fbff2d) 90.05%.
Report is 2 commits behind head on main.

Files Patch % Lines
xdsl/dialects/onnx.py 93.75% 2 Missing and 1 partial ⚠️
Additional details and impacted files
@@            Coverage Diff             @@
##             main    #2072      +/-   ##
==========================================
+ Coverage   90.04%   90.05%   +0.01%     
==========================================
  Files         292      292              
  Lines       36484    36552      +68     
  Branches     5415     5433      +18     
==========================================
+ Hits        32851    32918      +67     
+ Misses       2860     2858       -2     
- Partials      773      776       +3     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

Co-authored-by: Sasha Lopoukhine <superlopuh@gmail.com>
Copy link
Collaborator

@compor compor left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM, minor nits

xdsl/dialects/onnx.py Outdated Show resolved Hide resolved
xdsl/dialects/onnx.py Outdated Show resolved Hide resolved
xdsl/dialects/onnx.py Outdated Show resolved Hide resolved
@@ -64,3 +65,5 @@
%res_constant = "onnx.Constant"() {onnx_node_name = "/Constant", "value" = dense<1> : tensor<1xi64>}: () -> tensor<1xi64>
//CHECK: %res_constant = onnx.Constant() {"onnx_node_name" = "/Constant", "value" = dense<1> : tensor<1xi64>}: () -> tensor<1xi64>

%res_max_pool_single_out = "onnx.MaxPoolSingleOut"(%t26) {onnx_node_name = "/MaxPoolSingleOut", "auto_pad" = "VALID", "ceil_mode" = 0 : i64, "kernel_shape" = [3 : i64, 3 : i64], "dilations" = [1 : i64, 1 : i64], "pads" = [0 : i64, 0 : i64, 0 : i64, 0 : i64], "storage_order" = 0 : i64, "strides" = [1 : i64, 1 : i64]}: (tensor<5x5x32x32xf32>) -> tensor<5x5x30x30xf32>
//CHECK: %res_max_pool_single_out = onnx.MaxPoolSingleOut(%t26) {"onnx_node_name" = "/MaxPoolSingleOut", "auto_pad" = "VALID", "ceil_mode" = 0 : i64, "kernel_shape" = [3 : i64, 3 : i64], "dilations" = [1 : i64, 1 : i64], "pads" = [0 : i64, 0 : i64, 0 : i64, 0 : i64], "storage_order" = 0 : i64, "strides" = [1 : i64, 1 : i64]}: (tensor<5x5x32x32xf32>) -> tensor<5x5x30x30xf32>
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

it might be a good idea to check filecheck substitution patterns (https://www.llvm.org/docs/CommandGuide/FileCheck.html#filecheck-regex-matching-syntax).

It can save some typing when changing names, etc and make the checks for flexible.

You don't have to change this here now, just something for the future.

kayode-gif and others added 5 commits February 1, 2024 17:34
Co-authored-by: Chris Vasiladiotis <cvassiladiotis@gmail.com>
Co-authored-by: Chris Vasiladiotis <cvassiladiotis@gmail.com>
@compor compor merged commit 87c26a7 into main Feb 1, 2024
10 checks passed
@compor compor deleted the oke/onnx-max-pool-single-out branch February 1, 2024 19:29
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
dialects Changes on the dialects
Projects
None yet
Development

Successfully merging this pull request may close these issues.

add onnx.MaxPoolSingleOut
3 participants