[circle-mlir/models] Add Conv2d_F32_R4_p11_g2 test model#16395
Merged
hseok-oh merged 1 commit intoSamsung:masterfrom Feb 25, 2026
Merged
[circle-mlir/models] Add Conv2d_F32_R4_p11_g2 test model#16395hseok-oh merged 1 commit intoSamsung:masterfrom
hseok-oh merged 1 commit intoSamsung:masterfrom
Conversation
hseok-oh
reviewed
Feb 23, 2026
|
|
||
| _model_ = net_Conv2d() | ||
|
|
||
| _inputs_ = torch.randn(1, 256, 200, 320) |
Contributor
There was a problem hiding this comment.
Isn't it too big to test? Why don't you reduce input size?
Contributor
Author
There was a problem hiding this comment.
Yes it's a bit large but I want to use same arguments as the issued model.
Do you want me to reduce the size?
Contributor
There was a problem hiding this comment.
Do you want me to reduce the size?
Right. I want to reduce test time as possible
- For faster test on developer environment
- To reduce CI infra overhead
It adds the Conv2d test model with padding and group set. ONE-DCO-1.0-Signed-off-by: Jonghwa Lee <jonghwa3.lee@samsung.com>
batcheu
changed the title
batcheu
force-pushed
the
add_conv2d_test
branch
from
b96982b to
79380a4
Compare
batcheu
commented
Feb 24, 2026
| class net_Conv2d(torch.nn.Module): | ||
| def __init__(self): | ||
| super().__init__() | ||
| self.op = torch.nn.Conv2d(4, 4, 1, padding=(1, 1), groups=2) |
Contributor
Author
There was a problem hiding this comment.
I reduced tensor size referring to @hseok-oh comment.
loc("/op/Conv/split_input"): error: 'Circle.split' op output #0 should be 'tensor<1x5x5x2xf32>' instead got 'tensor<1x3x3x2xf32>
Contributor
Author
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
It adds the Conv2d test model with padding and group set.
ONE-DCO-1.0-Signed-off-by: Jonghwa Lee jonghwa3.lee@samsung.com