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.

Sign up for GitHub

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

[Draft] Add Dredd test for dynamic shape Multiply #14143

Closed
wants to merge 2 commits into from
Closed

[Draft] Add Dredd test for dynamic shape Multiply #14143

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4aade1d
[res] Add TFLiteRecipe for dynamic shape Multiply
qsunki Sep 30, 2024
d7ad88a
[circle2circle-dredd-recipe-test] Add Inf_Mul_000 test
qsunki Oct 2, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions compiler/circle2circle-dredd-recipe-test/test.lst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -147,3 +147,4 @@ Add(REGRESS_Issue_13863 PASS substitute_pack_to_reshape)

# SHAPE INFERENCE test
Add(Inf_Pad_000 PASS)
Add(Inf_Mul_000 PASS)
1 change: 1 addition & 0 deletions compiler/common-artifacts/exclude.lst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,6 +51,7 @@ tcgenerate(FullyConnected_I4_002)
tcgenerate(FullyConnected_U8_000)
tcgenerate(GatherNd_000)
tcgenerate(GatherNd_001)
tcgenerate(Inf_Mul_000) # TestDataGenerator does not support unknown dimension
tcgenerate(L2Pool2D_U8_000)
tcgenerate(Log_000)
tcgenerate(MatMul_000)
Expand Down
30 changes: 30 additions & 0 deletions res/TensorFlowLiteRecipes/Inf_Mul_000/test.recipe
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,30 @@
operand {
Copy link
Contributor

Choose a reason for hiding this comment

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

plz split this to another PR

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Ah, then I'll mark this PR as a draft and create separate PRs.

name: "ifm1"
type: FLOAT32
shape { dim: 1 dim: 4 dim: 1 dim: 1 }
shape_signature { dim: 1 dim: -1 dim: -1 dim: -1}
}
operand {
name: "ifm2"
type: FLOAT32
shape { dim: 1 dim: 1 dim: 4 dim: 1}
shape_signature { dim: 1 dim: -1 dim: 4 dim: -1}
}
operand {
name: "ofm"
type: FLOAT32
shape { dim: 1 dim: 1 dim: 4 dim: 1 }
shape_signature { dim: 1 dim: -1 dim: 4 dim: -1}
}
operation {
type: "Mul"
input: "ifm1"
input: "ifm2"
output: "ofm"
mul_options {
activation: NONE
}
}
input: "ifm1"
input: "ifm2"
output: "ofm"
5 changes: 5 additions & 0 deletions res/TensorFlowLiteRecipes/Inf_Mul_000/test.rule
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
# To check if dynamic dimension properly inferred

RULE "VERIFY_FILE_FORMAT" $(verify_file_format) '=' 1

RULE "MUL_SHAPE" $(tensor_shape ofm) '=' [1,-1,4,-1]