Eliminate nop Convert at the beginning of the MOC pipeline #26872
Conversation
This file contains 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
github-actions
bot
added
the
category: transformations
itikhono
commented
Oct 1, 2024
src/common/transformations/src/transformations/common_optimizations/moc_transformations.cpp
Outdated
Show resolved
Hide resolved
itikhono
changed the title
CuriousPanCake
approved these changes
Oct 2, 2024
github-merge-queue bot
pushed a commit
that referenced
this pull request
Oct 3, 2024
### Details:
Added NopElimination at the beginning of the MOC
After pytorch conversion, we can see useless Convert (fp32 to fp32) in
the graph
```
Constant (fp32) -> Node1
-> Convert( to fp32) -> Node2
```
So after ConstantFolding, we will get
```
Constant (fp32) -> Node1
Constant (fp32) -> Node2
```
Deletion of the convert above fixes the duplication of the constant
### Tickets:
- *CVS-151490*
github-merge-queue
bot
removed this pull request from the merge queue due to failed status checks
github-merge-queue bot
pushed a commit
that referenced
this pull request
Oct 4, 2024
### Details:
Added NopElimination at the beginning of the MOC
After pytorch conversion, we can see useless Convert (fp32 to fp32) in
the graph
```
Constant (fp32) -> Node1
-> Convert( to fp32) -> Node2
```
So after ConstantFolding, we will get
```
Constant (fp32) -> Node1
Constant (fp32) -> Node2
```
Deletion of the convert above fixes the duplication of the constant
### Tickets:
- *CVS-151490*
github-merge-queue
bot
removed this pull request from the merge queue due to failed status checks
|
TensorFlow2 Layer Tests failed in post-commit, investigating |
|
waiting for #26912 |
evkotov
approved these changes
Oct 7, 2024
pkowalc1
pushed a commit
to pkowalc1/openvino
that referenced
this pull request
Oct 9, 2024
…oolkit#26872) ### Details: Added NopElimination at the beginning of the MOC After pytorch conversion, we can see useless Convert (fp32 to fp32) in the graph ``` Constant (fp32) -> Node1 -> Convert( to fp32) -> Node2 ``` So after ConstantFolding, we will get ``` Constant (fp32) -> Node1 Constant (fp32) -> Node2 ``` Deletion of the convert above fixes the duplication of the constant ### Tickets: - *CVS-151490* --------- Co-authored-by: Ilya Lavrenov <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Details:
Added NopElimination at the beginning of the MOC
After pytorch conversion, we can see useless Convert (fp32 to fp32) in the graph
So after ConstantFolding, we will get
Deletion of the convert above fixes the duplication of the constant
Tickets: