-
Notifications
You must be signed in to change notification settings - Fork 112
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Integrating Keras capabilities to OPM
- Loading branch information
1 parent
eb6e6ca
commit 9dabbe9
Showing
30 changed files
with
2,281 additions
and
0 deletions.
There are no files selected for viewing
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
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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,22 @@ | ||
These ML modules are heavily modifiying and extending the previous work done in Kerasify by Maevskikh and Rose. Kerasify is a library for running trained Keras models from a C++ platform. Our implementation is also compliant with the automatic differentiation approach used in OPM. The implementation works with Python v.3.9.0 and above (up to <=3.12.0). | ||
|
||
|
||
-Unit tests are generated by: | ||
|
||
$ python3 generateunittests.py | ||
|
||
|
||
-To compile run the unit tests: | ||
|
||
$ make ml_model_test | ||
$ ./bin/ml_model_test | ||
TEST tensor_test | ||
TEST dense_1x1 | ||
TEST dense_10x1 | ||
TEST dense_2x2 | ||
TEST dense_10x10 | ||
TEST dense_10x10x10 | ||
TEST relu_10 | ||
TEST dense_relu_10 | ||
TEST dense_tanh_10 | ||
TEST scalingdense_10x1 |
Oops, something went wrong.