-
Notifications
You must be signed in to change notification settings - Fork 409
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
Reshape fixes: don't repack stream for flatten; remove final reshape #443
Merged
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
This was
linked to
issues
Nov 8, 2021
vloncar
reviewed
Nov 8, 2021
thesps
reviewed
Nov 8, 2021
I'm happy with the state of both developments:
Only question: do you want the CI test for the Some detail on the resource saving for that model:
|
Add a test for a model with Reshape as the final layer
Yes, now merged! |
thesps
approved these changes
Nov 8, 2021
thesps
added a commit
that referenced
this pull request
Nov 9, 2021
…443) * fix 2 reshape issues: don't reshape streams for flatten and remove final reshape * Add a test for a model with Reshape as the final layer * swap * only remove for io_parallel; warn for both io_parallel and io_stream Co-authored-by: Sioni Summers <[email protected]>
thesps
added a commit
that referenced
this pull request
Nov 11, 2021
…443) * fix 2 reshape issues: don't reshape streams for flatten and remove final reshape * Add a test for a model with Reshape as the final layer * swap * only remove for io_parallel; warn for both io_parallel and io_stream Co-authored-by: Sioni Summers <[email protected]>
jmitrevs
pushed a commit
that referenced
this pull request
Dec 2, 2021
* fix batched multiple inputs * Fixed 'qkeras_mnist_dense' example build problem #423 * Update for pyyaml 6.0 (#435) * yaml.safe_load instead of yaml.load * Use yaml.safe_load in converters __init__.py * `axi_stream_driver` update (#420) * Update `zcu102` and `pynq-z2` `axi-stream` driver * Reshape fixes: don't repack stream for flatten; remove final reshape (#443) * fix 2 reshape issues: don't reshape streams for flatten and remove final reshape * Add a test for a model with Reshape as the final layer * swap * only remove for io_parallel; warn for both io_parallel and io_stream Co-authored-by: Sioni Summers <[email protected]> * Reorder loops in im2col_2d_cl given resource strategy issue. Reenable relevant test. Use 5000 MNIST samples rather than full dataset for faster testing * Support applying Softmax over multidimensional tensors (#384) * Support softmax over multidimensional tensors * Style cleanup * Added axis part in keras_to_hls.py * Added some extensions to test_softmax.py but multidimensional softmax is still getting bad performances (i.e. below the one set in the assertion) * Clean up the softmax test * Make sure io_parallel softmax is not used on multi-dim input Co-authored-by: nicologhielmetti <[email protected]> * Disable some unsupported layers * Set appropriate data type for quantized_relu activations * Display unsigned types properly in profiling * Add a QONNX test, update the image * Don't convert Quant to BatchNorm. Convert weight-Quant to Constant, and activation-quant to Activation Co-authored-by: Javier M. Duarte <[email protected]> Co-authored-by: Thea Aarrestad <[email protected]> Co-authored-by: David Siorpaes <[email protected]> Co-authored-by: Nicolò Ghielmetti <[email protected]> Co-authored-by: vloncar <[email protected]>
calad0i
pushed a commit
to calad0i/hls4ml
that referenced
this pull request
Jul 1, 2023
…astmachinelearning#443) * fix 2 reshape issues: don't reshape streams for flatten and remove final reshape * Add a test for a model with Reshape as the final layer * swap * only remove for io_parallel; warn for both io_parallel and io_stream Co-authored-by: Sioni Summers <[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.
2 reshape-related fixes:
ReshapeStream
optimizer: don't repack stream for flatten; Addresses Flatten layer creating a lot of logic #408RemoveFinalReshape
optimizer to remove reshape if it's the final layer; Addresses Compilation error with concatenate layer #415repack_stream.py
, but it could be moved