Neureka #1
Open
Neureka #1
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
…EMO (Frontnet, ResidualNet, Dronet, MV1-128) and 4 networks from Quantlab (2 MV2 and 2 MV1, 4 bits and 8 bits). Only MV1-128 output is failing given the wrong export of last fully-connected layer weights
… conv generation for Diana
…ublebuffering and blocking DMA transfers.
added 30 commits
December 22, 2022 21:43
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Outdated suggestions cannot be applied.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.
This PR fixes various issues related to:
ONNX spec compliance of DORY_node tensor name casting
In the current version, tensor names are explicitly cast to an integer type. According to the ONNX spec, tensor names are strings and there is no guarantee for those strings to only contain numerics. This PR fixes issue by enumerating tensor names explicitly along the topologically sorted list representing the graph.
Typing issues, Calling of undefined variables
In the current version, some functions use bitwise operations intended to work on integers, on data that is not guaranteed to be integer type. This PR fixes this by checking if the data can be cast to an integer w/o loss of precision, and then casting to an integer.
In the current version, some functions refer to variables that are only conditionally defined, with an implicit None value default. Since this is leads to Exceptions, this PR adds default definitions of such variables.