Repository navigation
feat(akida2/portrait128): person segmentation example with trained models - #119
Open
mtorresBrainChip wants to merge 5 commits into
Open
mtorresBrainChip wants to merge 5 commits into
mtorresBrainChip wants to merge 5 commits into
Conversation
Refs HUB-43
… model zoo Refs HUB-43
…outputs Refs HUB-43
This file contains hidden or 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Refs HUB-43
Adds an Akida 2 example for Portrait128 person segmentation, ported from
akida_models(akida_unet_portrait128): an AkidaNet 0.5 encoder with atransposed-convolution decoder, the first Akida 2 example that upsamples.
Training run
bash portrait128_train.sh, 50 epochs from ImageNet encoder weights,6 h 51 min on an RTX 2080 Ti
weight penalty as computed on the quantized layers; the cross-entropy itself is
0.10 (float: 0.13).
FPGA benchmark (Akida 2, 25 MHz; projected at the 1 GHz AKD2500 target)
half the latency. Benchmark notebook executed on the FPGA (about 35 min).
Decisions
DepthwiseConv2DTransposeneeds 8-bit inputs and weights,so a 4-bit model falls back to software. BrainChip's model zoo also publishes this
model at 8 bits only. Added to
.claude/knowledge/akida.md.Repo-wide changes (please review)
check_content.py: exempt Jupytext notebook mirrors from the copyright check(they must start with their YAML header). New scripts without a header are still flagged.
.gitignore: ignorewget-log*andnohup.out.Open items
mixed-precision 4-bit (unconfirmed, see the knowledge base entry); more float epochs
(QAT improved on the float model).