Skip to content
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.

Sign up for GitHub

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

Jump to bottom

feat: model compression draft for review #2767

Draft
wants to merge 17 commits into
base: main
Choose a base branch
from
Draft

feat: model compression draft for review #2767

wants to merge 17 commits into from

Conversation

rkuester
Copy link
Contributor

This draft PR exists for reviewing the complete model compression feature. It and its series of commits are not designed to be merged into main; it comes from a branch that is a mostly-squashed snapshot of the feature.

@rkuester
feat: add model compression draft
6eac102 
Add a feature-complete draft of the model compression feature in
a single commit. This commit isn't intended for merging into
mainline; it exists solely for reviewers and testers to take an
early look.
@rkuester
feat(compression): update model compression tools
661ad5e
@ddavis-2015
Copy link
Member

ddavis-2015 commented Nov 14, 2024 •
edited
Loading

Regarding the changes to .c and .h files:

  • Header files
tensorflow/lite/micro/micro_interpreter_context.h
tensorflow/lite/micro/micro_context.h
tensorflow/lite/micro/micro_allocator.h
tensorflow/lite/micro/kernels/kernel_util.h
tensorflow/lite/micro/compression/metadata_saved.h
tensorflow/lite/micro/compression.h
  • Unit testing framework
tensorflow/lite/micro/test_helper_custom_ops.cc
tensorflow/lite/micro/test_helper_custom_ops.h
tensorflow/lite/micro/test_helpers.cc
tensorflow/lite/micro/test_helpers.h
tensorflow/lite/micro/micro_utils.h
  • Kernel unit tests
tensorflow/lite/micro/kernels/transpose_conv_test.cc
tensorflow/lite/micro/kernels/fully_connected_test.cc
tensorflow/lite/micro/kernels/depthwise_conv_test.cc
tensorflow/lite/micro/kernels/conv_test_common.cc
tensorflow/lite/micro/kernels/conv_test.h
tensorflow/lite/micro/kernels/conv_test.cc
tensorflow/lite/micro/kernels/concatenation_test.cc
  • Other unit tests
tensorflow/lite/micro/recording_micro_allocator_test.cc
tensorflow/lite/micro/micro_resource_variable_test.cc
tensorflow/lite/micro/micro_interpreter_test.cc
  • Reference kernels
tensorflow/lite/micro/micro_resource_variable.cc
tensorflow/lite/micro/micro_resource_variable.h
tensorflow/lite/micro/kernels/transpose_conv.h
tensorflow/lite/micro/kernels/transpose_conv.cc
tensorflow/lite/micro/kernels/fully_connected.h
tensorflow/lite/micro/kernels/fully_connected.cc
tensorflow/lite/micro/kernels/depthwise_conv_common.cc
tensorflow/lite/micro/kernels/depthwise_conv.cc
tensorflow/lite/micro/kernels/conv_common.cc
tensorflow/lite/micro/kernels/conv.h
tensorflow/lite/micro/kernels/conv.cc
tensorflow/lite/micro/kernels/concatenation.cc
tensorflow/lite/micro/kernels/assign_variable.cc
  • Xtensa kernels
tensorflow/lite/micro/kernels/xtensa/conv.cc
tensorflow/lite/micro/kernels/xtensa/conv_hifi.cc
tensorflow/lite/micro/kernels/xtensa/conv_int16_reference.cc
tensorflow/lite/micro/kernels/xtensa/conv_int8_reference.cc
tensorflow/lite/micro/kernels/xtensa/conv_vision.cc
tensorflow/lite/micro/kernels/xtensa/depthwise_conv.cc
tensorflow/lite/micro/kernels/xtensa/depthwise_conv_hifi.cc
tensorflow/lite/micro/kernels/xtensa/depthwise_conv_vision.cc
tensorflow/lite/micro/kernels/xtensa/fully_connected.cc
tensorflow/lite/micro/kernels/xtensa/fully_connected_common_xtensa.cc
tensorflow/lite/micro/kernels/xtensa/fully_connected_int8.cc
tensorflow/lite/micro/kernels/xtensa/fully_connected_vision.cc
tensorflow/lite/micro/kernels/xtensa/transpose_conv.cc
  • Reference decompression code
tensorflow/lite/micro/kernels/decompress_test.cc
tensorflow/lite/micro/kernels/decompress_common.cc
tensorflow/lite/micro/kernels/decompress.h
tensorflow/lite/micro/kernels/decompress.cc
  • Xtensa decompression code
tensorflow/lite/micro/kernels/xtensa/decompress.cc
  • MicroInterpreter/MicroContext compression support
tensorflow/lite/micro/micro_interpreter_context.cc
tensorflow/lite/micro/micro_context.cc
tensorflow/lite/micro/micro_allocator.cc
  • Generic Benchmark application
tensorflow/lite/micro/tools/benchmarking/generic_model_benchmark.cc
tensorflow/lite/micro/tools/benchmarking/metrics.cc
tensorflow/lite/micro/tools/benchmarking/show_meta_data.cc.template
tensorflow/lite/micro/recording_micro_allocator.cc
tensorflow/lite/micro/recording_micro_allocator.h
  • CI test failure due to strict arena size
tensorflow/lite/micro/examples/micro_speech/micro_speech_test.cc
tensorflow/lite/micro/memory_arena_threshold_test.cc
  • Improved debug output
tensorflow/lite/micro/memory_planner/greedy_memory_planner.cc

ddavis-2015 and others added 15 commits November 20, 2024 18:40
@ddavis-2015
Pre-rebase empty commit
bd04eb2
@ddavis-2015
Squashed commit of the following:
1110543 
commit 300751d
Author: ddavis-2015 <[email protected]>
Date:   Wed Nov 20 12:03:16 2024 -0800

    Update to latest Cadence code.  Int8 any bitwidth on normal quant axis updated.

commit 0a49b2a
Author: ddavis-2015 <[email protected]>
Date:   Wed Nov 20 10:50:30 2024 -0800

    Add input tensor CRC to Generic Benchmark application.
    Only use -O3 -LNO:simd with the xtensa decompress.cc target.

commit 83dafce
Author: ddavis-2015 <[email protected]>
Date:   Mon Nov 18 17:23:58 2024 -0800

    cleanup

commit 2f8cead
Author: ddavis-2015 <[email protected]>
Date:   Mon Nov 18 13:29:33 2024 -0800

    Revert FakeMicroContext changes for alternate profiler.
    Add default alternate profiler implementation to MicroContext.

commit fddf003
Author: ddavis-2015 <[email protected]>
Date:   Mon Nov 18 12:29:26 2024 -0800

    Fix typo.

commit ae6a207
Author: ddavis-2015 <[email protected]>
Date:   Mon Nov 18 12:29:06 2024 -0800

    Implement alternate profiler for MicroInterpreter.
    Enable use of alternate profiler by decompression code.
    Enable use of alternate profiler by Generic Benchmark application.

commit 5e1a1c9
Author: ddavis-2015 <[email protected]>
Date:   Sun Nov 10 18:24:02 2024 -0800

    changes to make the memory planner debug output easier to interpret

commit f651c88
Author: ddavis-2015 <[email protected]>
Date:   Sun Nov 10 04:27:29 2024 -0800

    single pending ops queue
    process pending ops recursively

commit cfd9890
Author: ddavis-2015 <[email protected]>
Date:   Sun Nov 10 00:26:14 2024 -0800

    expand model_facade
    redo var handle tracking

commit 7776cda
Author: ddavis-2015 <[email protected]>
Date:   Tue Nov 5 13:24:58 2024 -0800

    remove [[maybe_unused]]

commit 40e7530
Author: ddavis-2015 <[email protected]>
Date:   Mon Nov 4 11:17:43 2024 -0800

    fix arena

commit 0d889e0
Author: ddavis-2015 <[email protected]>
Date:   Sat Nov 2 14:18:55 2024 -0700

    Fix MicroProfiler bug with ClearEvents().
    Add pre-inference profiling to the Generic Benchmark.
@ddavis-2015
last merge missed xtensa.inc file
414a55a
@ddavis-2015
Squashed commit of the following:
5408be9 
commit 2788d32
Author: ddavis-2015 <[email protected]>
Date:   Mon Dec 2 13:55:35 2024 -0800

    support for alternate decompression memory.
@ddavis-2015
Squashed commit of the following:
661e7cf 
commit 9353cda
Author: ddavis-2015 <[email protected]>
Date:   Fri Dec 6 12:40:59 2024 -0800

    fix concatenation unit test to match refactored unit test helper framework.

commit cc1fb65
Author: ddavis-2015 <[email protected]>
Date:   Fri Dec 6 11:36:09 2024 -0800

    place TestConvFloat() back into conv_test_common.cc

commit 81795e7
Author: ddavis-2015 <[email protected]>
Date:   Fri Dec 6 10:48:55 2024 -0800

    finished refactor of compression unit tests

commit b9c62b9
Author: ddavis-2015 <[email protected]>
Date:   Fri Dec 6 09:28:29 2024 -0800

    initial refactor of compression unit tests
@ddavis-2015 @rkuester
feat(compression): implement tensor compression feature
307c634 
Implement the tensor compression feature.

BUG=part of tensorflow#2636
@rkuester
Merge branch 'feat-compression' into 'compress-testing'
3714cab 
Bring branch 'compress-testing' up-to-date with what has been
merged into branch 'main'.
@ddavis-2015
fix merge error
b6d8b75
@ddavis-2015
fixes for optional bias tensor DCHECK.
2335754 
Fixes for FULLY_CONNECTED optional bias tensor.
@ddavis-2015
Fixes to transpose_conv for optional bias tensor when compression is …
0171244 
…enabled.
@ddavis-2015
Fixes to depthwise_conv for optional bias tensor when compression is …
47b4d12 
…enabled.
@ddavis-2015
Fixes to CONV for optional bias tensor when compression is enabled.
98b1444
@ddavis-2015
check compression metadata schema version.
c3e761f
@ddavis-2015
update compression documentation
d36a9f2
@ddavis-2015
update generic benchmark tool documentation
2d2dff6
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@rkuester @ddavis-2015