Skip to content
This repository has been archived by the owner on Nov 17, 2023. It is now read-only.

[MXNET-1083] Add the example to demonstrate the inference workflow using C++ API. #12930

Closed
wants to merge 130 commits into from
Closed

[MXNET-1083] Add the example to demonstrate the inference workflow using C++ API. #12930

wants to merge 130 commits into from

Conversation

leleamol
Copy link
Contributor

Description

The PR includes an example that demonstrates the inference workflow using C++ API.

Checklist

Essentials

Please feel free to remove inapplicable items for your PR.

  • [y] The PR title starts with [MXNET-$JIRA_ID], where $JIRA_ID refers to the relevant JIRA issue created (except PRs with tiny changes)
  • [y] Changes are complete (i.e. I finished coding on this PR)
  • [y] All changes have test coverage:
  • Unit tests are added for small changes to verify correctness (e.g. adding a new operator)
  • Nightly tests are added for complicated/long-running ones (e.g. changing distributed kvstore)
  • Build tests will be added for build configuration changes (e.g. adding a new build option with NCCL)
  • [y] Code is well-documented:
  • For user-facing API changes, API doc string has been updated.
  • For new C++ functions in header files, their functionalities and arguments are documented.
  • For new examples, README.md is added to explain the what the example does, the source of the dataset, expected performance on test set and reference to the original paper if applicable
  • Check the API doc at https://mxnet-ci-doc.s3-accelerate.dualstack.amazonaws.com/PR-$PR_ID/$BUILD_ID/index.html
  • To the my best knowledge, examples are either not affected by this change, or have been fixed to be compatible with this change

Changes

  • Feature1, tests, (and when applicable, API doc)
  • Feature2, tests, (and when applicable, API doc)
    The example demonstrates how to load the pre-trained model and associated parameter files.
    The model and parameter files can be specified as command line arguments.

Comments

  • If this change is a backward incompatible change, why must this change be made.
  • Interesting edge cases to note here

This was referenced Oct 23, 2018
Closed
Closed
@roywei
Copy link
Member

roywei commented Oct 23, 2018

@leleamol Thanks for the contribution!
@mxnet-label-bot [pr-awaiting-review]

@marcoabreu marcoabreu added the pr-awaiting-review PR is waiting for code review label Oct 23, 2018
nswamy and others added 19 commits October 23, 2018 16:49
@nswamy
use ResourceScope in Model/Trainer/FeedForward.scala (apache#12882)
6b4df85 
* use ResourceScope in Model/Trainer/FeedForward.scala

* add moveToOuterScope public method to move resources to a outerScope if it exists

* fix memory leak in FeedForward.scala by making it a native resource and disposing argparams, auxParams
in dispose() method
@lebeg @nswamy
Disabled flaky test: test_gluon_gpu.test_slice_batchnorm_reshape_batc…
7d0f7d6 
…hnorm (apache#12768)
@apeforest @anirudh2290
Fix the operator API documentation (apache#12942)
af55104 
* Fix the operator API documentation

* update message
@leleamol
Made the load methods private, added code to print the last error mes…
9121d68 
…sage in case of exceptions.
@eric-haibin-lin
fix indpt[0] for take(csr) (apache#12927)
57176cd
@eric-haibin-lin
getnnz operator for CSR matrix (apache#12908)
1b96fc9 
* nnz

* update err msg

* skip nnz test on gpu
@aaronmarkham @zhreshold
fix broken docs (apache#12871)
50028e9
@leleamol
Organized the code as per feedback. The interface for Predict class i…
04c8b40 
…s similar to scala/java API
@frankfliu @szha
Add bytearray support back to imdecode (apache#12855, apache#12868) (a…
96df2c5 
…pache#12912)

1. Avoid raise exception when input is bytearray.
2. Avoid OpenCV crash for empty input.
3. Added unittests.
@ThomasDelteil @szha
Update tree lstm example (apache#12960)
d93467e 
* update tree lstm example

* update README.md

* Update README.md
@ThomasDelteil @szha
Update bilstm integer array sorting example (apache#12929)
a39152b 
* Update the bilstm example to Gluon

* Update formating

* Update example/vae/VAE_example.ipynb

Co-Authored-By: ThomasDelteil <[email protected]>
@apeforest @eric-haibin-lin
Fix the bug of assigning large integer to NDArray (apache#12921)
ffe551e 
* remove num_labels check in multibox_target

* add unit test

* test both cpu and gpu

* add contrib operator to GPU unit test

* do not test all contrib operator in gpu

* Fix the large int assign problem
@azai91 @sandeep-krishnamurthy
Refactor mkldnn test files (apache#12410)
fef9b5c 
* move mkldnn helper funcs to diff file

* create test file to test helper functions

* update comments in header

* move helpers into include dir

* fix lint

* update comment

* add stdlib headers

* remove unused headers

* add endif

* add missing header

* add inlines

* fix lint

* move copyfrom test to mkldnn_test
@DickJC123 @eric-haibin-lin
CudnnFind() usage improvements (apache#12804)
ee5f699 
* Add mx.context.gpu_memory_info() to python api for flexible tests.

* Add test_gluon_gpu.py:test_large_models to show cudnnFind headroom issue.

* Output model sizes tried by test_gluon_gpu.py:test_large_models.

* Fix perl interface to MXGetGPUMemoryInformation.

* Increase difficulty of test_gluon_gpu.py:test_large_models.

* Forgot a file in fix for perl.

* Modify test to pass on no-cudnn CI runner.

* Mutex algo reg updates, serialize cudnnFind calls.

* Fix for cudnnFind memory headroom issue.

* Fix cpplint.

* Respond to reviewers comments.

* Guard against improper MXNET_GPU_MEM_LARGE_ALLOC_ROUND_SIZE values.

* Fix potentially unassigned var.
@aaronmarkham @indhub
fix mac r install and windows python build from source docs (apache#1…
ffeaf31 
…2919)

* fix mac r install and windows python build from source docs

* reorder macos r install instructions
@roywei @marcoabreu
enable batchnorm unit tests (apache#12986)
2f6d224 
* enable bn unit tests

* travis timed out, trigger ci
@rahul3 @marcoabreu
Update CONTRIBUTORS.md (apache#12996)
148819b 
I have made two minor contributions with pull requests so far. I forgot to add my name here earlier.
@aaronmarkham @nswamy
fix Sphinx errors for tutorials and install ToCs (apache#12945)
1555735 
* missing line break fix for tutorials toc

* fix the install index toc errors
@gaurav-gireesh @szha
[MXNET -1030] Cosine Embedding Loss (apache#12750)
1f971c2 
* COsine Embedding Loss function added

* Added unit tests for Cosine Embedding Loss Function

* Added Latex code for formula for cosine embedding loss

* Fixing document rendering

* Fixing documentation issue

* PR Comments addressed for using F (NDArray or Symbol) to calculate norm, renaming parameters

* Markdown file updated. Added entry for CosineEmbeddingLoss

* Added a line after .. math:: to fix documentation

* Documentation check - pylint fix

* Formula update

* Making the formula simpler for correct rendering incrementally - Update 1

* Making the formula simpler for correct rendering incrementally - Update 2

* Making the formula simpler for correct rendering incrementally - Update 3

* Making the formula simpler for correct rendering incrementally - Update 4

* Making the formula simpler for correct rendering incrementally - Update 5

* Trigger CI

*  making the utility function cosine similarity internal

* Added a test case for label = -1, for dissimilar vectors

* Refactored names of parameters to the loss functions and updated the formula in docstring

* PR comments addressed changes in documentation

* Added random input vectors and labelled tests

* Renaming variables

* Pylint issues fixed

* Resolving conflicts

* Pylint issues fixed

* Style issues fixed trailing whitespaces removed

* Review comment addressed, sample_weight added in the parameter

* Trigger CI

* Reordered Parameter description

* comments addressed - spelling errors

* nit comments addressed

* Trigger CI

* Trugger CI

* Trigger CI

* Trigger CI
eric-haibin-lin and others added 22 commits November 13, 2018 16:31
@eric-haibin-lin @szha
Add gauss err function operator (apache#13229)
f5ba267 
* erf

register gpu

* add doc
@KellenSunderland @szha
Add Turing and Volta support to arch_name (apache#13168)
b8e36e0
@jlcontreras @sandeep-krishnamurthy
Bugfix in ci/docker_cache.py (apache#13249)
2eb76b5
@zachgk @nswamy
Fix scaladoc build errors (apache#13189)
8cb73ef 
* Fix scaladoc errors from missing classpath

Remove duplicate scalastyle plugin

* Fix scaladoc warnings

Also enable and fix all feature and deprecation warnings
@eric-haibin-lin @sandeep-krishnamurthy
Add missing documentations for getnnz (apache#13128)
ead3af2
@vdantu @sandeep-krishnamurthy
Addressed ONNX module documentation warnings and added notes for shor…
100a4aa 
…t-form representation (apache#13259)
@azai91 @cjolivier01
Manually track num_max_thread (apache#12380)
7541021 
* use cached version of get thread max

* reserve core affects omp singleton

* omp_thread_max_ updated in one line

* remove enabled block

* add brackets

* re-add excluded reserved

* add missing var

* refactor macro
@mseth10 @anirudh2290
adding unit test for MKLDNN FullyConnected operator (apache#12985)
cf991ff 
* adding unit test for MKLDNN FullyConnected operator

* removing mkldnn filter

* removing mkldnn filter
@Roshrini @sandeep-krishnamurthy
Doc fixes (apache#13256)
339e085
@roywei @nswamy
fix train mnist for inception-bn and resnet (apache#13239)
1ef83c9
@zheng-da @eric-haibin-lin
Fix a bug in index_copy (apache#13218)
e7f9770 
* fix.

* add test.

* retrigger
@vdantu @eric-haibin-lin
Addressed doc issues (apache#13165)
0259254 
* Addressed doc issues

* Update optimizer.py
@marcoabreu
Force APT cache update before executing install (apache#13285)
226f9cb
@ankkhedia @indhub
[Example] Gradcam consolidation in tutorial (apache#13255)
8ac7fb9 
* fixing gradcam

* changed loading parameters code

* fixing type conversions issue with previous versions of matplotlib

* gradcam consolidation

* creating directory structures in utils

* changing location

* empty commit
@NRauschmayr @indhub
[MXNET-1203] Tutorial infogan (apache#13144)
97fdfd9 
* Adding info_gan example

* adjust paths of filenames

* Update index.md

* Update index.md

* Update index.md

* Update info_gan.md

Added an image

* Update info_gan.md

Applied some fixes

* Update info_gan.md

Applied some fixes

* Update info_gan.md

Applied some fixes

* Update info_gan.md

* Updated index.md file

* Updated index.md file

* change links

* Fixed typo

* Delete Untitled.ipynb

* Adding Vishaals comments

* Adding Anirudh's comments

* Fixed some bugs

* Adding Anirudh's comments

* some minor fixes
@sandeep-krishnamurthy @eric-haibin-lin
Remove obsolete memory cost example (apache#13235)
c78f89f
@leleamol
Add the example to demonstrate the inference workflow.
6147b06
@leleamol
Fixed the example to no load synset file if not specified.
018d047
@leleamol
Made the load methods private, added code to print the last error mes…
8a43f89 
…sage in case of exceptions.
@leleamol
Organized the code as per feedback. The interface for Predict class i…
0b02133 
…s similar to scala/java API
@leleamol
Addressed the review comments. Optimized code to load the mean image …
c349eb2 
…only once. Removed the image_data instance member.
@leleamol
Merged the recent changes.
8cb9928
@leleamol leleamol closed this Nov 16, 2018
@leleamol
Copy link
Contributor Author

Opened a new PR #13294

@leleamol leleamol deleted the inception-inference branch December 19, 2018 00:45
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Reviewers

@cjolivier01 cjolivier01 cjolivier01 left review comments

@nswamy nswamy nswamy requested changes

@szha szha Awaiting requested review from szha szha is a code owner

@anirudh2290 anirudh2290 Awaiting requested review from anirudh2290

@gigasquid gigasquid Awaiting requested review from gigasquid gigasquid is a code owner

@marcoabreu marcoabreu Awaiting requested review from marcoabreu marcoabreu is a code owner

@sergeykolychev sergeykolychev Awaiting requested review from sergeykolychev sergeykolychev is a code owner

@yzhliu yzhliu Awaiting requested review from yzhliu yzhliu is a code owner

Assignees
No one assigned
Labels
pr-awaiting-review PR is waiting for code review
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.