Граф коммитов

607 Коммитов

Автор SHA1 Сообщение Дата
hlu1 fefbb0061e [Bugfix] Fix caffe2 nnvm frontend (#2996) 2019-04-12 21:33:45 -04:00
James Gilles 5178506255 [REFACTOR] Use more TypedPackedFuncs (#2981)
* Add `set_body_simple` to Registry, refactor a lot of code to use it

* Add more types to Relay PackedFuncs

* Add Registry::set_body_method to easily make Node methods into
PackedFuncs

* Add set_body_method, set_body_node_method; start typing api_lang

* Add some docs, remove unused script

* Fix mysterious linter problem

* Touch up api_ir.cc

* Fix some issues with TOPI argument counts

* Revert changes to topi.cc to avoid problems with optional arguments

* A little more cleanup

* Type more of the api _ functions

* Whitespace

* Finalize names and docs for new registry helpers

* Update docs
2019-04-10 14:28:25 -07:00
Tianqi Chen cffb4fba03
[HEADER] Add Header to Comply with ASF Release Policy (#2982)
* [HEADER] ASF header dir=include

* [HEADER] ASF Header dir=src

* [HEADER] ASF Header -dir=python

* [HEADER] ASF header dir=topi

* [HEADER] ASF Header dir=nnvm

* [HEADER] ASF Header -dir=tutorials

* [HEADER] ASF Header dir=tests

* [HEADER] ASF Header -dir=docker

* fix whitespace

* [HEADER] ASF Header -dir=jvm

* [HEADER] ASF Header -dir=web

* [HEADER] ASF Header --dir=apps

* [HEADER] ASF Header --dir=vta

* [HEADER] ASF Header -dir=go

* temp

* [HEADER] ASF Header --dir=rust

* [HEADER] Add ASF Header --dir=cmake

* [HEADER] ASF Header --dir=docs

* [HEADER] Header for Jenkinsfile

* [HEADER] ASF Header to toml and md

* [HEADER] ASF Header to gradle

* Finalize rat cleanup

* Fix permission

* Fix java test

* temporary remove nnvm onnx test
2019-04-07 21:14:02 -07:00
MORITA Kazutaka 162eab44dd [DOCKER][FRONTEND] Run DarkNet tests (#2673)
* [DOCKER][FRONTEND] Run DarkNet tests

* update tests to pass CI
2019-04-01 09:00:23 -07:00
Haichen Shen c6339730ad [Tutorial] Cache the test data in tutorial (#2923) 2019-03-30 00:11:55 -04:00
Mark Rogers 53511bf1a4 Unified error handling in NNVM and Relay frontends (#2828) 2019-03-28 22:18:18 -04:00
Haichen Shen e3206aa84d [TEST] Cache test data (#2921) 2019-03-28 22:12:25 -04:00
hlu1 a02916b5ae winograd_nnpack (#2721) 2019-03-25 20:12:32 -07:00
Siva bb3c815140
[FRONTEND][TENSORFLOW] Enhance with left over patches from NNVM. (#2757)
* [FRONTEND][TENSORFLOW] Enhance with left over patches from NNVM.

commit 76188a4
Author: Siva sivar.b@huawei.com
[NNVM][TENSORFLOW] bugfix. (#2444)

commit 6737739
Author: Ashutosh Parkhi ashutosh.parkhi@imgtec.com
[Tensorflow] Support for Crop (#2285)

commit f6c3f99
Author: Alexey Romanov alexey.v.romanov@gmail.com
[FRONTEND][TENSORFLOW] Use input shapes directly instead of 1-element lists (#2242)

commit e5d92e1
Author: Dominic Symes 36929632+dominicsymes@users.noreply.github.com
[FRONTEND][TENSORFLOW] Bugfix (#2326)

commit 00d509d
Author: Alexey Romanov alexey.v.romanov@gmail.com
[FRONTEND][TENSORFLOW] Support Unstack and Split (#2105)

commit df9d3ad
Author: Siva sivar.b@huawei.com
[FRONTEND][TENSORFLOW] Bugfix (#2267)

commit d1a0c90
Author: Zhebin Jin zhebin.jzb@alibaba-inc.com
[FRONTEND][TENSORFLOW]Add Split and realdiv op support (#2123)
* Add Split and realdiv op support
* Fix the pad calculation in the case of dilated convolution

* 	* review comments

* 	* resnet fix.

* 	* review comments
2019-03-19 12:25:07 +05:30
lixiaoquan 7182201d89 Fix a bug in nnvm to relay converter. (#2756) 2019-03-13 22:15:36 -07:00
Tianqi Chen 5e3ceaa073
[DOCKER] Update docker protocol (#2793) 2019-03-12 14:34:34 -07:00
Tianqi Chen 8fd847195b
[DOCS] Phase out nnvm tutorials (#2783) 2019-03-12 09:37:41 -07:00
Tianqi Chen 7226c01065
[TEST] Hotfix CI outrage after TF in docker update (#2781) 2019-03-11 17:52:10 -07:00
Yao Wang d2f29ba558 [Object Detection] Gluoncv SSD support on CPU (#2353) 2019-03-11 11:41:46 -07:00
Yong Wu f7eff09503 [relay][frontend] TensorFlow saved model support (#2586)
* [relay][frontend] TensorFlow saved model support

* Add Examples section

* keep one copy of tensorflow_parser in relay
2019-03-12 00:10:12 +05:30
abergeron 2239508be4 [Relay] Add logical operators (#2743) 2019-03-08 20:46:01 -05:00
MORITA Kazutaka 695647db94 Improve NNVM to Relay conversion (#2734)
* Improve NNVM to Relay conversion

* fix pylint

* support __lshift_scalar__, abs, ceil, floor, and trunc to pass CI
2019-03-07 21:35:46 -08:00
Ashutosh Parkhi af69f8730b [Tensorflow, NNVM, TOPI] Support for logical operators (#2453) 2019-03-03 10:20:59 -08:00
Hao Jin 8f5c27bd44 support MXNet _minimum and _maximum (#2709) 2019-03-01 09:26:45 -08:00
Yizhi Liu ee79703c3c [Lang] Layout in TVM node system (#2509)
* move layout.h & layout.cc from relay to tvm

* change ConvertLayout in relay to bijectiveLayout->Forward/backward

* add first test case

* add LayoutAxis

* add LayoutAxis struct and compiles

* simplify BijectiveLayout rule consturct

* polish func name for Layout, move impl to .cc, remove Layout::defined(), add defined() checker

* partially add layout py support

* add layout test cases

* add doc for tvm.layout & tvm.bijective_layout

* fix lint

* fix lint

* fix layout name generation bug

* fix layout typo

* address comments and add topi.layout_transform

* layout.h->data_layout.h, test_lang_layout.py->test_lang_data_layout.py
2019-02-28 12:26:22 +08:00
lixiaoquan dc7a7cbd42 Support mean in NNVM to Relay converter. (#2680) 2019-02-27 11:46:05 -08:00
Hao Jin 3b328b9085 add converter for MXNet slice in nnvm and relay (#2662) 2019-02-27 00:01:52 -08:00
Siju 0edb332fd9 REGION op removed from topi and added in darkent frontend (#2275) 2019-02-26 20:11:25 -08:00
Junru Shao 4ba30478a8 Fix -Wreturn-std-move and -Wself-assign-overloaded (#2669) 2019-02-24 12:24:32 -08:00
Hao Jin c4f03de367 add MXNet converter for where operator for both NNVM and Relay (#2647) 2019-02-21 22:14:08 -08:00
Marcus Shawcroft e20ef0d4a2 Fix pylint 2.2.2 gripes. (#2642) 2019-02-21 10:43:07 -08:00
Junru Shao 81334be34d [RUNTIME][NDArray] Allowing External Libraries to Subclass NDArrays (#2613) 2019-02-21 08:57:13 -08:00
Przemyslaw Tredak 8518c7ddb5 Fix the FInplaceIdentity (#2572) 2019-02-18 16:21:02 -05:00
Yizhi Liu c71654277d fix get layout in to_relay (#2610) 2019-02-15 23:33:18 -06:00
Yong Wu f347b52513 Get tags of saved model automatically
Remove exception trail in tf parser error message

Fix lint

Fix comments
2019-02-08 22:13:47 -08:00
Zhi Chen 916576c0c7 Support TensorFlow saved model
TF parser: return the consistent error message to error handler
2019-02-08 22:13:47 -08:00
Yong Wu f1782f3eb7 Add tf parser wrapper, infer shape automatically 2019-02-08 22:13:47 -08:00
Pedro Larroy 2da23bd869 Optimize move semantics of NodeEntry reducing copies of shared_ptr which causes atomic contention (#2576) 2019-02-08 10:18:50 -08:00
雾雨魔理沙 390b744588 Update plan_memory.cc (#2574) 2019-02-07 09:50:52 -08:00
Siva 2f859d712d [RELAY][FRONTEND] Tensorflow frontend. (#2216)
* [RELAY][FRONTEND] Tensorflow frontend support.

* 	* LSTM removed for a while.

* 	* basic ops are good.

* 	* nn wip

* 	* wip

* 	* python2.7 corrections.

* * NN ops are good.

* * e2e models working good

* 	* all good except LSTM

* 	* rebase, tutorials and CI trigger.

* 	* CI errors.

* 	* enable opt_level=3

* 	* Docstrings cleanup. testing.tf utils moved to relay from nnvm.

* 	* tutorials update.

* 	* LSTM work good now.

* 	* Rebase

* 	* CI error

* 	* enable PTB.

* 	* rebase.

* 	* tutorials

* Update python/tvm/relay/frontend/tensorflow.py

Co-Authored-By: srkreddy1238 <sivar.b@huawei.com>

* 	* review comments.

* 	CI fix.

* 	* review comments.
2019-02-05 15:11:17 -08:00
Yizhi Liu 881a78b3d6 [Relay][Frontend] CoreML Support (#2476)
* [Relay][Frontend] Add CoreML Support

* pip install six in CI

* remove triggering nnvm coreml test

* set opt_level=2 for nnvm coreml test case
2019-01-29 16:19:36 -08:00
Anthony Mai 75f91c45d7 Optimize Linux shared library modules (*.so files) (#2445) 2019-01-28 21:14:18 -08:00
Kuan Hsh Chen 45456b1495 Fix typo (#2467) 2019-01-19 11:41:30 -08:00
Siva 76188a43d0 [NNVM][TENSORFLOW] bugfix. (#2444) 2019-01-16 15:02:38 -08:00
Ashutosh Parkhi 6737739c37 [Tensorflow] Support for Crop (#2285)
fixes

fixes
2019-01-14 16:15:42 +05:30
Haichen Shen a61d3b4160
[FRONTEND][TEST] Remove duplicated frontend tests (#2414)
* Remove duplicated frontend tests

* Add test for nnvm to relay

* Add test to script

* Remove dcgan in nnvm_to_relay test due to unsupported op in cuda

* Fix bug in converting conv2d from nnvm to relay

* Fix dropout
2019-01-11 22:38:55 -08:00
Joshua Z. Zhang 30a5a6007d [RELAY][FRONTEND]Onnx to relay frontend (#2302) 2019-01-11 14:36:52 -08:00
Wu Zhao 394cf9f72a [ARM][Performance] Improve ARM CPU depthwise convolution performance (#2345)
* Add sptialpack schedule for arm cpu depthwise convolution

* Supply comments.
2019-01-11 17:49:09 +08:00
Joshua Z. Zhang a5784757e2 relax rtol atol for div/log operators (#2400) 2019-01-08 17:37:15 -08:00
Yang Chen f607d46cab relax rtol/atol checks on some onnx tests (#2403)
relax the error constraints on these tests due to likely
FP compuation accuracy issues.
2019-01-08 17:37:07 -08:00
Lianmin Zheng 426e3bb0a8 [RELAY] Port winograd ops to relay (#2356) 2019-01-07 08:46:34 -08:00
Alexey Romanov f6c3f99760 [FRONTEND][TENSORFLOW] Use input shapes directly instead of 1-element lists (#2242) 2018-12-29 16:16:59 +05:30
lixiaoquan 67fe4db0dc [NNVM] Fix dtype of output of mean. (#2334)
dtype of count is the same as dtype of inputs[0] when created, but its type may
  change when multiplied by inputs[0]->shape[i]. Which causes dtype of
  output is not same as dtype of input.
2018-12-26 09:49:17 -08:00
Dominic Symes e5d92e1b96 [FRONTEND][TENSORFLOW] Bugfix (#2326) 2018-12-24 13:08:45 -08:00
lixiaoquan d51644663e [NNVM] Fix dtype of output of pad. (#2331)
Dtype of output of pad should follows input, but if dtype of input is not float,
  output will still be float becase pad_value is float.
2018-12-24 09:37:55 -08:00