오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Aug 2019 09:52:39 +0000 (18:52 +0900)]
Support async execution in NNAPI (#6395)
Implement Event class to support async execution
Use internal async execution function for startCompute and wait
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Aug 2019 09:51:29 +0000 (18:51 +0900)]
Revise acl cl backend cmake (#6391)
- Set strict build option: nnfw_common
- Remove needless link
- Update header include for acl common
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Aug 2019 08:55:46 +0000 (17:55 +0900)]
Rename gather implementation in arm-compute-ex (#6388)
Rename CLGather and CLGatherKernel to CLGatherEx and CLGatherExKernel because acl 19.05 already have same name layer & kernel
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Aug 2019 08:46:19 +0000 (17:46 +0900)]
Revise acl neon backend cmake (#6393)
- Set strict build option: nnfw_common
- Remove needless link
- Update header include for acl common
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 8 Aug 2019 07:58:52 +0000 (16:58 +0900)]
[moco-tf] relocate input method in Concat import (#6394)
This will relocate input method in Concat after class declaration to put anonymous codes together
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 8 Aug 2019 07:43:00 +0000 (16:43 +0900)]
[moco-tf] Introduce ResolveConstantShape transform (#6379)
* [moco-tf] Introduce ResolveConstantShape transform
This commit introduces ResolveConstantShape transform, which is
responsible to replace determined TFShape node with TFConst.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
* Separate out condition check stage
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Aug 2019 07:42:30 +0000 (16:42 +0900)]
[loco] Update index on link (#6381)
Both "link" helpers now update the index of a corresponding node.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 8 Aug 2019 07:42:02 +0000 (16:42 +0900)]
[moco-tf] TFShape shape inference (#6373)
This commit implements TFShape node's shape inference.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Aug 2019 07:41:42 +0000 (16:41 +0900)]
[exo-tflite] Use shared shape inference framework by default (#6390)
This commit makes exo-tflite to use the shape inference framework
implemented in loco core by default.
Please note that it is possible to turn off this feature via setting
EXOTFLITE_USE_LOCO_SHAPE_INFERENCE as 0.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Aug 2019 07:39:37 +0000 (16:39 +0900)]
[loco] Simplify ReLU Graph Testcase (#6392)
Let's simplify ReLU Graph Testcase using GraphBuilder.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 8 Aug 2019 07:39:29 +0000 (16:39 +0900)]
[moco-tf] Revise sanity check for squeeze dim (#6370)
This commit would throw error for invalid squeeze dimension.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 8 Aug 2019 07:23:31 +0000 (16:23 +0900)]
[res] Small network mocking the Epilogue (#6375)
This commit adds TF_SMALL_NET_0014, a mock Epilogue network using ReLU
instead of Softmax
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
이한종/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 8 Aug 2019 07:04:05 +0000 (16:04 +0900)]
[neurun] Nit : fix OperandNode::BG_COLORS (#6384)
`BG_COLOR` is a static member of `Node` but it was refereced with a
subclass without a reason.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 8 Aug 2019 06:56:18 +0000 (15:56 +0900)]
[moco-tf] relocate MaxPool local class into anonymous (#6385)
This will relocate local class of MaxPool import into anonymous namespace
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 8 Aug 2019 06:55:53 +0000 (15:55 +0900)]
[moco-tf] relocate Mul local class into anonymous (#6386)
This will relocate local class of Mul import into anonymous namespace
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 8 Aug 2019 06:55:34 +0000 (15:55 +0900)]
[moco-tf] relocate Relu local class into anonymous (#6387)
This will relocate local class of Relu import into anonymous namespace
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 8 Aug 2019 06:52:39 +0000 (15:52 +0900)]
[moco-tf] relocate Relu6 local class into anonymous (#6389)
This will relocate local class of Relu6 import into anonymous namespace
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Aug 2019 05:42:38 +0000 (14:42 +0900)]
[loco] Simplify Identity Graph Testcase with Graph Builder (#6344)
* [loco] Simplify Identity Graph Testcase with Graph Builder
This commit simplifies Identity Graph Testcase with GraphBuilder.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Fix a typo
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 8 Aug 2019 05:40:14 +0000 (14:40 +0900)]
[moco-tf] relocate Identity local class into anonymous (#6382)
This will relocate local class of Identity import into anonymous namespace
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 8 Aug 2019 05:24:05 +0000 (14:24 +0900)]
[moco-tf] Switch on for ImportAsTFConcatV2 (#6380)
This will switch on for ImportAsTFConcatV2 in the knob
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 8 Aug 2019 04:30:28 +0000 (13:30 +0900)]
[moco-tf] Canonicalize ConcatV2 node (#6377)
This will enable Canonicalization of TFConcatV2 to canonical TensorConcat
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Aug 2019 04:19:50 +0000 (13:19 +0900)]
Fix acl backend test fail (#6376)
Fix acl cl backend test fail
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Aug 2019 04:19:19 +0000 (13:19 +0900)]
[loco] Add index getter (#6367)
This commit extends GraphInput and GraphOutput class with "index"
getter.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 8 Aug 2019 04:12:52 +0000 (13:12 +0900)]
[mocotest-tf] Enable Squeeze_002 (#6369)
This commit would enable squeeze network test with negative squeeze
dimension.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 8 Aug 2019 04:03:59 +0000 (13:03 +0900)]
[moco-tf] relocate FusedBatchNorm local class into anonymous (#6374)
This will relocate local class of FusedBatchNorm import into anonymous namespace
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 8 Aug 2019 04:00:26 +0000 (13:00 +0900)]
[moco-tf] TFShape summary (#6372)
This commit adds TFShape node summary.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 8 Aug 2019 03:54:17 +0000 (12:54 +0900)]
[moco-tf] Introduce ConcatV2Canonicalizer (#6360)
* [moco-tf] Introduce ConcatV2Canonicalizer
This will introduce ConcatV2Canonicalizer that converts TFConcatV2 to canonical TensorConcat node
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* fix typo
* remove unused header
Vladimir Plazun/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 8 Aug 2019 03:42:02 +0000 (06:42 +0300)]
Fix several warnings (#6242)
* Fix several warnings
Make class/struct definitions consistent( forward declararation with different type from definition )
Remove pessimising moves of temporary objects
Change `info` symbol in library_info.cc into non-static
Signed-off-by: Vladimir Plazun <v.plazun@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Aug 2019 03:40:39 +0000 (12:40 +0900)]
Replace strict build flag setting in libs/tflite (#6232)
Replace libs/tflite strict build setting cmake from using compile option to linking nnfw_common interface
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 8 Aug 2019 02:45:27 +0000 (11:45 +0900)]
[res] TF Shape-Reshape network (#6343)
This commit adds tensorflow Shape test using Reshape node.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Aug 2019 02:44:47 +0000 (11:44 +0900)]
Replace strict build setting in libs (#6226)
Replace strict build setting in libs to use nnfw_common interface (except libs/tflite)
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Aug 2019 02:41:16 +0000 (11:41 +0900)]
[loco] Infer the shape of bias-taking nodes (#6332)
* [loco] Infer the shape of bias-taking nodes
CanonicalShapeInferenceRule is now able to infer the shape of
BiasEncode, FeatureBiasAdd, and TensorBiasAdd nodes.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Fix a typo
이한종/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 8 Aug 2019 02:27:18 +0000 (11:27 +0900)]
[neurun] Enhance DotDumper backend color assign (#6368)
Enhance DotDumper backend color assignment. Each Backend will have its
unique color up to 8 of them. Before it was assigned based on hard-coded
Backend ID.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 8 Aug 2019 01:52:17 +0000 (10:52 +0900)]
[moco-tf] Introduce TFShape IR (#6322)
This commit introduces TF-dialect TFShape IR for tensorflow 'Shape'
operation
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Aug 2019 01:47:06 +0000 (10:47 +0900)]
[loco] Shape inference over Conv2D-related nodes (#6349)
CanonicalShapeInferenceRule is now able to infer the shape of nodes
related with Conv2D (such as FilterEncode).
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 8 Aug 2019 01:46:41 +0000 (10:46 +0900)]
[moco-tf] Resolve negative squeeze dimension (#6352)
This commit resolves negative squeeze dimension during shape inference
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
이한종/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 8 Aug 2019 01:46:33 +0000 (10:46 +0900)]
[neurun] Favor `map::emplace` over `map::insert` (#6355)
Favor `map::emplace` over `map::insert` for every occurences in neurun.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 8 Aug 2019 01:46:11 +0000 (10:46 +0900)]
[moco-tf] relocate AvgPool local class into anonymous (#6366)
This will relocate local class of AvgPool import into anonymous namespace
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 8 Aug 2019 01:45:50 +0000 (10:45 +0900)]
[moco-tf] relocate Add local class into anonymous (#6365)
This will relocate local class of Add import into anonymous namespace
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 8 Aug 2019 01:45:17 +0000 (10:45 +0900)]
[moco-tf] Disable usage of nodes.lst in FixPadding (#6361)
This will disable using CanonicalNodes.lst and TFNodes.lst so that we don't have to modify FixPaddingTransform
- this is a temporary fix before deleting FixPaddingTransform related files
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
이한종/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 8 Aug 2019 01:44:01 +0000 (10:44 +0900)]
[neurun] Refine DotDumper (#6347)
- Rename method `dumpIfNeeded` to `dump`
- Rename enum `OPTION` to `DotDumper::Level` and update comments
- Take out config fetching from class `DotDumper`
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 8 Aug 2019 01:42:30 +0000 (10:42 +0900)]
[moco-tf] Import as TFConcatV2 with a knob (#6348)
This will change import of ConcatV2 node as Canonical or TF-dialect with a knob.
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Aug 2019 01:20:17 +0000 (10:20 +0900)]
[loco] Hide deprecated "node" method (#6342)
Now, "node" method in GraphInput/GraphOutput is private.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 8 Aug 2019 01:19:57 +0000 (10:19 +0900)]
[res] Simple TF Shape test case (#6341)
This commit adds simple Shape network for TF test.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 8 Aug 2019 00:49:33 +0000 (09:49 +0900)]
Fix converting type of zero point in select_operator.py (#6353)
This commit fixes converting type of zero point in select_operator.py.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Aug 2019 00:45:46 +0000 (09:45 +0900)]
Revise acl common cmake (#6340)
- Add strict build option: nnfw_common
- Link arm_compute and arm_compute_ex library
- Include path acl_common for acl_common user (acl_cl, acl_neon)
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Aug 2019 00:45:27 +0000 (09:45 +0900)]
Merge neurun kernel and backend build (#6313)
- Merge neurun each backend's kernel and backend build
- Fix build error on cpu backend kernel by restrict build option
- Invalid type comparison
- Unused variable
- Unused function
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 8 Aug 2019 00:22:43 +0000 (09:22 +0900)]
[locop] FixedReshape node summary (#6354)
This commit adds FixedReshape node summary.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 22:01:57 +0000 (07:01 +0900)]
[moco-tf] Use common calc_paddata in FixShape (#6346)
This will change calc_node_pad() and calc_annot_paddata() to use common calc_annot_paddata() in FixShapeTransform
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
[nnc] Replace BiasAdd and Scale with elementwise equivalents (#6358)
`BiasAdd` and `Scale` are restricted versions of equivalent Elementwise ops and are going to be removed.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
이한종/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 7 Aug 2019 12:23:12 +0000 (21:23 +0900)]
Remove TensorBuilder getter from IKernelGenerator (#6331)
Now that `Backend` holds `TensorBuilder` directly, no need to have this
interface from `IkernelGenerator` any longer.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
[mir] Add binary elementwise operations (#6351)
first step of future replacement of single `ElementwiseOp` class with set of individual operations.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 09:56:12 +0000 (18:56 +0900)]
[moco-tf] Introduce TFConcatV2 IR (#6321)
This will introduce TFConcatV2 IR and required codes for TensorFlow Concat node
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 7 Aug 2019 09:44:42 +0000 (18:44 +0900)]
Support asynchronous execution (#6314)
- Introduce methods for start execution & wait finish in Execution class to support asynchronous execution
- Add test using introduced methods
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 09:21:33 +0000 (18:21 +0900)]
[tf2tflite] copying customop.conf into cmake build/compiler/tf2tflite (#6329)
* [tf2tflite] copying customop.conf into cmake build/compiler/tf2tflite
This makes cmake to copy customop.conf into cmake build/compiler/tf2tflite.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* indent, 'xxx_customop.conf' -> 'xxx.customop.conf'
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 7 Aug 2019 09:21:13 +0000 (18:21 +0900)]
[exo-tflite] Implement FilterShape converter (#6334)
This commit implement a helper which converts FilterShape as exo-tflite
internal ShapeDescription.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 7 Aug 2019 09:14:16 +0000 (18:14 +0900)]
[moco-tf] Remove redundant codes in FuseBinaryIntoPreceding (#6319)
* [moco-tf] Remove redundant codes in FuseBinaryIntoPreceding
There are some redundant codes in `FuseBinaryIntoPreceding.cpp`
This commit will remove them.
- Exactly only one of variables(`xc` and `yc`) is `nullptr` because `is_only_one_valid` already checks.
- Then `addparam` and `mulparam` cannot be `nullptr`.
- After removing above condition, there can be only one case that `bchanged` can be returned, that is when `biasadd` is `nullptr`. However when `biasadd` is `nullptr`, bchanged is always `false`.
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
* apply comments
* add missing codes
* fix comments
* apply comments
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 09:10:30 +0000 (18:10 +0900)]
[moco-tf] Common method for calculation of PadData (#6338)
This will introduce common method for calculation of PadData that exist in calc_node_pad() and calc_annot_paddata() of FixShapeTransform
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 7 Aug 2019 08:22:09 +0000 (17:22 +0900)]
[loco] Introduce GraphBuilder helper class (#6308)
* [loco] Introduce GraphBuilder helper class
This commit introduces GraphBuilder helper class which faciliates
testcase implementation.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Update comment
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 7 Aug 2019 08:18:58 +0000 (17:18 +0900)]
[loco] TensorConcat Shape Inference (#6315)
* [loco] TensorConcat Shape Inference
CanonicalShapeInferenceRule is now able to infer the shape of TensorConcat
nodes.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Remove invalid comments
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 08:18:46 +0000 (17:18 +0900)]
[moco-tf] Deprecate FixPaddingTransform (#6335)
This will remove using FixPaddingTransform.
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 7 Aug 2019 08:11:06 +0000 (17:11 +0900)]
Rename pacl build script (#6336)
Rename pacl build script: suffix pacl
Rename to avoid default runtime confusion
Update build introduction document
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 07:53:50 +0000 (16:53 +0900)]
[tf2tflite] Modified as CustomOp.info renamed to customop.conf (#6328)
CMakeLists.txt file was modified as CustomOp.info renamed to customop.conf.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 06:42:17 +0000 (15:42 +0900)]
[moco-tf] Fix pad for TF dialect nodes in FixShape (#6302)
This will merge fix pad for TF dialect nodes in FixShapeInference using calc_annot_paddata() method
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 06:41:48 +0000 (15:41 +0900)]
[moco-tf] Use calc_annot_paddata for fix pad of TF dialect nods (#6301)
This will change to use calc_annot_paddata() method to fix pad in FixShapeInference for TFAvgPool node
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 06:39:22 +0000 (15:39 +0900)]
[tf2tflite] driver can takes customop.conf as param (#6272)
* [tf2tflite] driver can takes customop.conf as param
This commit enable Driver to take customop.conf as the 5th param.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* optional param: '--customop <customop.conf path>'
* remove strcmp, parse conf before calling import
* nyi error
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 06:38:31 +0000 (15:38 +0900)]
[exo-tflite] Exporting Operator Code table including code of custom op (#6323)
Now when tflite opcode table is created, name and code for custom op is included.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 05:52:28 +0000 (14:52 +0900)]
[exo-tflite] type inferencing including custom op (#6320)
This commit enables exo-tflite to infer type canonical nodes as well as custop op.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 05:41:48 +0000 (14:41 +0900)]
[tf2tflite] Enable test RealDiv and Sub (#6325)
This will enable tf2tflite test of RealDiv and Sub
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 05:40:43 +0000 (14:40 +0900)]
[mocotest-tf] Enable RealDiv and Sub test (#6324)
This will enable mocotest-tf test for RealDiv and Sub
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 7 Aug 2019 05:40:25 +0000 (14:40 +0900)]
[loco] Identity Graph Testcase with Input Shape (#6307)
This commit allows users to build an identity graph testcase with
explicit input shape.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 05:16:27 +0000 (14:16 +0900)]
[moco-tf] Enable Canonicalization of Sub and RealDiv (#6316)
This will enable Canonicalizaton of TFSub and TFRealDiv nodes
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 04:15:57 +0000 (13:15 +0900)]
[moco-tf] Canonicalizer for RealDiv (#6306)
This will introduce Canonicalizer for TFRealDiv to EltwiseDiv
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
Ivan Vagin/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 7 Aug 2019 04:09:53 +0000 (07:09 +0300)]
[mir-tflite-importer] Perform operation sanity checks while converting it (#6069)
* [mir-tflite-importer] Perform operation sanity checks while creating
Perform operation sanity checks while creating it
Signed-off-by: Ivan Vagin <ivan.vagin@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 7 Aug 2019 03:45:29 +0000 (12:45 +0900)]
Remove format check warning by deleted file (#6312)
By filter out deleted file, remove warning on format checker's diff with master mode
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
이춘석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 7 Aug 2019 02:26:31 +0000 (11:26 +0900)]
Enable DETECTION_POSTPROCESS kernel in TFLite interpreter (#6214)
- Enable DETECTION_POSTPROCESS in interpreter
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 01:55:30 +0000 (10:55 +0900)]
[moco-tf] Canonicalizer for Sub (#6305)
This will introduce Canonicalizer for TFSub node to EltwiseSub
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 01:54:52 +0000 (10:54 +0900)]
[moco-tf] Graph build for RealDiv node (#6304)
This will enable graph building of RealDiv node for importer
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 01:54:29 +0000 (10:54 +0900)]
[moco-tf] Graph build for Sub node (#6303)
This will enable graph building of Sub node for importer
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 01:42:35 +0000 (10:42 +0900)]
[moco-tf] Use calc_node_pad for fix pad of loco nodes (#6300)
This will change to use calc_node_pad() method to fix pad in FixShapeInference for loco nodes
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 01:42:10 +0000 (10:42 +0900)]
[moco-tf] Fix pad for TFConv2D in fix shape (#6250)
This will merge fix pad for TFConv2D node in fix shape transform
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 7 Aug 2019 01:31:28 +0000 (10:31 +0900)]
[loco] Support ConstGen shape inference (#6290)
CanonicalShapeInferenceRule is now able to infer the shape of ConstGen
nodes.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 7 Aug 2019 01:30:01 +0000 (10:30 +0900)]
[exo-tflite] BiasShape to ShapeDescription Converter (#6289)
This commit implements BiasShape -> ShapeDescription converter.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 7 Aug 2019 01:16:30 +0000 (10:16 +0900)]
Introduce "xtrace" (#6158)
* Introduce "xtrace"
This commit introduces "xtract" which collects trace/benchmark events
via xray pipe and records it as Chrome Trace Event file format.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Add missing copyright
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 7 Aug 2019 00:44:41 +0000 (09:44 +0900)]
[loco] MaxPool2D Shape Inference (#6287)
CanonicalShapeInferenceRule is now able to infer the shape of MaxPool2D
nodes.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 00:43:24 +0000 (09:43 +0900)]
[nnpackage] Add an nnpackage example (one op, tflite) (#5929)
Add first minimal nnpackage example.
It has no custom op, one operator, uses tflite model.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 00:42:59 +0000 (09:42 +0900)]
[nnpackage] nnpackager -c will create compressed nnpackage (#6278)
Use "nnpackage -c path_to_nnpackage_root" to get compressed nnpackage.
Also it removed redundant parenthesis in if condition.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 7 Aug 2019 00:40:54 +0000 (09:40 +0900)]
Replace strict build flag setting in neurun frontend & core (#6279)
- Replace neurun frontends and core strict build setting cmake from using compile option to linking nnfw_common interface
- Add strict build setting for nnfw api frontend and fix unused parameter warning
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 7 Aug 2019 00:03:26 +0000 (09:03 +0900)]
[moco-tf] Introduce function to create BiasAdd operation (#6292)
This commit will introduce a new function to create `BiasAdd` operation
and insert it after preceding operation.
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
Add default fallback for Visitor::visit (#5889)
This will help to escape overriding a lot of visit()
with default body: empty body or `throw std::runtime_error("NYI")`:
just override this new method
additional changes:
* added file with all mir operation headers
* refined IVisitor
Signed-off-by: Dilshodzhon Poshshoev <d.poshshoev@samsung.com>
[mir_onnx] Replace BiasAdd and Scale with Elementwise equivalents (#6298)
`BiasAdd` and `Scale` are restricted versions of equivalent Elementwise ops and are going to be removed.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir2loco] Replace BiasAdd and Scale with Elementwise equivalents (#6296)
`BiasAdd` and `Scale` are restricted versions of equivalent Elementwise ops and are going to be removed.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir_caffe] Replace BiasAdd and Scale with elementwise equivalents (#6295)
`BiasAdd` and `Scale` are restricted versions of equivalent Elementwise ops and are going to be removed.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir_tflite] Replace BiasAdd and Scale with Elementwise equivalents (#6294)
`BiasAdd` and `Scale` are restricted versions of equivalent Elementwise ops and are going to be removed.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir_caffe2] Replace BiasAdd and Scale with Elementwise equivalents (#6293)
`BiasAdd` and `Scale` are restricted versions of equivalent Elementwise ops and are going to be removed.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir_onnx] Add NodeConverters for all supported operations from OpCreator (#6291)
* Added OpConverters
* Register all converters
* Remove OpCreator
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
[mir_onnx] Introduce NodeConverterRegistry and remove operation hash (#6241)
* Introduce NodeConverterRegistry
* Remove operation hash
* Replace operation hash uses with NodeConverter
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 6 Aug 2019 10:06:56 +0000 (19:06 +0900)]
[moco-tf] Divide into function for fused convolution node in FuseBinaryIntoPreceding (#6273)
* [moco-tf] Divide into function for fused convolution node in FuseBinaryIntoPreceding
This commit will introduce `fused_conv_node` function for dividing long code.
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
* add missing code
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 6 Aug 2019 09:37:51 +0000 (18:37 +0900)]
[loco] Use link helper (#6271)
Let's use link helper instead of deprecated node method.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 6 Aug 2019 09:36:10 +0000 (18:36 +0900)]
[loco] Update TensorShaped classes with initializer_list (#6284)
Now, "shape" setter in TensorShaped mixin takes initializer_list
as its input.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>