968ffef62b
[TFLite] Support depthwise convolution multiplier greater than 1 ( #3922 )
2019-09-10 21:09:25 -07:00
54dbcc2872
[Relay] fix exponential blowup in interpreter ( #3559 )
2019-09-10 23:30:46 -04:00
5bff6ccede
[Relay][Frontend][Keras] Fix ReLU in Keras Converter missed the case ( #3917 )
...
* [Relay][Frontend][Keras] Fix ReLU in Keras Converter missed the case
* [Relay][Frontend][Keras] Add test case for ReLU in Keras Converter missed the case
* [Relay][Frontend][Keras] Add test case for ReLU in Keras Converter missed the case
2019-09-10 10:41:16 -07:00
42195a48e0
[CODEGEN] Remove incorrect check for LLVM in C codegen test ( #3921 )
2019-09-10 08:43:01 +08:00
0f4c151f2a
[Relay][Training] Add gradient for max. ( #3915 )
...
* save
* save
2019-09-09 12:48:04 -07:00
63a91ebf45
Numpy compatible dtype inference for `tvm.convert` and `tvm.const` ( #3861 )
...
* numpy compatible type inference
* update
* try to fix
* fix
* try to fix
* fix lint
* Update nn.h
* cast to int32
* try to fix
* fix again
* retrigger ci
2019-09-10 01:26:34 +08:00
2f5b155ab5
[Relay/TOPI][Op] Add erf intrinsic and op ( #3702 )
...
* add more ops
* stop vectorization for erf
* x
* cleanup
* fix
* add whitelist for vectorizable intrin
* add tf converter
* fix dense
* fix
* add missing intrin
* fix mxnet frontend
* fix nvptx
2019-09-09 22:54:15 +08:00
6a377f77e8
[Relay][Training] Add gradient for cast ( #3894 )
...
save
fix
fix grad
2019-09-07 23:11:47 -04:00
184fa484ca
change docker install script ( #3524 )
2019-09-08 08:10:11 +08:00
70042b78ee
[TOPI] Intel graphics conv2d autotvm template added ( #3839 )
...
* update lint
* lint fixed
* lint updated
* lint fixed
* lint fixed
* lint fixed
* updates
* add intel graphics as a package
* remove print info
* depthwise conv2d schedule added for intel graphics
* asdf
* fix lint
* fix lint
* fix ci
* add channels
2019-09-06 17:01:29 -07:00
02ddb5a9c3
save ( #3901 )
2019-09-06 15:17:37 -07:00
ca0292d8c5
[Relay] Add ADTs to text format ( #3863 )
...
* Getting closer to having ADT defs
* ADT defs working probly
* Match parsing basipally done
* came to earth in a silver chrome UFO
* match finished?
* All tests but newest are passing
* ADT constructors work
now cleanup?
* Cleanup round 1
* Cleanup round 2
* Cleanup round 3
* Cleanup round 4
* Cleanup round 6
* Cleanup round 7
* Lil grammar fix
* Remove ANTLR Java files
* Lint roller
* Lint roller
* Address feedback
* Test completeness in match test
* Remove unused imports
* Lint roller
* Switch to Rust-style ADT syntax
* Lil fix
* Add dummy `extern type` handler
* Add type arg to test
* Update prelude semantic version
* Repair test
* Fix graph var handling in match
* Revert 's/graph_equal/is_unifiable' change
2019-09-06 11:04:34 -07:00
9b148f14a3
[schedule] Improve ceil_divide in tile/split ( #3842 )
2019-09-06 21:29:31 +08:00
08d92203f7
[Relay] add Tuple pattern ( #3596 )
...
* implement tuple pattern
* add tuple pattern
* lint;
* lint
* lint
* fix error
* fix
* add test
2019-09-05 16:41:44 -07:00
ca35277071
[Relay] Fix operator fusion for multiple output ( #3871 )
...
* save
* add test
* refactor
* fix indent
* save
* refactor
2019-09-06 06:39:13 +09:00
e873a73abd
[Test] enable NHWC of `relay.testing.mobilenet` ( #3886 )
...
* [Relay] enable NHWC of `relay.testing.mobilenet`
In this way, we can play around NHWC inside TVM regardless of
the frontends.
* [Test] test for NHWC of relay.testing.mobilenet
2019-09-05 11:32:21 -07:00
a6bb84a834
[QNN] Add - Refactoring to C++ ( #3736 )
2019-09-05 10:22:45 -07:00
0d4870cc70
[QNN] Convolution 2D Implementation. ( #3580 )
...
Rebasing. Empty commit.
Clang-format styling.
2019-09-04 10:05:22 -07:00
5ed251a68c
[Relay] Add grads ( #3857 )
...
* Add gradient implementations
* Add docstrings to fix lint errors
2019-09-04 00:07:39 -07:00
360d26ddc1
[Relay][Frontend][darknet] Solve tvm parsing darknet resnext failure bug ( #3778 )
...
* test_darkent_bug
* test_darkent
* add resnext tests
2019-09-04 13:46:29 +08:00
5fe61fd1b4
[VTA][Chisel] add scalafmt and format existing scala codebase ( #3880 )
...
* [VTA][Chisel] add scalafmt and format existing scala codebase
* change column width to 100
* add scalafmt conf file as a valid file type
* add asf header to scalafmt conf file and rerun formatter
2019-09-03 22:19:01 -07:00
6b0359b440
Revert "[Runtime] Allow parameter sharing between modules ( #3489 )" ( #3884 )
...
This reverts commit 224cc243b4
2019-09-03 15:31:04 +08:00
9e595b422f
ONNX frontend operator support: And ( #3878 )
2019-09-02 21:02:52 -07:00
224cc243b4
[Runtime] Allow parameter sharing between modules ( #3489 )
...
As GraphRuntime does not provide control-flow logics, we have to split
our model to two parts. While we need to share parameters between them
to save memory usage.
Solution:
1) add "lazy_init_input" in graph's attributes
"attrs": {
... ...
"lazy_init_input": [
"list_str",
[
"p0"
]
]
}
2) allow un-allocated NDArray entry in SetupStorage
3) utilize "set_input_zero_copy" function to set parameters
2019-09-02 20:53:42 -07:00
4b82759374
[Relay] [Parser] fix parser for cast. ( #3873 )
...
* fix
* lint
2019-09-02 11:22:11 -04:00
60de5be18e
[WIP][µTVM] Add OpenOCD Low-Level Device (RISC-V Support) ( #3756 )
2019-09-02 15:32:52 +08:00
1bc8385304
[QNN] Requantize - Optimize lowering for some corner cases. ( #3864 )
2019-09-01 22:58:38 -04:00
dee52466db
Implementation of tile for TFLite ( #3814 )
2019-08-31 18:56:39 -07:00
eef35a57d9
[Relay][Any] Add shape func for dynamic shape ( #3606 )
...
* init shape func in interpreter and vm compiler
* Update interpreter
* fix
* lint
* lint
* fix
* remove hack
* update
* fix
* fix
* update
* address comments & update for shape_of
* fix lint
* update
* fix hybrid
* lint
* fix bug & add take shape func
* lint
* lint
* update
* fix flaky test
* add todo
2019-08-31 18:50:22 -07:00
d08c74caf6
[Relay] Bitserial ops ( #3844 )
...
* Added arm_cpu NHWC schedules.
* Fixed kernel shape legalization.
* Added bitserial ops to relay.
* Snapshot and more missing files.
* Added dense testing.
* Added tests
* Added ASF header to new files.
* cc lint
* Pylint change.
* pylint fixes.
* Change arm legalize test.
* Added assert check to arm legalize.
* Added better documentation, fixed some bad style
* Reverted arm conv2d nhwc changes.
2019-08-31 17:51:51 -07:00
73dc5ac379
Add not operator for the frontend/onnx.py ( #3836 )
2019-08-31 17:50:36 -07:00
2ebf1bd14e
Add more cases to keras _convert_reshape ( #3846 )
2019-08-30 21:30:59 -07:00
ec7790e355
[QNN] Concat - Refactoring to C++ ( #3819 )
2019-08-30 21:30:18 -07:00
671421a805
[Relay][QNN] QNNtoRelay & QNNLegalize Pass utility using Relay Legalize API. ( #3838 )
2019-08-30 09:10:25 -07:00
a5def36f55
codegen_spirv support Call::reinterpret ( #3795 )
2019-08-30 08:25:07 +08:00
d201978415
[Relay] Conv2d grad ( #3636 )
...
* [Relay] Conv2d grad
* Fix test
* Fix first order gradient
2019-08-29 13:36:06 -04:00
ce031438a7
[TensorFlow] Fix limitation that depth_mult can only be 1 for DepthwiseConv2dNative ( #3676 )
...
* [TensorFlow] Fix limitation that depth_mult can only be 1 for DepthwiseConv2dNative
* Improve code readability
2019-08-29 10:59:06 +08:00
062f8cc42d
[AutoTVM] Fix database APIs ( #3821 )
...
* [AutoTVM] Fix database APIs
* Refactor the byte conversion
2019-08-28 10:04:12 -07:00
19b8b3a4e9
[Relay][Keras] Dot ( #3668 )
...
* [Relay][Keras] Dot
* fix reshape
* fix comments
2019-08-28 15:16:48 +09:00
07a83a669f
[Bugfix][Keras] axis of softmax ( #3834 )
2019-08-27 19:15:51 -07:00
283b0c3f7b
Fix inconsistent python/cpp API behavior for if_then_else, power ( #3829 )
...
* fix inconsistent python/cpp APIs for if_then_else
* fix error message
* fix power consistency
* fix
* fix bug
* add test
2019-08-26 11:31:10 -07:00
1e4aea8187
[Legalize][QNN] Pass out_types to Legalize. Update QNN requantize to read from out_types. ( #3782 )
2019-08-23 12:50:00 +08:00
554df21189
[TOPI][Relay][TensorFlow] Add OneHot operator ( #3781 )
...
* Add one-hot to Relay
* topi implementation
* Working
* add topi test
* Add TF test
* Fix check
* fix linting issues
* fix documentation
* Fix documentation
* Add support for on_value, off_value, axis, dtype
* Add full support for axis
* Fix compute and update test_forward
* Move on_value and off_value to inputs
* Add topi test
* Update tests
* Update docs
* Fix style
* re-enable tests
* Add one_hot to mxnet converter
2019-08-22 13:45:45 -07:00
7264cb6a59
Changed topi cc resize to python implementation with new features. ( #3788 )
2019-08-22 12:39:09 +09:00
95f12e3137
[Relay][VM]VM Profiler ( #3727 )
...
* [Relay][VM]VM debugger
* Report mean/min/max for op duration
* Typos
* Lint
* Lint
* Lint
* Support build debug VM in CMake
* Lint
* Enable VM debug in unit test
* Disable debug vm test until new docker image is built
* Add device sync code
* Fix qnn unit test
* Disable vm debug by default
* Rename files
* Rename classes
* Fix comment
* Fix comment
2019-08-20 21:28:05 -07:00
ebda258924
[CI] Solve occasional CI issue when pad value is all 0 ( #3801 )
2019-08-20 05:50:49 +08:00
3c8901ad0b
[Relay][Frontend][TFLite] transpose implementation for tflite.py ( #3705 )
...
* transpose implementation for tflite.py
* add TRANSPOSE to convert_map
* Fix Unexpected keyword argument 'axis' in function call
* add test for transpose oprator
* Add the parameter 'axes' handling
* add test for transpose oprator
* solve conflict within CONTRIBUTORS.md
* Improve the if condition for empty tuple
* Add one unit test to cover empty tuple
* solve conflict within CONTRIBUTORS.md
2019-08-19 10:20:38 -07:00
2b31404475
Fixed onnx test failures when run on a cpu backend ( #3764 )
...
* Fixed onnx test failures when run on a cpu backend
* Updated check_torch_conversion function to include output comparison
2019-08-19 09:33:43 -07:00
cb22d50ae4
[CoreML] Solve CoreML frontend issue of image scaler and padding so that Mobilenet mlmodel can work correctly. ( #3800 )
2019-08-19 14:05:41 +08:00
f9d8d06324
Fix ArgBinder assert order ( #3794 )
2019-08-16 20:28:46 -07:00
Zhao Wu
雾雨魔理沙
Neo Chien
Pratyush Patel
Xingjian Shi
Haichen Shen
Leyuan Wang
Logan Weber
Yizhi Liu
黎明灰烬
Animesh Jain
SWu
youluexx
Luis Vega
Tianqi Chen
Yong Sun
Josh Fromm
Alexander Pivovarov
Andrew Tulloch
Wuwei Lin
lixiaoquan
Cody Hao Yu
Yong Wu
Jon Soifer
Wei Chen
tristan-arm