d0dca01a36
[LINT] recover lint error, add asf header check ( #3117 )
2019-04-28 13:21:08 -07:00
fbcb67afdc
[CI] Add file type check ( #3116 )
2019-04-28 12:04:19 -07:00
e22b5802a3
[TOPI] Fix group_conv2d unit test ( #3113 )
2019-04-28 12:48:34 +09:00
5d7c0e3286
fixed some typos ( #3112 )
2019-04-27 20:20:38 -07:00
1146b81619
Check that the node is not null, add contains to OpMap ( #3037 )
2019-04-26 19:56:34 -07:00
b405f68bb4
[TOPI] Bitserial dense operators for CPU ( #3051 )
2019-04-26 19:55:22 -07:00
d8f547c7c7
[ROCM] Fix conv2d ( #3107 )
2019-04-26 19:49:24 -07:00
8f56949b34
Fixed issue #3069 by checking op tag ( #3070 )
...
* Fixed issue #3069 by adding in_channels
* Registerd group_conv2d_nchw as topi compute
* Improved by checking tag value
* Removed group_conv2d_nchw topi registration
* Added test for relay group_conv2d_nchw
* Added assertions to forbid small group size
* Removed hard-coded oc_block_factor
* Added explanatory comments to group_conv2d_nchw_cuda
* Updated group_conv2d_nchw_cuda schedule
Removed 'direct' CUDA tests
* Reverted an accidental change in a conv2d test
* Fixed indentation problems
* Fixed a mis-commented line
* Reverted change in group_conv2d_nchw tag
* Removed commented int8 group_conv2d test
* Fixed group size assertions in group_conv2d_nchw_cuda
2019-04-27 10:15:21 +08:00
7e68d63f75
1) fixed a functional bug in loop partitioning algorithm that is exposed when double splitting with indivisible factors 2) added a testcase ( #2956 )
2019-04-26 14:10:42 -07:00
8b5b180af5
[TVM][ARITH] Teach BoundDeduce to handle the case in which target var can appear in rhs of expression ( #2795 )
...
* target variable can now appear in either lhs or rhs of the expression to be analyzed
* removed extra spaces
2019-04-26 09:49:29 -07:00
cc09497ee1
[Relay, Quantization, TOPI] int8 dense on CUDA & Dense op quantization ( #2877 )
...
* Quantize dense layers
* Add out_dtype arggument to dense; Add dense_int8 on CUDA
* Add topi unittest of dense int8
* Fix relay
* Fix topi integration
* Fix quantization
* Update dense_rewrite
* Triger CI
* Change qconfig quantize_dense to quantize_op
* Fix
* Remove quantize_op from qconfig
2019-04-26 09:41:54 -07:00
879f91d0d8
[COMMUNITY] @vinx13 -> committer ( #3100 )
2019-04-26 09:09:11 -07:00
cb16cd445d
[TEST][FLAKY] fix for #3099 ( #3101 )
2019-04-26 08:27:30 -07:00
036294c94d
[Relay][TensorFlow] Remove 'input_0d_mismatch' special handling ( #3087 )
...
* [Relay][TensorFlow] Remove 'input_0d_mismatch' special handling
* Add more tests.
* Cover the case that strided_slice outputs a scalar
2019-04-25 22:57:37 -07:00
6a956fbca3
Add VSCode directories to gitignore ( #3095 )
2019-04-25 15:38:40 -07:00
9bfdc55c57
[Relay][TOPI] Add rsqrt operator ( #2949 )
2019-04-25 11:05:42 -07:00
fed1c08e8d
[Relay][Text Format] Fix Pretty Printing Annotations ( #3041 )
2019-04-25 10:56:45 -07:00
cdc9e85c06
Use bridge network and expose port on macOS when launch docker image ( #3086 )
2019-04-25 10:49:50 -07:00
1e84d04cbd
check in ( #3089 )
2019-04-24 20:16:59 -07:00
eed28f5815
Fix UnboundLocalError: local variable 'tensor' referenced before assignment ( #3074 )
2019-04-25 06:17:40 +08:00
3f835bd974
Enhance upsample operator to adapt onnx opset version 9 for nnvm comp… ( #2968 )
...
* Enhance upsample operator to adapt onnx opset version 9 for nnvm compiler
* Add upsample test case for newer opset in nnvm
* re-trigger the CI
2019-04-23 09:20:55 +05:30
dd63c75590
[Relay] fix target string ( #3071 )
2019-04-22 16:21:47 -07:00
4335db0a21
Fix code comment and typos. ( #3063 )
2019-04-21 17:17:50 -07:00
51e2e31f99
[Frontend][TF] Fix Placeholder issue ( #2834 )
...
* [Frontend][TF] Fix Placeholder issue
* Add test cases
2019-04-21 15:59:21 +09:00
7e34988e8e
[TOPI] Rename output tensors for better readability ( #3006 )
2019-04-20 16:20:03 -07:00
c64a33ed8b
[Bugfix] Fix winograd nnpack fp16 ( #3046 )
2019-04-19 17:50:34 -07:00
6b2e18ed96
fix PostOrderVisit signature ( #3048 )
2019-04-19 09:20:19 -07:00
4b530561f2
[RELAY] Avoid unnecessarily reconstructing FunctionNode. ( #3047 )
2019-04-19 09:19:22 -07:00
85a3ea08d7
[Relay][Frontend] TF Tile Round Sign Pow Exp Reverse ( #2960 )
...
* [Relay][Frontend] TF Round Sign Pow Exp Reverse
* fix ci
* fix comments
2019-04-19 06:37:25 +05:30
50484b38ee
Bugfix for path issues ( #3038 )
2019-04-18 15:20:11 -07:00
2a7f754852
Additional fix for PR#2972 ( #3044 )
2019-04-18 15:14:00 -07:00
4ab97dfae1
[Relay] Add printing for ADT Type ( #3030 )
...
* Update pretty_printer.cc
* Update pretty_printer.cc
2019-04-17 13:16:37 -07:00
12257ddd2d
Implement relay nn.bias_add compute in C++ ( #3027 )
...
* Implement nn.bias_add compute in C++
* Address comments
* Remove unnecessary check
2019-04-17 13:06:30 -07:00
c91f714170
Support Deriving channels when it is not provided in AlterLayout. ( #2972 )
2019-04-17 22:20:41 +08:00
8d50312f74
[Relay] Fix Fuse ( #3035 )
...
* save
* fix
* Update fuse_ops.cc
2019-04-17 14:33:31 +09:00
d5f7224dda
Update dmlc-core, fix default ctors of NodeEntry ( #3017 )
2019-04-16 20:16:23 -04:00
fcc5b42208
Ensure interpreted functions can take values that are not TensorValues ( #3015 )
2019-04-16 16:44:30 -04:00
561e422b95
Add caffe2 nnvm frontend to CI ( #3018 )
2019-04-16 16:43:37 -04:00
faf6806fa5
Update expr.h ( #3031 )
2019-04-16 16:43:10 -04:00
2b24e23fbf
Simplify TF get_output_names ( #3025 )
2019-04-16 16:28:37 -04:00
7ee5cbac6d
[Relay] Fix BatchMatMulRel typerelation ( #3032 )
...
return false mean retry in the future, and in the case of error, it should be report ASAP, not retry.
2019-04-16 15:37:49 -04:00
4b487c0d09
[ARITH] Fix x||!x for comparisons in rewrite simplifier ( #3029 )
2019-04-16 12:37:45 -04:00
0f8686e819
[DOC] Add Android Tutorial ( #2977 )
...
* fix APP_STL for latest android ndk
* add vulkan sdk for tutorial
* add android tutorial
* fix of invalid input layer name
* update relay build opt_level 1 -> 3
2019-04-15 18:11:51 -07:00
fbb74892c4
[Relay] Add compiler pass tutorial docs ( #2746 )
...
* Add Relay compiler pass tutorial docs
* Add Python API hook wrapping step
* Incorporate feedback
* More doc iteration
* Mooooore iteration
* Rewrite `runtime.md` in rst
2019-04-15 15:58:54 -07:00
5293c6bf66
[Relay] use unordered_map instead of map in ANF ( #3024 )
2019-04-15 12:56:31 -07:00
8d3b392da6
[RUST][FRONTEND] Fix resnet example ( #3000 )
...
Due to the previous changes the frontend resnet example failed to build. So this patch
1) fixes it
2) adds ~~a local `run_tests.sh` to remedy non-existence of MXNet CI (used in python build example)~~ the example build to CI with random weights and a flag for pretrained resnet weights
Please review: @tqchen @nhynes @kazimuth
2019-04-14 19:11:18 -07:00
151ccdf950
[COMMUNITY] @hlu1 -> Reviewer ( #3021 )
2019-04-13 19:20:24 -04:00
2bf666601d
[Heterogeneous][Bugfix] Fix bug of wrongly generated device_map ( #2990 )
...
* fix bug of device_index
* cpplint
* nose
* Update test_pass_annotation.py
* fix name of testcase
* delete comment
2019-04-12 20:03:11 -07:00
dc97e52789
[Relay][Text Format] Pretty Printer Smart Inlining ( #2881 )
2019-04-12 21:36:19 -04:00
fefbb0061e
[Bugfix] Fix caffe2 nnvm frontend ( #2996 )
2019-04-12 21:33:45 -04:00
Tianqi Chen
Wuwei Lin
MaxXing
Pedro Larroy
Meghan Cowan
Bing Xu
Ruizhe Zhao (Vincent)
Salem Derisavi
Siva
lixiaoquan
Logan Weber
Hiroyuki Makino
Josh Pollock
Liang-Chi Hsieh
eqy
OuHangKresnik
Gemfield
Yong Wu
Lianmin Zheng
hlu1
masahi
Siju
Balint Cristian
雾雨魔理沙
Yinghai Lu
Steven S. Lyubomirsky
Alexander Pivovarov
Sergei Grechanik
tkat0
Ehsan M. Kermani
MORINAGA
Josh Pollock