| cf3c77f683b6bc27408a58ca9eb7ea5afb4568f6 |
|
09-Feb-2018 |
gracehoney <31743510+aaroey@users.noreply.github.com> |
Fix LINT.IfChange comment
/external/tensorflow/tensorflow/contrib/tensorrt/convert/convert_graph.cc
|
| 9b9567adccde7ab08d683b5b64a8870e74635f62 |
|
09-Feb-2018 |
gracehoney <31743510+aaroey@users.noreply.github.com> |
Fix more build dependencies and includes.
/external/tensorflow/tensorflow/contrib/tensorrt/convert/convert_graph.cc
|
| bfe8b85cad3be1a82234500fce3064c98dd20d09 |
|
06-Feb-2018 |
gracehoney <31743510+aaroey@users.noreply.github.com> |
1. Use tensorflow::string instead of std::string
2. Fix swig problem in trt_conversion.i
3. Fix c++ styles
4. Fix BUILD dependencies
/external/tensorflow/tensorflow/contrib/tensorrt/convert/convert_graph.cc
|
| 9f292d8eac67ed53248e019a969d39c63bca1868 |
|
01-Feb-2018 |
Jie <jiej@nvidia.com> |
[update]
addressing comment issues
/external/tensorflow/tensorflow/contrib/tensorrt/convert/convert_graph.cc
|
| f8b1986d67b1bcc352acb7644b642faf46ca79cb |
|
31-Jan-2018 |
Sami Kama <skama@nvidia.com> |
Change VLOGs to increasing verbosity mode
/external/tensorflow/tensorflow/contrib/tensorrt/convert/convert_graph.cc
|
| 599eadc299ae680bfb569ace4278b2eb262ecc44 |
|
30-Jan-2018 |
Sami Kama <skama@nvidia.com> |
Changes for more PR comments
/external/tensorflow/tensorflow/contrib/tensorrt/convert/convert_graph.cc
|
| d7b4fe4d4322a3fdab8a1dedb93d37a1f800a559 |
|
30-Jan-2018 |
gracehoney <31743510+aaroey@users.noreply.github.com> |
Fix the build dependencies and formatting of the code, and make sure
they follow the style conventions.
/external/tensorflow/tensorflow/contrib/tensorrt/convert/convert_graph.cc
|
| 90d628b0ba66a6144c4a83292e95f4dde287f5a9 |
|
30-Jan-2018 |
Sami Kama <skama@nvidia.com> |
Remove debug log and use vlog instead
/external/tensorflow/tensorflow/contrib/tensorrt/convert/convert_graph.cc
|
| 8e03944589542bd64559d68989bca4a4705eed93 |
|
29-Jan-2018 |
gracehoney <31743510+aaroey@users.noreply.github.com> |
Fix build (part1):
1. Changed includes of "NvInfer.h" to "tensorrt/include/NvInfer.h"
2. Remove build target "tensorrt_ops.so" (src file doesn't exist and the
target is not used anywhere)
3. Add missing '#if GOOGLE_TENSORRT's
4. Use tf_cuda_library instead of cc_library for some targets to get the
tf_copts naturally.
5. Revert the changes that was accidentally made (by merging with
upstream head) from configure.py
6. Replace exception with LOG(FATAL) in
tensorflow/contrib/tensorrt/convert/convert_nodes.cc as exception is
not supported.
7. Revert the reinterprete_cast change in
tensorflow/contrib/tensorrt/kernels/trt_engine_op.cc
8. Fix minor formatting and naming issues according to the style guide.
/external/tensorflow/tensorflow/contrib/tensorrt/convert/convert_graph.cc
|
| e01844e65e0dbd2682a894946bec7f072d36fa27 |
|
29-Jan-2018 |
Jie <jiej@nvidia.com> |
[update]
clang-format & cpplint done.
TODO: compile and test after build fix.
/external/tensorflow/tensorflow/contrib/tensorrt/convert/convert_graph.cc
|
| ae740a67bdc01b991ead6ac047c774bff4d7bc8f |
|
29-Jan-2018 |
Jie <jiej@nvidia.com> |
[update]
addressing:
i. some naming conventions
ii. add macro to guard cpp files
TODO:
cpplint
/external/tensorflow/tensorflow/contrib/tensorrt/convert/convert_graph.cc
|
| 98ffa7b2bb5b273b4ae2b052e82fb0d8c054d96b |
|
29-Jan-2018 |
gracehoney <31743510+aaroey@users.noreply.github.com> |
Fix compilation, there are still linking issues which will be fixed in a followup commit.
/external/tensorflow/tensorflow/contrib/tensorrt/convert/convert_graph.cc
|
| 75adab6104362d71ce28b0269bf31fd30471b1b6 |
|
29-Jan-2018 |
Jie <jiej@nvidia.com> |
[UPDATE]
addressing code review comments.
TODO:
MACRO GOOGLE_TENSORRT to guard c++ files.
build/test -> current code works on local repo before the master merge.
/external/tensorflow/tensorflow/contrib/tensorrt/convert/convert_graph.cc
|
| 6908cc233c679b8fe61d99a30d3828362caf47be |
|
25-Jan-2018 |
Sami Kama <skama@nvidia.com> |
[ Fixes for PR comments]
- removed commented code
- moved all code to tensorflow namespace
- removed a dangling config parameter from tensorflow/BUILD
- fixed Copyright notice years
/external/tensorflow/tensorflow/contrib/tensorrt/convert/convert_graph.cc
|
| 320e07a3c7f2815b31cd534ea714616040abe91c |
|
24-Jan-2018 |
Jie <jiej@nvidia.com> |
[BUG_FIX]
git patch issue fixed.
modified: tensorflow/contrib/tensorrt/convert/convert_graph.cc
/external/tensorflow/tensorflow/contrib/tensorrt/convert/convert_graph.cc
|
| 68e17d497497119c24ad506dac4e34e127cf836c |
|
24-Jan-2018 |
Jie <jiej@nvidia.com> |
[UPDATE]
Refactoring optimization pass and shape inference
shape inference
Removed shape refiner and apply shape inference through
grappler/costs/graph_properties
Currently using static shape inference
optimization pass
Moved Python optimization pass to c++ optimization pass
/external/tensorflow/tensorflow/contrib/tensorrt/convert/convert_graph.cc
|
| 825e7a32e9f4dbad21a9ddb9d8a34bd3e32b1d0e |
|
19-Jan-2018 |
Sami Kama <skama@nvidia.com> |
Introducing TensortRT Operator to TF which can run (sub)graphs in
highly optimized TensorRT engines. This commit is a merged version of
many commits by
benbarsdell <bbarsdell at nvidia.com>
deadeyegoodwin <davidg at nvidia.com
jjsjann123 <jiej at nvidia.com>
samikama <skama at nvidia.com>
/external/tensorflow/tensorflow/contrib/tensorrt/convert/convert_graph.cc
|