- 09 Jan, 2020 1 commit
-
-
* [Relay][Frontend][Tflite] Add parses support for unary elemwise ops * Add generic method to convert unary functions: abs, exp, ceil, floor log, sin, cos, sqrt, rsqrt, neg * Add relevant tests * Delete excessive underscores as requested in PR review * Change parameter name as suggested in PR review
Ina Dobreva committed
-
- 14 Dec, 2019 1 commit
-
-
* Replace sigmoid() with tanh() in tests for TANH
Ina Dobreva committed
-
- 09 Dec, 2019 1 commit
-
-
* use SPLIT & SQUEEZE = UNPACK as implemented in tensorflow parser Relay doesn't support UNPACK * tflite 1.13: UNPACK doesn't work as exepcted -> copies the values from 1st unpacked tensor to the other unpacks * tflite 1.13: doesn't accept negative axis
Ina Dobreva committed
-
- 01 Dec, 2019 2 commits
-
-
Alexander Pivovarov committed
-
* Add a function to set the qnn output range wrt each elemwise operation. * Add comments warning for nonsense clamped output in the tflite/tvm results comparison.
Ina Dobreva committed
-
- 22 Nov, 2019 1 commit
-
-
tristan-arm committed
-
- 20 Nov, 2019 1 commit
-
-
Alexander Pivovarov committed
-
- 19 Nov, 2019 1 commit
-
-
Alexander Pivovarov committed
-
- 15 Nov, 2019 1 commit
-
-
Zhao Wu committed
-
- 12 Nov, 2019 1 commit
-
-
* Add test for the qnn_add operator The tests use fake quant approach so until the tf session tensors remain in float32. The test data has to be passed in uint8 because of how the tflite/tvm comparison works. Abs tolerance up to 1 is allowed for the qnn results. For now input_stats are hardcoded assuming the tests for the other qnn ops will pass the input data in the same range. * Separate qnn uint8 test function from the fp32 elemwise tests Isolate qnn uint8 elemwise tests Remove blank lines
Ina Dobreva committed
-
- 10 Nov, 2019 1 commit
-
-
Zhao Wu committed
-
- 24 Oct, 2019 1 commit
-
-
Ina Dobreva committed
-
- 18 Oct, 2019 1 commit
-
-
Animesh Jain committed
-
- 14 Oct, 2019 1 commit
-
-
Animesh Jain committed
-
- 13 Oct, 2019 1 commit
-
-
This implementation provides cast to limited number of dtypes that tflite currently supports for placeholder op. Add INT64 in the possible dtypes as it appears to be supported accrording to tlfite schema.
Ina Dobreva committed
-
- 06 Oct, 2019 1 commit
-
-
The tensorflow zeros_like operation provided in array_ops.py produces directly a tensor with zeros without a graph, using only the shape and type of the input. This imposes the use of gen_array_ops.py that produces both a tensor and a graph so a comparison between tflite and tvm can be done.
Ina Dobreva committed
-
- 28 Sep, 2019 1 commit
-
-
Ina Dobreva committed
-
- 25 Sep, 2019 1 commit
-
-
add test for GREATER
Ina Dobreva committed
-
- 24 Sep, 2019 1 commit
-
-
Ina Dobreva committed
-
- 20 Sep, 2019 1 commit
-
-
* Fix unittest * Fix pylint error: Line 915 too long * Fix the conflicting files * frontend operator support: space_to_batch_nd * add test case for frontend operator support: space_to_batch_nd * add test case for frontend operator support: space_to_batch_nd * frontend operator support: space_to_batch_nd * Fix ValueError: don't know how to convert type <class 'numpy.ndarray'> to node
Neo Chien committed
-
- 11 Sep, 2019 1 commit
-
-
Zhao Wu committed
-
- 01 Sep, 2019 1 commit
-
-
Neo Chien committed
-
- 19 Aug, 2019 1 commit
-
-
* 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
Neo Chien committed
-
- 22 Jul, 2019 1 commit
-
-
* [RFC] Initial support for Tflite operator SPLIT This patch adds initial support for the tflite operator split. However I am not yet sure how to handle the axis parameter for the split operator and support it in the test infrastructure. Putting this up for an initial review and comment. The split operator in tflite according to https://www.tensorflow.org/lite/guide/ops_compatibility appears to take num_or_size_split as a 0D tensor. I also note that tflite.split is one of the few operators that returns multiple outputs and thus the helper routines in the tests needed some massaging to make this work. @apivarov , could you please review this ? Thanks, Ramana * Fix the axis parameter Add more tests * Address review comments * Try out frozen_gene's suggestion * Handle split of 1 element * int32 is only supported in tflite 1.14, let's check that version here. * Keep this at python3.5 * Add packaging as a python package to be installed
Ramana Radhakrishnan committed
-
- 10 Jul, 2019 1 commit
-
-
tristan-arm committed
-
- 27 Jun, 2019 1 commit
-
-
Alexander Pivovarov committed
-
- 25 Jun, 2019 1 commit
-
-
Sammy committed
-
- 24 Jun, 2019 1 commit
-
-
Alexander Pivovarov committed
-
- 18 Jun, 2019 1 commit
-
-
Alexander Pivovarov committed
-
- 17 Jun, 2019 2 commits
-
-
Alexander Pivovarov committed
-
Zhi committed
-
- 14 Jun, 2019 1 commit
-
-
Alexander Pivovarov committed
-
- 13 Jun, 2019 3 commits
-
-
Hua committed
-
Hua committed
-
Alexander Pivovarov committed
-
- 11 Jun, 2019 1 commit
-
-
Alexander Pivovarov committed
-
- 10 Jun, 2019 1 commit
-
-
Alexander Pivovarov committed
-
- 09 Jun, 2019 1 commit
-
-
Alexander Pivovarov committed
-
- 22 May, 2019 1 commit
-
-
* Convert TFLite NCHW to NHWC * Minor comment fix
Zhao Wu committed
-
- 01 May, 2019 1 commit
-
-
* Add FULLY_CONNECTED op into tflite frontend, support Inception V4 * Fix comment style in TF Lite tests.
songqun committed
-