Commit message (Collapse) | Author | Age | |
---|---|---|---|
* | Use Ophints to support TfLite UnidirectionaSequenceLstm and add an e2e test. | A. Unique TensorFlower | 2018-10-09 |
| | | | | | | Support peephole and num_proj as well. PiperOrigin-RevId: 216467578 | ||
* | Return ::tensorflow::Status in Toco Graph Transformations. | Yu-Cheng Ling | 2018-10-09 |
| | | | | PiperOrigin-RevId: 216392908 | ||
* | Implementation of unpack op. | A. Unique TensorFlower | 2018-08-23 |
| | | | | PiperOrigin-RevId: 210051131 | ||
* | Implementation of ctc beam search decoder op in custom op fashion. | A. Unique TensorFlower | 2018-08-02 |
| | | | | PiperOrigin-RevId: 207210333 | ||
* | Fix lint issue | A. Unique TensorFlower | 2018-07-30 |
| | | | | PiperOrigin-RevId: 206690288 | ||
* | Implementation of logical_or. | A. Unique TensorFlower | 2018-07-30 |
| | | | | PiperOrigin-RevId: 206549781 | ||
* | Add one_hot op support to TFLite | Jared Duke | 2018-07-26 |
| | | | | PiperOrigin-RevId: 206185190 | ||
* | Support for shape attributes in custom ops for Toco | A. Unique TensorFlower | 2018-07-25 |
| | | | | PiperOrigin-RevId: 206012140 | ||
* | Implementation of stack. | A. Unique TensorFlower | 2018-07-23 |
| | | | | PiperOrigin-RevId: 205763219 | ||
* | Import/export support for Any, LogicalAnd, and LogicalNot ops. | A. Unique TensorFlower | 2018-07-18 |
| | | | | PiperOrigin-RevId: 205134621 | ||
* | Implementation of arg_min. | A. Unique TensorFlower | 2018-07-10 |
| | | | | PiperOrigin-RevId: 203908601 | ||
* | Implementation of pow. | A. Unique TensorFlower | 2018-06-28 |
| | | | | PiperOrigin-RevId: 202262513 | ||
* | Fix operator names. | A. Unique TensorFlower | 2018-06-20 |
| | | | | PiperOrigin-RevId: 201422566 | ||
* | Implementation of TensorFlowEqual and TensorFlowNotEqual. | A. Unique TensorFlower | 2018-06-07 |
| | | | | PiperOrigin-RevId: 199602232 | ||
* | implementation of sparse_to_dense | A. Unique TensorFlower | 2018-05-31 |
| | | | | PiperOrigin-RevId: 198710452 | ||
* | Add support for select (via tf.where) support to tflite. | A. Unique TensorFlower | 2018-05-07 |
| | | | | PiperOrigin-RevId: 195734246 | ||
* | Merge changes from github. | Patrick Nguyen | 2018-05-01 |
| | | | | PiperOrigin-RevId: 194997009 | ||
* | Adding support for RandomUniform. Basic support for op import/export of ↵ | A. Unique TensorFlower | 2018-04-02 |
| | | | | | | RandomUniform, and constant resolution with static seeds. PiperOrigin-RevId: 191293897 | ||
* | Support for transpose convolution. Includes striding, and a reference ↵ | A. Unique TensorFlower | 2018-03-07 |
| | | | | | | implementation. PiperOrigin-RevId: 188210975 | ||
* | Add 8bit Tanh support to tflite | A. Unique TensorFlower | 2018-02-27 |
| | | | | | | Allow output datatypes for custom ops to be more than the output types used in the graph. When an op has multiple outputs, some of them not used will be optimized away. This results in a failure. The change in propagate_array_data_types.cc fix this. PiperOrigin-RevId: 187198815 | ||
* | Internal Change | A. Unique TensorFlower | 2018-01-23 |
| | | | | PiperOrigin-RevId: 182974191 | ||
* | TFLite export optional tensor as -1 id. | Zhixian Yan | 2018-01-19 |
| | | | | PiperOrigin-RevId: 182592943 | ||
* | Adding support for to resolve constant FloorDiv, FloorMod, StridedSlice, ↵ | A. Unique TensorFlower | 2018-01-17 |
| | | | | | | Stack, Rank and Range. PiperOrigin-RevId: 182261052 | ||
* | Automated g4 rollback of changelist 179836027 | Gunhan Gulsoy | 2017-12-21 |
| | | | | PiperOrigin-RevId: 179848421 | ||
* | Adding support for to resolve constant FloorDiv, FloorMod, StridedSlice, ↵ | A. Unique TensorFlower | 2017-12-21 |
| | | | | | | Stack, Rank and Range. PiperOrigin-RevId: 179836027 | ||
* | internal change | A. Unique TensorFlower | 2017-12-15 |
| | | | | PiperOrigin-RevId: 179217499 | ||
* | Adding support for new TensorFlow operators. Also adding a transformation to ↵ | A. Unique TensorFlower | 2017-12-08 |
| | | | | | | convert an ExpandDims into a Reshape op. PiperOrigin-RevId: 178418377 | ||
* | Simplification of propagate_array_data_types: | A. Unique TensorFlower | 2017-12-06 |
| | | | | | | | | | | | No need to distinguish between ops for which we propagate the type of the first input, and ops for which we require all inputs to have the same type then propagate that type. Doing only the former is a mild relaxation of what we've been doing, allows to drop much code, and makes this code far less frequently needing to be updated again in the future as we drop a long non-canonical list of operator types being special-cased. PiperOrigin-RevId: 178156653 | ||
* | Internal Change. | Andrew Selle | 2017-11-10 |
PiperOrigin-RevId: 175307445 |