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 | ||
* | Handle Range & BatchMatMul in partial Flex mode | Yu-Cheng Ling | 2018-10-05 |
| | | | | PiperOrigin-RevId: 215957535 | ||
* | Fixes in ResolveReorderAxes. | A. Unique TensorFlower | 2018-09-19 |
| | | | | | | The main issue is we were keeping the input array, updating it in place and discarding the output array. That was a problem when the input array had multiple consumer ops. Now we're keeping the output array instead, which is the correct thing to do. However, in order to minimize disruption, we keep using the input array's name whenever possible, by means of some array renamings. PiperOrigin-RevId: 213678219 | ||
* | Implement ZerosLike | A. Unique TensorFlower | 2018-09-17 |
| | | | | PiperOrigin-RevId: 213227615 | ||
* | Dilated Depthwise Conv reference implementations. | Suharsh Sivakumar | 2018-09-13 |
| | | | | PiperOrigin-RevId: 212884951 | ||
* | Fixing Any operator. | A. Unique TensorFlower | 2018-08-31 |
| | | | | PiperOrigin-RevId: 211159438 | ||
* | Implementation of reduce_any. | A. Unique TensorFlower | 2018-08-28 |
| | | | | PiperOrigin-RevId: 210507220 | ||
* | Implementation of unpack op. | A. Unique TensorFlower | 2018-08-23 |
| | | | | PiperOrigin-RevId: 210051131 | ||
* | Merge pull request #21086 from taehoonlee:fix_typos | TensorFlower Gardener | 2018-08-08 |
|\ | | | | | | | PiperOrigin-RevId: 207988541 | ||
* | | Add support for float output arrays in Quantized custom operators (custom ↵ | A. Unique TensorFlower | 2018-08-03 |
| | | | | | | | | | | | | ops only). PiperOrigin-RevId: 207306198 | ||
* | | Implementation of ctc beam search decoder op in custom op fashion. | A. Unique TensorFlower | 2018-08-02 |
| | | | | | | | | PiperOrigin-RevId: 207210333 | ||
* | | 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 | ||
| * | Fix typos | Taehoon Lee | 2018-07-24 |
|/ | |||
* | 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 | ||
* | Fixing gather to support round-tripping non-zero axis. | A. Unique TensorFlower | 2018-07-18 |
| | | | | PiperOrigin-RevId: 205122011 | ||
* | toco thinks Stack is the same as Pack. | A. Unique TensorFlower | 2018-07-17 |
| | | | | | | | | | | | | | | Stack is not Pack. tf.stack() yields Pack ops. Pack ops stack tensors. Stack ops manipulate the TF runtime stack. This cl unaliases "Stack" and "Pack" ops in toco, and renames most things that refer to "Stack" ops to "Pack" to be consistent across the codebase. In summary: Stack is whack. 'Stack' should be 'Pack'. Hack 'Stack's into 'Pack's like a maniac. This keeps 'Stack's from wracking runtime graphs. (We apologize for the fault in the change description. Those responsible have been...er...sacked). PiperOrigin-RevId: 204951155 | ||
* | Support reduce_max and reduce_prod | A. Unique TensorFlower | 2018-07-16 |
| | | | | PiperOrigin-RevId: 204846139 | ||
* | Support narrow_range attr on FakeQuant nodes | A. Unique TensorFlower | 2018-07-12 |
| | | | | PiperOrigin-RevId: 204339562 | ||
* | Implementation of arg_min. | A. Unique TensorFlower | 2018-07-10 |
| | | | | PiperOrigin-RevId: 203908601 | ||
* | Allow transposition of the weights in fully connected ops. | A. Unique TensorFlower | 2018-06-29 |
| | | | | PiperOrigin-RevId: 202693036 | ||
* | Add complex64 support to tf.lite runtime. | RJ Ryan | 2018-06-27 |
| | | | | PiperOrigin-RevId: 202403235 | ||
* | Implementation of pow. | A. Unique TensorFlower | 2018-06-27 |
| | | | | PiperOrigin-RevId: 202262513 | ||
* | Graduate the 'experimental' fully connected weights shuffling feature | A. Unique TensorFlower | 2018-06-21 |
| | | | | | | | | | (which enables faster runtime kernels) as no longer experimental, no longer behind a flag, and replace the bool experimental_shuffled_weights field on FullyConnectedOperator with an enum. PiperOrigin-RevId: 201569224 | ||
* | Fix operator names. | A. Unique TensorFlower | 2018-06-20 |
| | | | | PiperOrigin-RevId: 201422566 | ||
* | Implement TFLite Shape operator | Jared Duke | 2018-06-20 |
| | | | | PiperOrigin-RevId: 201389618 | ||
* | Reconcile enum types. | A. Unique TensorFlower | 2018-06-19 |
| | | | | PiperOrigin-RevId: 201210730 | ||
* | Implement reduce_sum | A. Unique TensorFlower | 2018-06-17 |
| | | | | PiperOrigin-RevId: 200895985 | ||
* | Merged commit includes the following changes: | A. Unique TensorFlower | 2018-06-14 |
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 200617269 by A. Unique TensorFlower: Internal change -- 200603378 by jpienaar: The output of the merge should be the value's and not the original output port. The output port of the IfOp is already taken into account by selecting the merge node and the output of the merge should be the value used (which is the 0th output of the merge node). -- 200601721 by A. Unique TensorFlower: Basic support for tf.tile that multiplies a single axis. -- 200600686 by A. Unique TensorFlower: Internal change. -- PiperOrigin-RevId: 200617269 | ||
* | Allow large allocations in toco. | A. Unique TensorFlower | 2018-06-08 |
| | | | | PiperOrigin-RevId: 199855838 | ||
* | Optimizing transpose_conv. | A. Unique TensorFlower | 2018-06-08 |
| | | | | PiperOrigin-RevId: 199839745 | ||
* | Implementation of TensorFlowEqual and TensorFlowNotEqual. | A. Unique TensorFlower | 2018-06-07 |
| | | | | PiperOrigin-RevId: 199602232 | ||
* | Support 5-inputs LSTM kernel in TFLite (float only). | Yu-Cheng Ling | 2018-06-01 |
| | | | | PiperOrigin-RevId: 198943559 | ||
* | implementation of sparse_to_dense | A. Unique TensorFlower | 2018-05-31 |
| | | | | PiperOrigin-RevId: 198710452 | ||
* | Modify the python interface to toco to provide arithmetic operations used by ↵ | A. Unique TensorFlower | 2018-05-11 |
| | | | | | | the model. PiperOrigin-RevId: 196314416 | ||
* | Implement sin operator | A. Unique TensorFlower | 2018-05-09 |
| | | | | PiperOrigin-RevId: 196062186 | ||
* | Add support for select (via tf.where) support to tflite. | A. Unique TensorFlower | 2018-05-07 |
| | | | | PiperOrigin-RevId: 195734246 | ||
* | add support for PadV2 | A. Unique TensorFlower | 2018-05-05 |
| | | | | PiperOrigin-RevId: 195503894 | ||
* | Merge changes from github. | Yifei Feng | 2018-04-23 |
| | | | | PiperOrigin-RevId: 194031845 | ||
* | Fixing a bug in strided slice. The op was not handling negative indices ↵ | A. Unique TensorFlower | 2018-04-17 |
| | | | | | | correctly. PiperOrigin-RevId: 193245539 | ||
* | Experiment with pre-shuffled fully-connected weights | A. Unique TensorFlower | 2018-04-13 |
| | | | | PiperOrigin-RevId: 192771889 | ||
* | Adding support for batch_to_space_nd op with crops. | A. Unique TensorFlower | 2018-04-11 |
| | | | | PiperOrigin-RevId: 192511036 | ||
* | Supporting FakeQuant num_bits and getting the fake quant op matching tensorflow. | A. Unique TensorFlower | 2018-04-10 |
| | | | | PiperOrigin-RevId: 192367307 | ||
* | Add quantized LogSoftmax. | A. Unique TensorFlower | 2018-04-10 |
| | | | | PiperOrigin-RevId: 192352432 | ||
* | Adding support for the standalone log operator. Basic import/export only, No ↵ | A. Unique TensorFlower | 2018-04-09 |
| | | | | | | run time support. PiperOrigin-RevId: 192135843 | ||
* | Guard against out-of-bounds dims accesses, even in optimized, no-asserts | A. Unique TensorFlower | 2018-04-04 |
| | | | | | | builds. PiperOrigin-RevId: 191617948 | ||
* | 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 | ||
* | Supports PReLU in TFLite & Toco. | Yu-Cheng Ling | 2018-03-22 |
| | | | | PiperOrigin-RevId: 190097557 |