Commit message (Collapse) | Author | Age | |
---|---|---|---|
* | Update unidirectional sequential RNN to support state API. | A. Unique TensorFlower | 2018-08-29 |
| | | | | PiperOrigin-RevId: 210746360 | ||
* | Implementation of the unidirectional_sequence_rnn TFLite Op using the ↵ | A. Unique TensorFlower | 2018-05-10 |
| | | | | | | symmetric quantization. PiperOrigin-RevId: 196152754 | ||
* | Cleanup: Ran clang-format on all *.{cc,h} files in ↵ | A. Unique TensorFlower | 2018-01-30 |
| | | | | | | tensorflow/contrib/.../*.{hh,c}. PiperOrigin-RevId: 183855242 | ||
* | Add support for time_major shape format to the sequential RNN Op in TF Lite. | A. Unique TensorFlower | 2018-01-19 |
| | | | | | | | | This option, if set, changes the shape format of the inputs and outputs to [max_time, batch_size, depth]. If false, it uses [batch_size, max_time, depth]. By default, it is set to false. PiperOrigin-RevId: 182569507 | ||
* | Add unidirectional sequence RNN to TFLite Ops. | A. Unique TensorFlower | 2017-12-14 |
PiperOrigin-RevId: 179086788 |