Commit message (Collapse) | Author | Age | ||
---|---|---|---|---|
... | ||||
* | Do not delegate temporary tensors to NNAPI. | A. Unique TensorFlower | 2018-05-03 | |
| | | | | | | - also added delegation for MUL, and set the default scale to be 0.0f. PiperOrigin-RevId: 195288948 | |||
* | Implement floor operator | A. Unique TensorFlower | 2018-04-26 | |
| | | | | PiperOrigin-RevId: 194490433 | |||
* | Implementation of Less | A. Unique TensorFlower | 2018-04-13 | |
| | | | | PiperOrigin-RevId: 192728635 | |||
* | Added minimum op, better type support in maximum. | A. Unique TensorFlower | 2018-04-10 | |
| | | | | PiperOrigin-RevId: 192292693 | |||
* | Implementation of ArgMax | A. Unique TensorFlower | 2018-04-09 | |
| | | | | PiperOrigin-RevId: 192236845 | |||
* | Enable C++ warnings on a few targets. | Shashi Shekhar | 2018-04-03 | |
| | | | | PiperOrigin-RevId: 191454435 | |||
* | Automated g4 rollback of changelist 190858242 | Jianwei Xie | 2018-03-29 | |
| | | | | PiperOrigin-RevId: 190953197 | |||
* | Automated g4 rollback of changelist 190835392 | Anna R | 2018-03-28 | |
| | | | | PiperOrigin-RevId: 190858242 | |||
* | Merge changes from github. | Jianwei Xie | 2018-03-28 | |
| | | | | PiperOrigin-RevId: 190835392 | |||
* | Supports PReLU in TFLite & Toco. | Yu-Cheng Ling | 2018-03-22 | |
| | | | | PiperOrigin-RevId: 190097557 | |||
* | Add support for the "DEQUANTIZE" op. This cover only ops that are generated ↵ | A. Unique TensorFlower | 2018-03-07 | |
| | | | | | | | | by TOCO in order to handle UINT8 input to floating-point models. PiperOrigin-RevId: 188182372 | |||
* | Implementation of tf.cast in TfLite | A. Unique TensorFlower | 2018-03-06 | |
| | | | | PiperOrigin-RevId: 188036286 | |||
* | Add bidirectional sequence LSTM to TFLite Ops. | A. Unique TensorFlower | 2018-02-21 | |
| | | | | PiperOrigin-RevId: 186497571 | |||
* | TFLite: Define a DELEGATE op type. | Yu-Cheng Ling | 2018-02-20 | |
| | | | | PiperOrigin-RevId: 186405366 | |||
* | Basic LogSoftmax support | A. Unique TensorFlower | 2018-02-20 | |
| | | | | PiperOrigin-RevId: 186357933 | |||
* | Implement Split | A. Unique TensorFlower | 2018-02-15 | |
| | | | | PiperOrigin-RevId: 185904437 | |||
* | Implementation of tf.nn.top_k in TfLite | A. Unique TensorFlower | 2018-02-15 | |
| | | | | PiperOrigin-RevId: 185872292 | |||
* | Supports op exp (tf.exp) in Toco and Tensorflow Lite. | A. Unique TensorFlower | 2018-02-14 | |
| | | | | PiperOrigin-RevId: 185747281 | |||
* | Add bidirectional sequence RNN to TFLite Ops. | A. Unique TensorFlower | 2018-01-26 | |
| | | | | PiperOrigin-RevId: 183465032 | |||
* | Support StridedSlice in TFLite for 1D-4D tensors. | A. Unique TensorFlower | 2018-01-23 | |
| | | | | PiperOrigin-RevId: 183020501 | |||
* | Add unidirectional sequence LSTM to TFLite Ops. | A. Unique TensorFlower | 2018-01-23 | |
| | | | | PiperOrigin-RevId: 183010993 | |||
* | Supports Squeeze in Tf Lite. | A. Unique TensorFlower | 2018-01-18 | |
| | | | | PiperOrigin-RevId: 182429180 | |||
* | Create support for div and sub in tensorflow lite. | Andrew Selle | 2018-01-17 | |
| | | | | PiperOrigin-RevId: 182226574 | |||
* | Rename RELU1 to RELU_N1_TO_1 to indicate that the image of the Op is in ↵ | A. Unique TensorFlower | 2018-01-13 | |
| | | | | | | between -1 and 1. PiperOrigin-RevId: 181864303 | |||
* | * Added code to delegate LSTM operation to NN API. Off by default. | A. Unique TensorFlower | 2018-01-11 | |
| | | | | | | * Added code to turn on NN API delegation for speaker id test. Off by default. PiperOrigin-RevId: 181666821 | |||
* | Adds Mean op to Tensorflow Lite. | A. Unique TensorFlower | 2018-01-11 | |
| | | | | PiperOrigin-RevId: 181658399 | |||
* | Support Transpose in TFLite. | Nupur Garg | 2018-01-08 | |
| | | | | | | The internal implementation supports 1D-4D tensors. PiperOrigin-RevId: 181221674 | |||
* | Support SpaceToBatchND in TFLite. | Nupur Garg | 2018-01-02 | |
| | | | | | | | | The internal implementation only supports 4D tensors for now. The dimension has to be 1 batch + 2 spatial + 1 other. The most common format within this restriction is NHWC. PiperOrigin-RevId: 180592870 | |||
* | Support BatchToSpaceND in TFLite | Yu-Cheng Ling | 2017-12-14 | |
| | | | | | | | | | | The internal implementation only support 4D tensors for now. The dimension has to be 1 batch + 2 spatial + 1 other. The most common format within this restriction is NHWC. Cropping is not supported by the internal implementation. PiperOrigin-RevId: 179143332 | |||
* | Implementation of Gather in TfLite | A. Unique TensorFlower | 2017-12-14 | |
| | | | | PiperOrigin-RevId: 179101363 | |||
* | Add unidirectional sequence RNN to TFLite Ops. | A. Unique TensorFlower | 2017-12-14 | |
| | | | | PiperOrigin-RevId: 179086788 | |||
* | Add support for "Pad". | Nupur Garg | 2017-12-13 | |
| | | | | PiperOrigin-RevId: 178962340 | |||
* | Add hvx/nnapi supports for Tensorflow Lite benchmark | Zhixian Yan | 2017-12-11 | |
| | | | | PiperOrigin-RevId: 178643959 | |||
* | Internal Change. | Andrew Selle | 2017-11-10 | |
PiperOrigin-RevId: 175307445 |