aboutsummaryrefslogtreecommitdiffhomepage
path: root/tensorflow/contrib/lite/nnapi_delegate.cc
Commit message (Collapse)AuthorAge
...
* Do not delegate temporary tensors to NNAPI.Gravatar A. Unique TensorFlower2018-05-03
| | | | | | - also added delegation for MUL, and set the default scale to be 0.0f. PiperOrigin-RevId: 195288948
* Implement floor operatorGravatar A. Unique TensorFlower2018-04-26
| | | | PiperOrigin-RevId: 194490433
* Implementation of LessGravatar A. Unique TensorFlower2018-04-13
| | | | PiperOrigin-RevId: 192728635
* Added minimum op, better type support in maximum.Gravatar A. Unique TensorFlower2018-04-10
| | | | PiperOrigin-RevId: 192292693
* Implementation of ArgMaxGravatar A. Unique TensorFlower2018-04-09
| | | | PiperOrigin-RevId: 192236845
* Enable C++ warnings on a few targets.Gravatar Shashi Shekhar2018-04-03
| | | | PiperOrigin-RevId: 191454435
* Automated g4 rollback of changelist 190858242Gravatar Jianwei Xie2018-03-29
| | | | PiperOrigin-RevId: 190953197
* Automated g4 rollback of changelist 190835392Gravatar Anna R2018-03-28
| | | | PiperOrigin-RevId: 190858242
* Merge changes from github.Gravatar Jianwei Xie2018-03-28
| | | | PiperOrigin-RevId: 190835392
* Supports PReLU in TFLite & Toco.Gravatar Yu-Cheng Ling2018-03-22
| | | | PiperOrigin-RevId: 190097557
* Add support for the "DEQUANTIZE" op. This cover only ops that are generated ↵Gravatar A. Unique TensorFlower2018-03-07
| | | | | | | | by TOCO in order to handle UINT8 input to floating-point models. PiperOrigin-RevId: 188182372
* Implementation of tf.cast in TfLiteGravatar A. Unique TensorFlower2018-03-06
| | | | PiperOrigin-RevId: 188036286
* Add bidirectional sequence LSTM to TFLite Ops.Gravatar A. Unique TensorFlower2018-02-21
| | | | PiperOrigin-RevId: 186497571
* TFLite: Define a DELEGATE op type.Gravatar Yu-Cheng Ling2018-02-20
| | | | PiperOrigin-RevId: 186405366
* Basic LogSoftmax supportGravatar A. Unique TensorFlower2018-02-20
| | | | PiperOrigin-RevId: 186357933
* Implement SplitGravatar A. Unique TensorFlower2018-02-15
| | | | PiperOrigin-RevId: 185904437
* Implementation of tf.nn.top_k in TfLiteGravatar A. Unique TensorFlower2018-02-15
| | | | PiperOrigin-RevId: 185872292
* Supports op exp (tf.exp) in Toco and Tensorflow Lite.Gravatar A. Unique TensorFlower2018-02-14
| | | | PiperOrigin-RevId: 185747281
* Add bidirectional sequence RNN to TFLite Ops.Gravatar A. Unique TensorFlower2018-01-26
| | | | PiperOrigin-RevId: 183465032
* Support StridedSlice in TFLite for 1D-4D tensors.Gravatar A. Unique TensorFlower2018-01-23
| | | | PiperOrigin-RevId: 183020501
* Add unidirectional sequence LSTM to TFLite Ops.Gravatar A. Unique TensorFlower2018-01-23
| | | | PiperOrigin-RevId: 183010993
* Supports Squeeze in Tf Lite.Gravatar A. Unique TensorFlower2018-01-18
| | | | PiperOrigin-RevId: 182429180
* Create support for div and sub in tensorflow lite.Gravatar Andrew Selle2018-01-17
| | | | PiperOrigin-RevId: 182226574
* Rename RELU1 to RELU_N1_TO_1 to indicate that the image of the Op is in ↵Gravatar A. Unique TensorFlower2018-01-13
| | | | | | between -1 and 1. PiperOrigin-RevId: 181864303
* * Added code to delegate LSTM operation to NN API. Off by default.Gravatar A. Unique TensorFlower2018-01-11
| | | | | | * Added code to turn on NN API delegation for speaker id test. Off by default. PiperOrigin-RevId: 181666821
* Adds Mean op to Tensorflow Lite.Gravatar A. Unique TensorFlower2018-01-11
| | | | PiperOrigin-RevId: 181658399
* Support Transpose in TFLite.Gravatar Nupur Garg2018-01-08
| | | | | | The internal implementation supports 1D-4D tensors. PiperOrigin-RevId: 181221674
* Support SpaceToBatchND in TFLite.Gravatar Nupur Garg2018-01-02
| | | | | | | | 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 TFLiteGravatar Yu-Cheng Ling2017-12-14
| | | | | | | | | | 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 TfLiteGravatar A. Unique TensorFlower2017-12-14
| | | | PiperOrigin-RevId: 179101363
* Add unidirectional sequence RNN to TFLite Ops.Gravatar A. Unique TensorFlower2017-12-14
| | | | PiperOrigin-RevId: 179086788
* Add support for "Pad".Gravatar Nupur Garg2017-12-13
| | | | PiperOrigin-RevId: 178962340
* Add hvx/nnapi supports for Tensorflow Lite benchmarkGravatar Zhixian Yan2017-12-11
| | | | PiperOrigin-RevId: 178643959
* Internal Change.Gravatar Andrew Selle2017-11-10
PiperOrigin-RevId: 175307445