| Commit message (Collapse) | Author | Age | |
|---|---|---|---|
| * | Use weak symbols to inject flex delegates |  Jared Duke | 2018-10-04 |
| | | | | | PiperOrigin-RevId: 215788183 | ||
| * | TFLite: Rename ResetVariableTensorsToZero -> ResetVariableTensors |  Yu-Cheng Ling | 2018-09-27 |
| | | | | | PiperOrigin-RevId: 214820383 | ||
| * | Add an experimental API to allow half precision for FP32 calculation. |  A. Unique TensorFlower | 2018-09-11 |
| | | | | | PiperOrigin-RevId: 212535448 | ||
| * | Modularize TF Lite interface definitions and reorganize file structure |  Pete Warden | 2018-09-07 |
| | | | | | PiperOrigin-RevId: 212064501 | ||
| * | Preallocate the node structure std::vector |  Andrew Selle | 2018-08-22 |
| | | | | | PiperOrigin-RevId: 209830234 | ||
| * | Extend external context for Edge TPU | A. Unique TensorFlower | 2018-08-16 |
| | | | | | PiperOrigin-RevId: 209077767 | ||
| * | Internal change | Jared Duke | 2018-08-15 |
| | | | | | PiperOrigin-RevId: 208910402 | ||
| * | Provide TfLiteContext arg to all TfLiteDelegate callbacks | Jared Duke | 2018-08-14 |
| | | | | | | | | Note: This change may break clients who have custom TfLiteDelegate implementations; this API has been and remains experimental and subject to such changes. PiperOrigin-RevId: 208683190 | ||
| * | Fix unnecessary semicolon (lint warning) |  Suharsh Sivakumar | 2018-08-10 |
| | | | | | PiperOrigin-RevId: 208262999 | ||
| * | Minor fixes to Eager delegate. |  Nupur Garg | 2018-08-08 |
| | | | | | PiperOrigin-RevId: 207937525 | ||
| * | Small changes to interpreter.{h,cc}: refactoring plus improved error message. | A. Unique TensorFlower | 2018-07-25 |
| | | | | | PiperOrigin-RevId: 205992521 | ||
| * | Initialize profiler pointer to null. |  Shashi Shekhar | 2018-07-17 |
| | | | | | PiperOrigin-RevId: 204972768 | ||
| * | [tflite] Add macro registration for type string to typeToTfLiteType. |  Eugene Brevdo | 2018-07-11 |
| | | | | | PiperOrigin-RevId: 204210338 | ||
| * | Remove framework's dependency on eigen and gemmlowp. | A. Unique TensorFlower | 2018-07-03 |
| | | | | | PiperOrigin-RevId: 203172717 | ||
| * | Add complex64 support to tf.lite runtime. |  RJ Ryan | 2018-06-27 |
| | | | | | PiperOrigin-RevId: 202403235 | ||
| * | Allow ops to annotate their own profile info. | A. Unique TensorFlower | 2018-06-21 |
| | | | | | PiperOrigin-RevId: 201579919 | ||
| * | 16-bit quantized add support in TFLite interpreter | A. Unique TensorFlower | 2018-06-20 |
| | | | | | PiperOrigin-RevId: 201374318 | ||
| * | Refresh allocations in the presence of dynamic tensors | A. Unique TensorFlower | 2018-06-19 |
| | | | | | PiperOrigin-RevId: 201193941 | ||
| * | Variable Tensor API for TF Lite. | Yu-Cheng Ling | 2018-06-13 |
| | | | | | PiperOrigin-RevId: 200457602 | ||
| * | Expose read-only versions of input tensors in tflite. | A. Unique TensorFlower | 2018-05-18 |
| | | | | | PiperOrigin-RevId: 197183345 | ||
| * | Expose read-only versions of tensors in tflite. | A. Unique TensorFlower | 2018-05-05 |
| | | | | | PiperOrigin-RevId: 195491701 | ||
| * | Fix a bug in profiler. | Shashi Shekhar | 2018-04-30 |
| | | | | | PiperOrigin-RevId: 194838948 | ||
| * | Convert int -> size_t so that implicit conversion doesn't lose integer ↵ | A. Unique TensorFlower | 2018-04-23 |
| | | | | | | | precision. PiperOrigin-RevId: 193955175 | ||
| * | Add a simple Profiler and instrument operator invocations in Interpreter. | Shashi Shekhar | 2018-04-16 |
| | | | | | PiperOrigin-RevId: 193133955 | ||
| * | TFLite: Copy output data from BufferHandle to CPU memory by default. | Yu-Cheng Ling | 2018-04-13 |
| | | | | | PiperOrigin-RevId: 192846824 | ||
| * | Add boolean type to tflite in favor of comparison implementations. | A. Unique TensorFlower | 2018-04-12 |
| | | | | | PiperOrigin-RevId: 192711203 | ||
| * | Make node and registration getter const. | Shashi Shekhar | 2018-04-09 |
| | | | | | PiperOrigin-RevId: 192183067 | ||
| * | Merge changes from github. |  Jacques Pienaar | 2018-03-21 |
| | | | | | PiperOrigin-RevId: 189945839 | ||
| * | TFLite Delegate: Add an `allow_dynamic_tensors` parameter. | Yu-Cheng Ling | 2018-03-19 |
| | | | | | PiperOrigin-RevId: 189641833 | ||
| * | Automated g4 rollback of changelist 189231636 | A. Unique TensorFlower | 2018-03-15 |
| | | | | | PiperOrigin-RevId: 189258641 | ||
| * | Merge changes from github. | Jacques Pienaar | 2018-03-15 |
| | | | | | PiperOrigin-RevId: 189231636 | ||
| * | Removed the pointer to model from interpreter. | A. Unique TensorFlower | 2018-03-15 |
| | | | | | PiperOrigin-RevId: 189186901 | ||
| * | [TFLite] Don't require a std::vector for Interpreter::SetTensorParameters*. | Eugene Brevdo | 2018-03-12 |
| | | | | | PiperOrigin-RevId: 188770522 | ||
| * | TFLite: Delegate Buffer Handle interface (take 2) | Yu-Cheng Ling | 2018-03-08 |
| | | | | | PiperOrigin-RevId: 188366045 | ||
| * | Automated g4 rollback of changelist 188263046 |  Gunhan Gulsoy | 2018-03-08 |
| | | | | | PiperOrigin-RevId: 188293315 | ||
| * | TFLite: Delegate Buffer Handle interface | Yu-Cheng Ling | 2018-03-07 |
| | | | | | PiperOrigin-RevId: 188263046 | ||
| * | TFLite: Ensures pointers to tensors won't be invalidated unless 16+ tensors ↵ | Yu-Cheng Ling | 2018-02-26 |
| | | | | | | | are added. PiperOrigin-RevId: 187052100 | ||
| * | Internal change. | A. Unique TensorFlower | 2018-02-21 |
| | | | | | PiperOrigin-RevId: 186534524 | ||
| * | Add delegate API to tflite. | Andrew Selle | 2018-02-09 |
| | | | | | | | | | | - Context gets GetNodes, num_nodes and PartitionNodesIntoSubgraphs. - TfLiteDelegate provides one function that need be implemented - Delegates choose nodes and those nodes are all compacted into a new macro kernel. PiperOrigin-RevId: 185204338 | ||
| * | Proper reallocation of dynamic tensors. | A. Unique TensorFlower | 2018-02-05 |
| | | | | | PiperOrigin-RevId: 184550199 | ||
| * | Allow reordering of execution order of nodes with indirect execution_plan. | Andrew Selle | 2018-02-01 |
| | | | | | | | | | Now whenever we want to operate in dependency order we use execution_plan. It begins as identity map (0, ..., nodes_size()) but can be changed in the future. This is the basis for more pluggable delegation. PiperOrigin-RevId: 184216885 | ||
| * | Cleanup: Ran clang-format on all *.{cc,h} files in ↵ | A. Unique TensorFlower | 2018-01-30 |
| | | | | | | | tensorflow/contrib/.../*.{hh,c}. PiperOrigin-RevId: 183855242 | ||
| * | Fix a comment | Yu-Cheng Ling | 2018-01-29 |
| | | | | | PiperOrigin-RevId: 183685209 | ||
| * | Remove THIRD_PARTY_ from #include guards |  Sanjoy Das | 2018-01-24 |
| | | | | | | | They don't make sense in the open source repository. PiperOrigin-RevId: 183140889 | ||
| * | Clean up the allocation logic in the interpreter. | A. Unique TensorFlower | 2018-01-13 |
| | | | | | PiperOrigin-RevId: 181865795 | ||
| * | Avoid a dependency between the interpreter and tensorflow | A. Unique TensorFlower | 2017-11-17 |
| | | | | | PiperOrigin-RevId: 176179748 | ||
| * | Internal Change. | Andrew Selle | 2017-11-10 |
| PiperOrigin-RevId: 175307445 | |||
 |
index : tensorflow | |
| machine learning framework |
| aboutsummaryrefslogtreecommitdiffhomepage |