aboutsummaryrefslogtreecommitdiffhomepage
path: root/tensorflow/contrib/lite/toco/graph_transformations/propagate_fixed_sizes.cc
Commit message (Collapse)AuthorAge
* Use Ophints to support TfLite UnidirectionaSequenceLstm and add an e2e test.Gravatar A. Unique TensorFlower2018-10-09
| | | | | | Support peephole and num_proj as well. PiperOrigin-RevId: 216467578
* Return ::tensorflow::Status in Toco Graph Transformations.Gravatar Yu-Cheng Ling2018-10-09
| | | | PiperOrigin-RevId: 216392908
* Allow empty arrays to occur as the first input to the concat op.Gravatar A. Unique TensorFlower2018-09-25
| | | | | | | The conversion process fails for graphs that use tf.boolean_mask(..., axis=0) -- this op calls tf.concat with an empty array as the first argument. PiperOrigin-RevId: 214451470
* TOCO transformations updated to support dilated depthwise convolution.Gravatar Suharsh Sivakumar2018-09-19
| | | | PiperOrigin-RevId: 213729750
* Implement ZerosLikeGravatar A. Unique TensorFlower2018-09-17
| | | | PiperOrigin-RevId: 213227615
* Convert more kernel signatures to use runtime shapes.Gravatar A. Unique TensorFlower2018-09-06
| | | | PiperOrigin-RevId: 211874785
* Fixing Any operator.Gravatar A. Unique TensorFlower2018-08-31
| | | | PiperOrigin-RevId: 211159438
* Implementation of reduce_any.Gravatar A. Unique TensorFlower2018-08-28
| | | | PiperOrigin-RevId: 210507220
* Implementation of unpack op.Gravatar A. Unique TensorFlower2018-08-23
| | | | PiperOrigin-RevId: 210051131
* Fixing for TopKV2 shape propagation in Toco.Gravatar A. Unique TensorFlower2018-08-08
| | | | PiperOrigin-RevId: 207917321
* Implementation of logical_or.Gravatar A. Unique TensorFlower2018-07-30
| | | | PiperOrigin-RevId: 206549781
* Add one_hot op support to TFLiteGravatar Jared Duke2018-07-26
| | | | PiperOrigin-RevId: 206185190
* Support for shape attributes in custom ops for TocoGravatar A. Unique TensorFlower2018-07-25
| | | | PiperOrigin-RevId: 206012140
* Import/export support for Any, LogicalAnd, and LogicalNot ops.Gravatar A. Unique TensorFlower2018-07-18
| | | | PiperOrigin-RevId: 205134621
* Fixing gather to support round-tripping non-zero axis.Gravatar A. Unique TensorFlower2018-07-18
| | | | PiperOrigin-RevId: 205122011
* Fixing bugs in graphdef export of bool types and a few broken ops.Gravatar A. Unique TensorFlower2018-07-18
| | | | PiperOrigin-RevId: 205111208
* toco thinks Stack is the same as Pack.Gravatar A. Unique TensorFlower2018-07-17
| | | | | | | | | | | | | | 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_prodGravatar A. Unique TensorFlower2018-07-16
| | | | PiperOrigin-RevId: 204846139
* Implementation of arg_min.Gravatar A. Unique TensorFlower2018-07-10
| | | | PiperOrigin-RevId: 203908601
* Remove reduntant checks in gather op.Gravatar A. Unique TensorFlower2018-07-02
| | | | PiperOrigin-RevId: 203027634
* Ignore stop indices when shrink_axis_mask is set in tf.lite StridedSlice ↵Gravatar RJ Ryan2018-06-27
| | | | | | | | | | implementation. Due to an issue with negative StridedSlice indices in TensorFlow, the end indices can specify degenerate slices when negative indices are used to shrink an axis (e.g. for tf.range(4)[-1], start is -1, end is 0, and stride is 1). This fix works around the issue by ignoring stop indices entirely when an axis is shrinking, since in order to be shrunk the length is by definition 1. Fixes Issue #19260. PiperOrigin-RevId: 202398678
* Have EnsureBiasVector create bias vectors that already have theGravatar A. Unique TensorFlower2018-06-27
| | | | | | | | | | | constant value 0 and already have their shape set from the output activations shape; instead of having it create dummy placeholders and relying on PropagateFixedSizes to create the constant array. Rationale: It wasn't PropagateFixedSizes's job to create constant arrays, and that broke down in a case where the bias vectors not being constant prevented FuseBinaryIntoPrecedingAffine from running. PiperOrigin-RevId: 202365030
* Implementation of pow.Gravatar A. Unique TensorFlower2018-06-27
| | | | PiperOrigin-RevId: 202262513
* Automated g4 rollback of changelist 202120850Gravatar A. Unique TensorFlower2018-06-26
| | | | PiperOrigin-RevId: 202130585
* Have EnsureBiasVector create bias vectors that already have theGravatar A. Unique TensorFlower2018-06-26
| | | | | | | | | | | constant value 0 and already have their shape set from the output activations shape; instead of having it create dummy placeholders and relying on PropagateFixedSizes to create the constant array. Rationale: It wasn't PropagateFixedSizes's job to create constant arrays, and that broke down in a case where the bias vectors not being constant prevented FuseBinaryIntoPrecedingAffine from running. PiperOrigin-RevId: 202120850
* Fix operator names.Gravatar A. Unique TensorFlower2018-06-20
| | | | PiperOrigin-RevId: 201422566
* Fix a bug: the conversion of pure Conv to DepthwiseConv did notGravatar A. Unique TensorFlower2018-06-20
| | | | | | properly check the necessary precondition that the input depth is 1. PiperOrigin-RevId: 201389819
* Merged commit includes the following changes:Gravatar A. Unique TensorFlower2018-06-14
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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
* Optimized implementation of transpose conv. Uses an im2col array and GEMM, ↵Gravatar A. Unique TensorFlower2018-06-14
| | | | | | similar to conv. PiperOrigin-RevId: 200592004
* Optimizing transpose_conv.Gravatar A. Unique TensorFlower2018-06-08
| | | | PiperOrigin-RevId: 199839745
* Implementation of TensorFlowEqual and TensorFlowNotEqual.Gravatar A. Unique TensorFlower2018-06-07
| | | | PiperOrigin-RevId: 199602232
* implementation of sparse_to_denseGravatar A. Unique TensorFlower2018-05-31
| | | | PiperOrigin-RevId: 198710452
* Implement sin operatorGravatar A. Unique TensorFlower2018-05-09
| | | | PiperOrigin-RevId: 196062186
* Add support for select (via tf.where) support to tflite.Gravatar A. Unique TensorFlower2018-05-07
| | | | PiperOrigin-RevId: 195734246
* Adding Greater/GreaterEqual/LessEqual ops to complement Less.Gravatar A. Unique TensorFlower2018-05-07
| | | | PiperOrigin-RevId: 195704492
* add support for PadV2Gravatar A. Unique TensorFlower2018-05-05
| | | | PiperOrigin-RevId: 195503894
* Some fixes to support another TF graph:Gravatar A. Unique TensorFlower2018-05-04
| | | | | | | | | | | | | 1. Fix ResolveBatchNormalization to avoid deleting arrays that may still be used. 2. Correctly count the number of ops using a given array, even when some ops use the same array as more than one of their inputs. 3. In PropagateFixedSizes for Concatenation ops, when resolving a -1 wildcard to a fixed value, we were doing so in a local 'axis' variable without actually updating op->axis! The resulting -1 value still in op->axis tripped runtime code, causing the concatenation to misbehave during inference. PiperOrigin-RevId: 195454037
* Merge changes from github.Gravatar Patrick Nguyen2018-05-01
| | | | PiperOrigin-RevId: 194997009
* Adding some slightly more exhaustive strided_slice test parameters.Gravatar A. Unique TensorFlower2018-04-26
| | | | PiperOrigin-RevId: 194446000
* Make ProcessArgMaxOperator faster by reserving the correct output dims.Gravatar A. Unique TensorFlower2018-04-25
| | | | PiperOrigin-RevId: 194200078
* More relaxed size checking for TransposeConv, and miscellaneous bug fixes.Gravatar A. Unique TensorFlower2018-04-23
| | | | PiperOrigin-RevId: 193977375
* internal changeGravatar A. Unique TensorFlower2018-04-20
| | | | PiperOrigin-RevId: 193659701
* Fixing a bug in strided slice. The op was not handling negative indices ↵Gravatar A. Unique TensorFlower2018-04-17
| | | | | | correctly. PiperOrigin-RevId: 193245539
* Adding support for batch_to_space_nd op with crops.Gravatar A. Unique TensorFlower2018-04-11
| | | | PiperOrigin-RevId: 192511036
* Adding support for the standalone log operator. Basic import/export only, No ↵Gravatar A. Unique TensorFlower2018-04-09
| | | | | | run time support. PiperOrigin-RevId: 192135843
* Check arguments of ComputeConvSizes that should be positive.Gravatar A. Unique TensorFlower2018-04-04
| | | | PiperOrigin-RevId: 191604311
* Adding support for RandomUniform. Basic support for op import/export of ↵Gravatar A. Unique TensorFlower2018-04-02
| | | | | | RandomUniform, and constant resolution with static seeds. PiperOrigin-RevId: 191293897
* Supports PReLU in TFLite & Toco.Gravatar Yu-Cheng Ling2018-03-22
| | | | PiperOrigin-RevId: 190097557
* Support for transpose convolution. Includes striding, and a reference ↵Gravatar A. Unique TensorFlower2018-03-07
| | | | | | implementation. PiperOrigin-RevId: 188210975
* Implement support for unpartitioning tf.nn.embedding_lookup into a single ↵Gravatar A. Unique TensorFlower2018-02-27
| | | | | | gather. PiperOrigin-RevId: 187241089
generated by cgit v1.2.3 (git 2.39.1) at 2024-06-14 13:27:45 +0000