aboutsummaryrefslogtreecommitdiffhomepage
Commit message (Collapse)AuthorAge
...
* Made the collections argument of text_summary un-deprecated.Gravatar A. Unique TensorFlower2017-07-10
| | | | | | The argument is actually still used for adding summaries to collections. PiperOrigin-RevId: 161459624
* Dump LLVM IR to disk (when asked to) as individual files, and not a singleGravatar A. Unique TensorFlower2017-07-10
| | | | | | | concatenated file. This is a bit more usable since we can feed these files directly to opt, llc etc. PiperOrigin-RevId: 161459565
* Add check py_test to sanity to make sure BUILD files with py_test targets ↵Gravatar A. Unique TensorFlower2017-07-10
| | | | | | loads 'py_test' from tensorflow.bzl. PiperOrigin-RevId: 161457087
* [TF:XLA] Remove unneeded backend parameter in CreateModuleConfig.Gravatar Kay Zhu2017-07-10
| | | | PiperOrigin-RevId: 161453063
* Fixed crash in graph summarization toolGravatar Pete Warden2017-07-10
| | | | PiperOrigin-RevId: 161452440
* Fix bug with graph_replace on graphs with gradients. Added a test to verify ↵Gravatar A. Unique TensorFlower2017-07-10
| | | | | | the fix. PiperOrigin-RevId: 161452438
* Added Mobilenet support to TensorFlow toolingGravatar Pete Warden2017-07-10
| | | | PiperOrigin-RevId: 161445783
* Adds support for retrieving instances from the Google Compute Engine ↵Gravatar Frank Chen2017-07-10
| | | | | | | | instance group APIs, with support (in conjunction with UnionClusterResolver) for mapping multiple instance groups into one TensorFlow job (see the `testUnionMultipleInstanceRetrieval` test for details). This should simplify creating and using standardized grpc TensorFlow server based instances using Compute Engine instance groups for distributed training. PiperOrigin-RevId: 161443891
* Correct elu grad grad.Gravatar Alexandre Passos2017-07-10
| | | | | | Fixes issue #11091 PiperOrigin-RevId: 161427084
* Add documentation for build targets generated by tflibrary.Gravatar A. Unique TensorFlower2017-07-10
| | | | PiperOrigin-RevId: 161426590
* Speed up CreateMemoryMinimizingSequence.Gravatar Justin Lebar2017-07-10
| | | | | | | | | | In particular, BytesFreedIfScheduled is the O(n^2) kernel of our scheduling algorithm, and it used to do one hashtable lookup for each input and output buffer of its instruction. This patch gets rid of all of the hashtable lookups, replacing them with simple pointer dereferences. PiperOrigin-RevId: 161413495
* Fix SliceHelper _baseslice case to use the same dtype for begin and strides.Gravatar Vijay Vasudevan2017-07-10
| | | | | | | | | | | | | | | Using '1' automatically gets converted to int32, but when the user explicitly uses an int64 for the 'begin' argument, we want to make sure that 'strides' is of the same dtype, so we make sure we use a 1 of the proper dtype. Adds a test that failed before and passes with this change. Also tested the indexing case in addition to the _baseslice case, and added tests for both 'begin' as a Tensor as well as a non-Tensor. Fixes #11380. RELNOTES: Fixes 'strides' and 'begin' dtype mismatch when slicing using int64 Tensor index in python. See #11380. PiperOrigin-RevId: 161411479
* Fix output type of IOUGreaterThanThreshold to be bool.Gravatar A. Unique TensorFlower2017-07-10
| | | | PiperOrigin-RevId: 161404589
* Debugger.md: Fix missing line breaksGravatar Shanqing Cai2017-07-10
| | | | PiperOrigin-RevId: 161401043
* Fix tensorforest for using sparse-only data.Gravatar A. Unique TensorFlower2017-07-10
| | | | PiperOrigin-RevId: 161396592
* [TF:XLA] Use xla::Shape instead of TensorShape for representing ↵Gravatar Peter Hawkins2017-07-10
| | | | | | | | argument/resource update shapes to XlaCompiler. Change in preparation for adding implementations of the Stack... operators in the Tensorflow/XLA bridge. The representation of a Stack will be a tuple of (stack value, stack size). xla::Shape can represent tuples, but TensorShape cannot. PiperOrigin-RevId: 161391774
* Further BUILD cleanup in tensorflow/contrib/...Gravatar A. Unique TensorFlower2017-07-10
| | | | PiperOrigin-RevId: 161391365
* Update deprecated ByteSize to ByteSizeLongGravatar A. Unique TensorFlower2017-07-10
| | | | PiperOrigin-RevId: 161388633
* tfdbg CLI: add text summary of numeric valuesGravatar Shanqing Cai2017-07-09
| | | | | | | | | | For the `pt` or `print_tensor` command, the numeric summary can be activated with the `-s` option flag, e.g., tfdbg> pt -s cross_entropy/Log:0 Numeric summaries are applicable only to non-empty tensors of Boolean and numeric (int*, float*, complex*) types. PiperOrigin-RevId: 161350396
* Allow adding new functions to an already-run sessionGravatar Skye Wanderman-Milne2017-07-09
| | | | PiperOrigin-RevId: 161337922
* Fix typos in comments.Gravatar A. Unique TensorFlower2017-07-08
| | | | PiperOrigin-RevId: 161305803
* Reduce code duplication in the CreateScalarXXXComputation routines.Gravatar A. Unique TensorFlower2017-07-08
| | | | PiperOrigin-RevId: 161300540
* Update ops-related pbtxt files.Gravatar A. Unique TensorFlower2017-07-07
| | | | PiperOrigin-RevId: 161278460
* Add new transformation `tf.contrib.data.Dataset.interleave()`.Gravatar Derek Murray2017-07-07
| | | | | | | | This transformation acts like `tf.contrib.data.Dataset.flat_map()` but produces output elements from `k` input elements in an interleaved fashion, optionally in blocks of consecutive elements of length `b`. PiperOrigin-RevId: 161277614
* Account for the fact that the equivallent of the IsVariableInitialized op is ↵Gravatar Benoit Steiner2017-07-07
| | | | | | VarIsInitializedOp when working on ResourceVariables PiperOrigin-RevId: 161272800
* Rename HloInstruction::slice_stride(int64) toGravatar A. Unique TensorFlower2017-07-07
| | | | | | | | | HloInstruction::slide_strides(int64). This is so that the function matches the naming convention of the other slice accessors. PiperOrigin-RevId: 161272516
* Don't mess with nodes in the fanin or the fanout of a function since that canGravatar Benoit Steiner2017-07-07
| | | | | | lead to inlining failures. PiperOrigin-RevId: 161271376
* Disable graph optimizations in delay_compensated_gradient_descent_testGravatar Benoit Steiner2017-07-07
| | | | | | since they appear to make the test more flaky PiperOrigin-RevId: 161265638
* Fix FunctionDefsEqual to handle multiple attributes.Gravatar A. Unique TensorFlower2017-07-07
| | | | | | | | | | | | | | | | | | | | | | | | | | | The fix is to change StringPiece to string in our temporary maps, since the backing memory for the StringPiece was actually dead by the time we used the temporary maps. Note that FunctionDef::attr() is a proto2::Map, which has a value_type that behaves similarly to std::pair. Here's a re-written snippet of the original GetSetAttrs code, which makes the bug more apparent: std::map<StringPiece, AttrValue> GetSetAttrs(const FunctionDef& fdef) { std::map<StringPiece, AttrValue> attrs; for (std::pair<string, AttrValue> pair : fdef.attr()) { attrs[pair.first] = pair.second; } return attrs; } The problem is that the `pair` that captures each entry of fdef.attr() creates a copy of the underlying string, and we're converting that into a StringPiece. The underlying memory for the string is dead on each iteration of the loop. I've also added a test that fails with the old implementation, and passes with the new implementation. PiperOrigin-RevId: 161265130
* More WhereOp/TopK GPU bugfixes: use the direct cuda stream for CUB GPU kernel.Gravatar Eugene Brevdo2017-07-07
| | | | | | | | Turns out using the StreamInterface objects leads to "invalid resource handle" errors, so we have to use the cudaStream_t directly. This change is based on similar code in cuda_solvers.cc. PiperOrigin-RevId: 161261085
* Go: Update generated wrapper functions for TensorFlow ops.Gravatar A. Unique TensorFlower2017-07-07
| | | | PiperOrigin-RevId: 161258773
* Update ops-related pbtxt files.Gravatar A. Unique TensorFlower2017-07-07
| | | | PiperOrigin-RevId: 161257957
* Double MinSystemMemory for non-opt builds. This allows more complicated kernelsGravatar Eugene Brevdo2017-07-07
| | | | | | | | (i.e., CUB reduces) a more GPU memory to launch. Prior to this, calling WhereOp with the BFC allocator in non-opt mode led to "out of memory" error when launching the kernel. PiperOrigin-RevId: 161255358
* [tf.contrib.data] Add `ConcatenateDataset` to concatenate two datasets.Gravatar A. Unique TensorFlower2017-07-07
| | | | | | | | This change also adds helper class BinaryDatasetOpKernel, that simplifies parsing two input datasets. RELNOTES: Add `ConcatenateDataset` to concatenate two datasets. PiperOrigin-RevId: 161254998
* Add a README to the TPU contrib directory.Gravatar Brennan Saeta2017-07-07
| | | | PiperOrigin-RevId: 161254616
* Improving TF documentation for the convolution operation with padding scheme ↵Gravatar A. Unique TensorFlower2017-07-07
| | | | | | | | | | SAME. This CL introduces - a new expression for the total padding which is much easier to parse than the previous one - a new section which derives this expression, explaining why it is used. PiperOrigin-RevId: 161254603
* Refactor Keras Sequence utility.Gravatar Francois Chollet2017-07-07
| | | | | | Correct Keras version number. PiperOrigin-RevId: 161252947
* Fix KeyError when looking for 'softmax_tensor' in the layers tutorial.Gravatar Igor Saprykin2017-07-07
| | | | PiperOrigin-RevId: 161247019
* Added missing square on the L2 term in the python doc for the FTRL optimizer.Gravatar A. Unique TensorFlower2017-07-07
| | | | PiperOrigin-RevId: 161245173
* Add a tag constant, gpu, to present graph with GPU support.Gravatar A. Unique TensorFlower2017-07-07
| | | | PiperOrigin-RevId: 161242660
* PiperOrigin-RevId: 161240586Gravatar Skye Wanderman-Milne2017-07-07
|
* TFTS: Add srcs_version to structural_ensemble_testGravatar Allen Lavoie2017-07-07
| | | | | | Switched it to py_test for timeout=, but forgot to add PY2AND3. PiperOrigin-RevId: 161235480
* Enabled model pruning by defaultGravatar Benoit Steiner2017-07-07
| | | | PiperOrigin-RevId: 161234072
* Updating tf/contrib/boosted_trees to support multiclass diagonal hessian ↵Gravatar A. Unique TensorFlower2017-07-07
| | | | | | strategy. PiperOrigin-RevId: 161233946
* Fixed initialization of variables: when a variable w is initialized with theGravatar Benoit Steiner2017-07-07
| | | | | | value of another variable v, make sure that the initializer of v is run first. PiperOrigin-RevId: 161226052
* TFTS: Structural ensemble test timeout adjustment for asan/tsanGravatar Allen Lavoie2017-07-07
| | | | PiperOrigin-RevId: 161221736
* Automated g4 rollback of changelist 161203536Gravatar Suharsh Sivakumar2017-07-07
| | | | PiperOrigin-RevId: 161218103
* Internal-only changes.Gravatar Shanqing Cai2017-07-07
| | | | PiperOrigin-RevId: 161214648
* BUILD cleanup of tensorflow/contrib/learnGravatar A. Unique TensorFlower2017-07-07
| | | | PiperOrigin-RevId: 161209972
* Edits to "Threading and Queues" section of programmers guide.Gravatar Derek Murray2017-07-07
| | | | PiperOrigin-RevId: 161203568
generated by cgit v1.2.3 (git 2.39.1) at 2024-09-01 03:32:38 +0000