tensorflow - machine learning framework

	Commit message (Collapse)	Author	Age
*	Rename TFLite Eager delegate -> Flex delegate	Yu-Cheng Ling	2018-09-27
\| \| \| \|	PiperOrigin-RevId: 214835588
*	Automated rollback of commit 82af048bc8c3c044c98a27b1c4c27bb62d4e4a14	Nupur Garg	2018-09-26
\| \| \| \|	PiperOrigin-RevId: 214705311
*	Rename TFLite Eager delegate -> Flex delegate	Yu-Cheng Ling	2018-09-26
\| \| \| \|	PiperOrigin-RevId: 214674717
*	Minimum change for generating Eager ops with Toco.	Yu-Cheng Ling	2018-09-05
\| \| \| \|	PiperOrigin-RevId: 211621189
*	Introduce post_training_quantize flag and deprecate quantize_weights flag.	Suharsh Sivakumar	2018-08-31
\| \| \| \|	PiperOrigin-RevId: 211124183
*	Removes SavedModel support from toco.cc.	Nupur Garg	2018-06-28
\| \| \| \|	PiperOrigin-RevId: 202249095
*	Quantize weights transformation for toco.	Suharsh Sivakumar	2018-06-01
\| \| \| \| \| \|	Finds float weight tensors, quantizes them to 8 bits, and adds Dequantize operations after them. PiperOrigin-RevId: 198955123
*	Support 5-inputs LSTM kernel in TFLite (float only).	Yu-Cheng Ling	2018-06-01
\| \| \| \|	PiperOrigin-RevId: 198943559
*	Post-transform pass to dedupe large constant arrays.	A. Unique TensorFlower	2018-05-03
\| \| \| \|	PiperOrigin-RevId: 195260578
*	Make toco generate uint8 weights that are safe for fast int8 kernels.	A. Unique TensorFlower	2018-04-18
\| \| \| \|	PiperOrigin-RevId: 193395910
*	Allow default min/max ranges for int16 data types.	A. Unique TensorFlower	2018-04-18
\| \| \| \|	PiperOrigin-RevId: 193362891
*	Fixes and cleanup to support more complex quantized models and adds ↵	A. Unique TensorFlower	2018-04-17
\| \| \| \| \| \|	PropagateFakeQuantNumBits. PiperOrigin-RevId: 193232630
*	Adds support for SavedModel to TOCO.	Nupur Garg	2018-03-25
\| \| \| \|	PiperOrigin-RevId: 190242571
*	Add basic support for quantized unfused LSTMs.	A. Unique TensorFlower	2018-02-22
\| \| \| \|	PiperOrigin-RevId: 186650338
*	Add available choices to toco flags and fix minor formatting issues.	Suharsh Sivakumar	2018-01-26
\| \| \| \|	PiperOrigin-RevId: 183415713
*	Better deprecation message for --input_type[s].	A. Unique TensorFlower	2017-12-04
\| \| \| \|	PiperOrigin-RevId: 177824668
*	Make drop_control_dependency a TocoFlag, not a ModelFlag.	A. Unique TensorFlower	2017-11-22
\| \| \| \|	PiperOrigin-RevId: 176680726
*	Input types flags refactoring.	A. Unique TensorFlower	2017-11-20
\| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \|	1. --input_type[s] is deprecated. Its semantics were not clearly defined, and included both ModelFlags-like semantics (describing a property of the input file) and TocoFlags-like semantics (describing a requested property of the output file). 2. New ModelFlags: --input_data_type[s], represented as a new 'type' field on each input array proto. This is unambiguously describing a property of the input file, similar to the existing input_array[s], input_shape[s] etc. 3. New TocoFlag: --inference_input_type. This is essentially the new name of --input_type, except that it's purely a transformation flag, only describing a property of the requested output file, not anymore mixed with ModelFlags-like semantics (now taken care of by 2.). The name --inference_input_type makes it clear that it's a companion of --inference_type. Also, --inference_input_type is now optional, defaulting to using the same value as --inference_type. This reflects the fact that most users want to do either float inference on a float input, or quantized inference on a quantized input. The only case at the moment where --inference_input_type is needed, is for doing float inference on a quantized input, which is typically done in some vision applications where the input is a bitmap image with integer-quantized channels. PiperOrigin-RevId: 176356352
*	Internal Change.	Andrew Selle	2017-11-10
	PiperOrigin-RevId: 175307445