| 5827bdb5bd8f83f0617693bbe2caca253a13c7ed |
|
16-Feb-2018 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Fix handling of types in RNN state import. Sanitize TF node names.
PiperOrigin-RevId: 185942921
/external/tensorflow/tensorflow/contrib/lite/toco/tooling_util.h
|
| dd5dab7c45e0089af81cfe2955bf3e24a7917771 |
|
14-Feb-2018 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Fixing IdentifyRelu1 transform to recognize min+max in addition to max+min.
PiperOrigin-RevId: 185725946
/external/tensorflow/tensorflow/contrib/lite/toco/tooling_util.h
|
| 528d0c5e4d148655b797368fd55fe6304730fece |
|
07-Feb-2018 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Add BatchMatMul support and improve tensorflow graphdef export by adding ops and fixing typing and resolving constant Transpose ops.
PiperOrigin-RevId: 184878663
/external/tensorflow/tensorflow/contrib/lite/toco/tooling_util.h
|
| 0255d9a9ca66d233ca4befcceff5d6e70b16d0e0 |
|
07-Feb-2018 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Support for quantized LstmCell, with initial reference runtime code.
The current 'optimized' code is just a copy of the reference code,
a true optimized implementation will follow separately.
PiperOrigin-RevId: 184830223
/external/tensorflow/tensorflow/contrib/lite/toco/tooling_util.h
|
| 60d5caeb2d506401d480503e21cc97c9a784c81b |
|
07-Feb-2018 |
A. Unique TensorFlower <gardener@tensorflow.org> |
We used to bypass fake-quant nodes in resolve_reorder_axes, as a hack as we
needed to preserve fake-quant nodes on constant weights as the only way to
encode min-max information when exporting to GraphDef.
Not anymore. Now we unconditionally enable the resolve_constant_fake_quant
transformation, and we don't do this bypass anymore; instead, when exporting
to GraphDef, we re-add FakeQuant nodes just before exporting, around
constant arrays that have minmax.
PiperOrigin-RevId: 184774680
/external/tensorflow/tensorflow/contrib/lite/toco/tooling_util.h
|
| 3cf771cc92402b1b52ea3d1f4b29046e4a7927b2 |
|
05-Feb-2018 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Support for quantized LSTM models.
PiperOrigin-RevId: 184476753
/external/tensorflow/tensorflow/contrib/lite/toco/tooling_util.h
|
| f6c1dd3264d518d74928676d49171af77a823692 |
|
30-Jan-2018 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Add transformation that exchanges a Reshape followed by an activation function.
PiperOrigin-RevId: 183735457
/external/tensorflow/tensorflow/contrib/lite/toco/tooling_util.h
|
| f1f4169e42320419b0a5df39c454ca39a57f5a42 |
|
28-Jan-2018 |
Zhixian Yan <zhixianyan@google.com> |
Internal Change
PiperOrigin-RevId: 183551521
/external/tensorflow/tensorflow/contrib/lite/toco/tooling_util.h
|
| 2b7d03c91d092cda88e6db345705fff3cd5b7b77 |
|
26-Jan-2018 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Allow passing dummy/custom minmax information on a per-array basis,
unlike the existing --default_ranges_{min,max} flags which only allowed
to set a single global value for all arrays.
This takes the form of a new embedded message in ModelFlags, which is
its own message so that it can be serialized separately. The command-line
interface is --arrays_extra_info_file=some_proto.pbtxt, i.e. we don't
try to make a command-line-flags-only interface, we mandate putting the info
in a file. The rationale is that users may want to specify custom minmax
for hundreds of arrays, so it would be cumbersome to have that all in a
command line.
This should be considered an experimental feature, in the sense that
in properly quantized models, minmax information is already embedded
in the graph (e.g. in FakeQuant nodes). This is an extension of the
existing --default_ranges_{min,max} feature which had turned out to be
too restrictive for many users.
PiperOrigin-RevId: 183326000
/external/tensorflow/tensorflow/contrib/lite/toco/tooling_util.h
|
| f8347ceebbad0e06552633fcdf8e63f52246ba62 |
|
24-Jan-2018 |
Sanjoy Das <sanjoy@google.com> |
Remove THIRD_PARTY_ from #include guards
They don't make sense in the open source repository.
PiperOrigin-RevId: 183140889
/external/tensorflow/tensorflow/contrib/lite/toco/tooling_util.h
|
| 8aa3253dbf881538d67e315e5ae6f1458d125416 |
|
23-Jan-2018 |
Nupur Garg <nupurgarg@google.com> |
Add support for conv and matmul operators with variable filter.
PiperOrigin-RevId: 182984061
/external/tensorflow/tensorflow/contrib/lite/toco/tooling_util.h
|
| cf327e8560fc044ab37e6a766c852e7b6546f228 |
|
17-Jan-2018 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Allow ReorderAxes to work on QUINT8 arrays. This will be necessary in order to support models that include tensorflow's DequantizeOp (such models were "quantized" using tensorflow's transform_graph tool).
PiperOrigin-RevId: 182131833
/external/tensorflow/tensorflow/contrib/lite/toco/tooling_util.h
|
| 6040ed631ba8e95b97c0e3edb1dd31e04569b521 |
|
20-Nov-2017 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Input types flags refactoring.
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
/external/tensorflow/tensorflow/contrib/lite/toco/tooling_util.h
|
| f5250528a952a37abb8ffae92e77e8f8961c2499 |
|
16-Nov-2017 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Move IODataType to a new types.proto in preparation for using it
in ModelFlags
PiperOrigin-RevId: 176024307
/external/tensorflow/tensorflow/contrib/lite/toco/tooling_util.h
|
| 0b15439f8f0f2d4755587f4096c3ea04cb199d23 |
|
10-Nov-2017 |
Andrew Selle <aselle@google.com> |
Internal Change.
PiperOrigin-RevId: 175307445
/external/tensorflow/tensorflow/contrib/lite/toco/tooling_util.h
|