| Commit message (Collapse) | Author | Age |
|
|
|
| |
PiperOrigin-RevId: 216191084
|
|
|
|
| |
PiperOrigin-RevId: 215910400
|
|
|
|
| |
PiperOrigin-RevId: 215870962
|
|
|
|
|
|
| |
architectures.
PiperOrigin-RevId: 215757844
|
|
|
|
|
|
| |
microcontroller
PiperOrigin-RevId: 215748973
|
|
|
|
| |
PiperOrigin-RevId: 214883775
|
|
|
|
| |
PiperOrigin-RevId: 214879388
|
|
|
|
| |
PiperOrigin-RevId: 214831837
|
|
|
|
| |
PiperOrigin-RevId: 214767788
|
|
|
|
| |
PiperOrigin-RevId: 214763814
|
|
|
|
| |
PiperOrigin-RevId: 214668695
|
|
|
|
| |
PiperOrigin-RevId: 214661332
|
|
|
|
| |
PiperOrigin-RevId: 214627202
|
|
|
|
| |
PiperOrigin-RevId: 214384090
|
|
|
|
| |
PiperOrigin-RevId: 214377809
|
|
|
|
| |
PiperOrigin-RevId: 214346240
|
|
|
|
| |
PiperOrigin-RevId: 214062241
|
|
|
|
| |
PiperOrigin-RevId: 214004752
|
|
|
|
| |
PiperOrigin-RevId: 213693027
|
|
|
|
| |
PiperOrigin-RevId: 213673402
|
|
|
|
| |
PiperOrigin-RevId: 213651158
|
|
|
|
| |
PiperOrigin-RevId: 213640434
|
|
|
|
| |
PiperOrigin-RevId: 213536334
|
|
|
|
| |
PiperOrigin-RevId: 213386145
|
|
|
|
| |
PiperOrigin-RevId: 213350122
|
|
|
|
| |
PiperOrigin-RevId: 213316034
|
|
|
|
| |
PiperOrigin-RevId: 213314024
|
|
|
|
| |
PiperOrigin-RevId: 213281730
|
|
|
|
| |
PiperOrigin-RevId: 213275003
|
|
|
|
| |
PiperOrigin-RevId: 213037039
|
|
|
|
| |
PiperOrigin-RevId: 213023245
|
|
|
|
| |
PiperOrigin-RevId: 213012717
|
|
|
|
| |
PiperOrigin-RevId: 213007905
|
|
|
|
| |
PiperOrigin-RevId: 212884951
|
|
|
|
| |
PiperOrigin-RevId: 212861571
|
|
|
|
| |
PiperOrigin-RevId: 212834379
|
|
|
|
| |
PiperOrigin-RevId: 212826308
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
TFLite has an optimized matmul path for cases where the input and
filter tensors have matching width+height. However, this case doesn't
properly account for multiple *batches*. Account for this and add
an appropriate test.
Credit to zgxnet for the bug and proposed fix.
Fixes #21817
PiperOrigin-RevId: 212645329
|
|
|
|
| |
PiperOrigin-RevId: 212521825
|
|
|
|
| |
PiperOrigin-RevId: 212064501
|
|
|
|
| |
PiperOrigin-RevId: 211874785
|
|
|
|
| |
PiperOrigin-RevId: 211722113
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
LSTM Op.
This introduces a connection between forward and backward cells across subsequent layers when stacking bidirectional LSTM Ops on top of each other.
In more detail:
Previously, the Op had only one input that was fed into the layer in the
following way:
INPUT (INPUT_REVERSED)
| |
-----------------------
| FW_LSTM BW_LSTM | <----- bidi-LSTM cell (with one input / two outputs)
-----------------------
| |
FW_OUT BW_OUT
Now, the Op can have an (optional) auxiliary input in the following way:
AUX_INPUT (AUX_INPUT_REVERSED)
| |
INPUT | (INPUT_R'D.)|
| | | |
-------------------------
| \ / \ / |
| FW_LSTM BW_LSTM | <----- bidi-LSMT cell (with 2 inputs / 2 outputs)
-------------------------
| |
FW_OUT BW_OUT
When stacking these Ops, previously, only the following flow was allowed:
Input
/ \
FW_LSTM1 BW_LSTM1
| |
| |
FW_LSTM2 BW_LSTM2
| |
| |
FW_LSTM3 BW_LSTM3
\ /
Output
With the introduction of an auxiliary input to the bidi-LSTM layer, the forward
(FW_LSTMi) output of the ith layer is fed into as the input to the next layer
(hence, inputs to both FW_LSTM{i+1} and BW_LSTM{i+1}) and the backward output is
fed as the auxiliary inputs to both FW_LSTM{i+1} and BW_LSTM{i+1}). This way, the
stacking can be changed to allow for the "cross-linking" between subsequent
layer in the following way:
Input
/ \
FW_LSTM1 BW_LSTM1
| \ / |
| / \ |
FW_LSTM2 BW_LSTM2
| \ / |
| / \ |
FW_LSTM3 BW_LSTM3
\ /
Output
PiperOrigin-RevId: 211659472
|
|
|
|
| |
PiperOrigin-RevId: 211633744
|
|
|
|
|
|
| |
microcontrollers
PiperOrigin-RevId: 211543125
|
|
|
|
| |
PiperOrigin-RevId: 211505721
|
|
|
|
| |
PiperOrigin-RevId: 211459453
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This introduces a connection between forward and backward cells across subsequent layers when stacking bidirectional RNN Ops on top of each other.
In more detail:
Previously, the Op had only one input that was fed into the layer in the
following way:
INPUT (INPUT_REVERSED)
| |
---------------------
| FW_RNN BW_RNN | <----- bidi-RNN cell (with one input / two outpus)
---------------------
| |
FW_OUT BW_OUT
Now, the Op can have an (optional) auxiliary input in the following way:
AUX_INPUT (AUX_INPUT_REVERSED)
| |
INPUT | (INPUT_R'D.)|
| | | |
-----------------------
| \ / \ / |
| FW_RNN BW_RNN | <----- bidi-RNN cell (with 2 inputs / 2 outpus)
-----------------------
| |
FW_OUT BW_OUT
When stacking these Ops, previously, only the following flow was allowed:
Input
/ \
FW_RNN1 BW_RNN1
| |
| |
FW_RNN2 BW RNN2
| |
| |
FW_RNN3 BW_RNN3
\ /
Output
With the introduction of an auxiliary input to the bidi-RNN layer, the forward
(FW_RNNi) output of the ith layer is fed into as the input to the next layer
(hence, inputs to both FW_RNN{i+1} and BW_RNN{i+1}) and the backward output is
fed as the auxiliary inputs to both FW_RNN{i+1} and BW_RNN{i+1}). This way, the
stacking can be changed to allow for the "cross-linking" between subsequent
layer in the following way:
Input
/ \
FW_RNN1 BW_RNN1
| \ / |
| / \ |
FW_RNN2 BW RNN2
| \ / |
| / \ |
FW_RNN3 BW_RNN3
\ /
Output
PiperOrigin-RevId: 211401475
|
|
|
|
| |
PiperOrigin-RevId: 211085787
|
|
|
|
| |
PiperOrigin-RevId: 211028752
|