platform_hardware_interfaces/neuralnetworks
Lev Proleev e465f8e659 LSTM: require input layer norm weights to be omitted in case CIFG is used.
In case of CIFG LSTM, input layer norm weights are not used in the
computation.

Bug: 129126572
Test: mma
Change-Id: I57bc578606132a2c44c71ab63dd7645dcc001302
Merged-In: I57bc578606132a2c44c71ab63dd7645dcc001302
(cherry picked from commit 0480af9aa8)
2019-04-08 14:28:23 +01:00
..
1.0 Propagate ANNMemory_free to IBurstContext::freeMemory -- VTS update 2019-04-03 22:48:35 +00:00
1.1 Fix the documentation about paddings for SPACE_TO_BATCH_ND 2019-03-12 15:08:08 -07:00
1.2 LSTM: require input layer norm weights to be omitted in case CIFG is used. 2019-04-08 14:28:23 +01:00
README Add README to NeuralNetworks HAL 2018-03-05 12:59:35 -08:00
TEST_MAPPING Add presubmit tests to NNAPI -- hardware/interfaces/neuralnetworks 2019-02-19 12:04:24 -08:00

NeuralNetworks sample driver implementation is located at
frameworks/ml/nn/driver/sample.