diff options
| author |  A. Unique TensorFlower <gardener@tensorflow.org> | 2017-12-01 12:32:10 -0800 |
|---|---|---|
| committer | TensorFlower Gardener <gardener@tensorflow.org> | 2017-12-01 12:35:41 -0800 |
| commit | e0a668270742718a595ca9620727986de26781af (patch) | |
| tree | 7792d7a713a4a147faea3f5f8f0faf8479f4bf23 /tensorflow/contrib/lite/models | |
| parent | 487558cf40f85539f740959dd54a4f5eee8e0560 (diff) | |
Update the comment in speech_hotword_model_test.
PiperOrigin-RevId: 177625918
Diffstat (limited to 'tensorflow/contrib/lite/models')
| -rw-r--r-- | tensorflow/contrib/lite/models/speech_hotword_model_test.cc | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/tensorflow/contrib/lite/models/speech_hotword_model_test.cc b/tensorflow/contrib/lite/models/speech_hotword_model_test.cc index 0b8266447a..f69cae8d2c 100644 --- a/tensorflow/contrib/lite/models/speech_hotword_model_test.cc +++ b/tensorflow/contrib/lite/models/speech_hotword_model_test.cc @@ -73,8 +73,8 @@ void RunTest(int model_input_tensor, int svdf_layer_state_tensor, float* output_ptr = interpreter->tensor(model_output_tensor)->data.f; // The first layer (SVDF) input size is 40 (speech_input_size). Each speech - // input frames for this model is 1280 floats, which can be fed to input in a - // sequence of size 32 (input_sequence_size). + // input frames for this model is 1600 floats, which can be fed to input in a + // sequence of size 40 (input_sequence_size). for (int i = 0; i < TestInputSize(input_frames); i++) { int frame_ptr = 0; for (int s = 0; s < input_sequence_size; s++) { |