-
The [current implementation of the SVDF layer](https://github.com/google-research/google-research/blob/master/kws_streaming/layers/svdf.py) doesn’t get fused as an SVDF operator when converted to TFLi…
-
@meelislootus
https://www.tensorflow.org/lite/microcontrollers
https://www.hackster.io/search?i=projects&q=tinyML
Cool projects:
https://www.hackster.io/contests/ElephantEdge
-
# Steps
1. You'll train a model in Jupyter notebook, named "training.ipynb", as instruc…
-
# Steps
1. You'll convert a model in Jupyter notebook, named "compiling.ipynb", as inst…
-
**System information**
- OS Platform and Distribution (e.g., Linux Ubuntu 22.04):
- TensorFlow installed from (source or binary): pip
- TensorFlow version (or github SHA if from source): 2.15.0.pos…
-
When I use the test_app, I know that different algorithms have their own execution effects.
But when I what to use `esp_nn_fully_connected_s8` opened in `repo/test/src/fully_connected_test_c`, I do…
-
@gregory-bronstain
Have you deployed transformer to TFLite micro kernel? I found that the model has different inference result with TFLite Mirco kernel than TFLite kernel with Python interface.
I a…
-
In the newer version of TFLM, user could see that the span source code and static vector source codes are being added after running create_tflm.py.
However, they are also accompanying with their res…
-
On a project I'm working on, we have a dependency both on [tensorflow](https://github.com/tensorflow/tensorflow) and [tflite-micro](https://github.com/tensorflow/tflite-micro).
We recently had an i…
-
I just found that Register_CONV_2D,QUANTIZE,FULLY_CONNECTED,SOFTMAX,DEPTHWISE_CONV_2D are not declared in micro_ops.h
I need to figure out how to fix the examples!
PS: Sorry, I did not fall off th…