tflite-support
tflite-support copied to clipboard
tensorflow
TFLite Support is a toolkit that helps users to develop ML and deploy TFLite models onto mobile / ioT devices.
The reason to use tf.test, is to be able to use [https://www.tensorflow.org/api_docs/python/tf/test/TestCase#assertProtoEquals](https://www.google.com/url?sa=D&q=https%3A%2F%2Fwww.tensorflow.org%2Fapi_docs%2Fpython%2Ftf%2Ftest%2FTestCase%23assertProtoEquals) instead of [our own implementation](https://github.com/tensorflow/tflite-support/blob/f451c8cd86d201db9ed76c9e4b0ac1524fecf547/tensorflow_lite_support/python/test/base_test.py#L24). @kinaryml Could you investigate if you can migrate away from using assertDeepAlmostEqual?
The current [C++ category mask test](https://github.com/tensorflow/tflite-support/blob/master/tensorflow_lite_support/cc/test/task/vision/image_segmenter_test.cc#L462) mocks an empty frame buffer to test the [Postprocess](https://github.com/tensorflow/tflite-support/blob/master/tensorflow_lite_support/cc/task/vision/image_segmenter.h#L120) function. There is no test for calling the Segment function with a frame buffer constructed...
Hi all, I am working on optimization. I have a .h5 keras model named "model.h5" --> I pruned this model to become a smaller and slighter model named "pruned_model.h5". I...
Hi, I'm trying to inspect the tflite model and extract quantization parameters for each layer (min/max fp, scale, offset). It can be easily done using Netron App (all needed values...
Hello Team, is it posibble to set the scale and offset of all the activations and weights manually, rather than going with tflite quantization schemes? Actually I want to run...
* Avoid using calling the object setters directly. Use property instead. For example, `obj.prop = 123` * Change the initialization interface of model output classes to: * Have readonly properties....
It turned out that `_eq_` and `options` functions in all Python Task APIs are no longer needed. Please remove them and avoid implementing them in future tasks. In other word,...
**I hope there is a more concise iOS demo for audio classification (YAMNet model) ,** thank you. I have tried https://github.com/tensorflow/examples/tree/master/lite/examples/sound_classification/ios, But this example does not use the model https://tfhub.dev/google/lite-model/yamnet/classification/tflite/1,...
Hi, I have a person segmentation model which I have converted to Tflite file, while running this model on **some** Android phones I am getting these errors - ``` Fatal...
Metadata
Owner
Metadata
TFLite Support is a toolkit that helps users to develop ML and deploy TFLite models onto mobile / ioT devices.