tflite-support icon indicating copy to clipboard operation
tflite-support copied to clipboard

TFLite Support is a toolkit that helps users to develop ML and deploy TFLite models onto mobile / ioT devices.

Results 112 tflite-support issues
Sort by recently updated
recently updated
newest added

Not sure what hinders from allowing downloading models in runtime and serving them? https://github.com/tensorflow/tflite-support/blob/master/tensorflow_lite_support/java/src/java/org/tensorflow/lite/support/common/FileUtil.java ``` public static MappedByteBuffer loadMappedFile(@NonNull Context context, @NonNull String filePath) throws IOException { SupportPreconditions.checkNotNull(context, "Context should...

Continuation of #679. @lu-wang-g

cla: yes

Not sure if this is the correct place to report this problem, or I should report it at tensorflow/tensorflow repository. As said [here](https://www.tensorflow.org/tutorials/images/data_augmentation), using Keras preprocessing layers as part of...

@lu-wang-g As discussed. Related #679

cla: yes

Continuation of #720 @lu-wang-g

cla: yes

i dont understand the problem from where its coming but when i call createtflitesimdmodule from the tflite.simd file it return empty buffers but before it was working as expected and...

few weeks ago this tensorflow official tutorial used to work now it breaks in model.evalute_tflite(test_data) with the follwing error: InvalidArgumentError: required broadcastable shapes [Op:Mul] ![image](https://user-images.githubusercontent.com/50331878/131367583-4bad7af1-227d-42cc-b6c5-4a95b5009755.png)

![image](https://user-images.githubusercontent.com/775466/110644221-2bde8880-81b5-11eb-888a-5330ee2fd633.png) it looks like the paths that are printed by a logger are wrong and do not even exist. Or am I missing anything here?

Hello tflite-support team! Thank you for building an awesome project. Do you have roadmap visibility for model personalization (transfer learning) on IoT devices (e.g. rpi) ? The feature has been...

Hello everybody :) I am using a custom TFLite model in an Android Studio Application and want to profile it so I can see the resources spent in each layer...