You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Keras mode output: [[16. 19.]]
Lite mode output: RuntimeError: tensorflow/lite/kernels/fully_connected.cc:360 NumElements(bias) != SizeOfDimension(filter, 0) (1 != 2)Node number 0 (FULLY_CONNECTED) failed to prepare.Failed to apply the default TensorFlow Lite delegate indexed at 0.
Conversion Failure:
During conversion, the model fails due to the following check at tensorflow/lite/kernels/fully_connected.cc:360
if (bias) {
TF_LITE_ENSURE_EQ(context, NumElements(bias), SizeOfDimension(filter, 0));
}
The text was updated successfully, but these errors were encountered:
This issue originally reported by @YaoJiayi has been moved to this dedicated repository for LiteRT to enhance issue tracking and prioritization. To ensure continuity, we have created this new issue on your behalf.
We appreciate your understanding and look forward to your continued involvement.
1. System information
2. Code
This is the minimized code to reproduce the issue:
3. Failure after conversion
Output:
Conversion Failure:
tensorflow/lite/kernels/fully_connected.cc:360
The text was updated successfully, but these errors were encountered: