tensorflow: Unsupported Operation (MEAN) while trying to apply GpuDelegate to tflite

Please make sure that this is a bug. As per our GitHub Policy, we only address code/doc bugs, performance issues, feature requests and build/installation issues on GitHub. tag:bug_template

System information

• Have I written custom code: Nop, just some assembled statements
• OS Platform and Distribution (e.g., Linux Ubuntu 16.04): MacOS 10.14
• Mobile device (e.g. iPhone 8, Pixel 2, Samsung Galaxy) if the issue happens on mobile device: Samsung S9
• TensorFlow installed from (source or binary): binary
• TensorFlow version (use command below): tf-nightly 1.15.0.dev20190812
• Python version: 3.6.5

Describe the current behavior I’m trying to convert the Keras’s MobileNet model with float16 precision for Gpu Inference. But when running tasks, I encountered the following Error:

Caused by: java.lang.IllegalArgumentException: Internal error: Failed to apply delegate: Next operations are not supported by GPU delegate: MEAN: Operation is not supported. First 88 operations will run on the GPU, and the remaining 5 on the CPU.tensorflow/lite/kernels/conv.cc:259 bias->type != input_type (10 != 1)Node number 90 (CONV_2D) failed to prepare. tensorflow/lite/kernels/conv.cc:259 bias->type != input_type (10 != 1)Node number 3 (CONV_2D) failed to prepare.

Describe the expected behavior

Code to reproduce the issue the Python script for conversion is here:

import tensorflow as tf
import tensorflow.keras as keras

model = keras.applications.mobilenet.MobileNet(input_shape=None, alpha=1.0, depth_multiplier=1, dropout=1e-3, include_top=True, weights='imagenet', input_tensor=None, pooling=None, classes=1000)
converter = tf.lite.TFLiteConverter.from_keras_model_file("mobilenet.h5")
converter.optimizations = [tf.lite.Optimize.DEFAULT]
converter.target_spec.supported_types = [tf.lite.constants.FLOAT16]
tflite_model = converter.convert()
open("mobilenet.tflite", "wb").write(tflite_model)

and in Android code, I called tfliteOptions.setAllowFp16PrecisionForFp32(true); Other info / logs Include any logs or source code that would be helpful to diagnose the problem. If including tracebacks, please include the full traceback. Large logs and files should be attached.