ValueError: `to_annotate` can only be a `keras.layers.Layer` instance. You passed an instance of type: Dense.

import tensorflow as tf
from tensorflow.keras import layers, models
import tensorflow_model_optimization as tfmot

Use quantize_annotate_layer to annotate that the Dense layer

should be quantized.

input_shape = (20,)
annotated_model = tf.keras.Sequential([
tfmot.quantization.keras.quantize_annotate_layer(tf.keras.layers.Dense(20, input_shape=input_shape)),
tf.keras.layers.Flatten()
])

Use quantize_apply to actually make the model quantization aware.

quant_aware_model = tfmot.quantization.keras.quantize_apply(annotated_model)
quant_aware_model.summary()

when run the above code, error appears:"ValueError: to_annotate can only be a keras.layers.Layer instance. You passed an instance of type: Dense." Can anyone find the way to fix it? Thanks a lot

Start by running the provided TensorFlow and Keras example with tensorflow_model_optimization and confirm the quantize_annotate_layer error. Trace the type check at quantize_annotate_layer and quantize_apply, then verify that the example accepts the Dense layer and produces the quantization-aware model summary without the ValueError.