I would like to be able to reset the weights of my entire Keras model so that I do not have to compile it again. Compiling the model is currently the main bottleneck of my code. Here is an example of what I mean:

import tensorflow as tf  model = tf.keras.Sequential([tf.keras.layers.Flatten(input_shape=(28, 28)),tf.keras.layers.Dense(16, activation='relu'),tf.keras.layers.Dense(10)
])model.compile(optimizer=tf.keras.optimizers.SGD(learning_rate=0.001),loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),metrics=['accuracy'])data = tf.keras.datasets.mnist
(x_train, y_train), (x_test, y_test) = data.load_data()model.fit(x=x_train, y=y_train, epochs=10)# Reset all weights of model here
# model.reset_all_weights() <----- something like thatmodel.fit(x=x_train, y=y_train, epochs=10)

I wrote a function that reinitializes weights in tensorflow 2.

def reinitialize(model):for l in model.layers:if hasattr(l,"kernel_initializer"):l.kernel.assign(l.kernel_initializer(tf.shape(l.kernel)))if hasattr(l,"bias_initializer"):l.bias.assign(l.bias_initializer(tf.shape(l.bias)))if hasattr(l,"recurrent_initializer"):l.recurrent_kernel.assign(l.recurrent_initializer(tf.shape(l.recurrent_kernel)))

It took me way longer than it should have to come up with this and i tried many things that failed in my specific use case. IMO this should be a standard TF feature.