Custom weight initialization tensorflow tf.layers.dense

Question

I'm trying to set up custom initializer to tf.layers.dense where I initialize kernel_initializer with a weight matrix I already have.

u_1 = tf.placeholder(tf.float32, [784, 784])
first_layer_u = tf.layers.dense(X_, n_params, activation=None, 
                              kernel_initializer=u_1,
                              bias_initializer=tf.keras.initializers.he_normal())

This is throwing error saying ValueError: If initializer is a constant, do not specify shape.

Is it a problem to assign placeholder to kernel_initializer or am I missing something?

Answer 1

Jonathan's answer worked for me on conv as well -

kernel_in = np.random.uniform(100,1000,(filter_width, filter_height, input_channels, output_channels)).astype(np.float32)
init = tf.constant_initializer(kernel_in)
def model(x):
    x = tf.layers.conv2d(x, filters=3, kernel_size=1, strides=1, kernel_initializer=init)