Ufdjrw

I have the code below from Github Tutorial, and I want to access the values of each "x layer" and save it into numpy array after the training is completed.

def decoder(sampled_z, keep_prob):
 with tf.variable_scope("decoder", reuse=None):
 x = tf.layers.dense(sampled_z, units=inputs_decoder, activation=lrelu)
 x = tf.layers.dense(x, units=inputs_decoder * 2 + 1, activation=lrelu)
 x = tf.reshape(x, reshaped_dim)
 x = tf.layers.conv2d_transpose(x, filters=64, kernel_size=4, strides=2, 
 padding='same', activation=tf.nn.relu)
 x = tf.nn.dropout(x, keep_prob)
 x = tf.layers.conv2d_transpose(x, filters=64, kernel_size=4, strides=1, 
 padding='same', activation=tf.nn.relu)
 x = tf.nn.dropout(x, keep_prob)
 x = tf.layers.conv2d_transpose(x, filters=64, kernel_size=4, strides=1, 
 padding='same', activation=tf.nn.relu)
 x = tf.contrib.layers.flatten(x)
 x = tf.layers.dense(x, units=28*28, activation=tf.nn.sigmoid)
 img = tf.reshape(x, shape=[-1, 28, 28])
 return img

Regardless of whether you have a convolutional or a dense layer, and whether you have finished your training or not, you can access the values of your variables via session interface (once you have initialized them).

Consider following example:

import tensorflow as tf

def two_layer_perceptron(x):
 with x.graph.as_default():
 with tf.name_scope('fc'):
 fc = tf.layers.dense(
 inputs=x, units=2,
 kernel_initializer=tf.initializers.truncated_normal)
 with tf.name_scope('logits'):
 logits = tf.layers.dense(
 inputs=fc, units=2,
 kernel_initializer=tf.initializers.truncated_normal)
 return logits

x = tf.placeholder(tf.float32, shape=(None, 2))
logits = two_layer_perceptron(x)

# define loss, train operation and start training

with tf.Session() as sess:
 sess.run(tf.global_variables_initializer())
 # train here
 # ...
 # sess.run(train_op, feed_dict=...)
 # ...
 # when training is finished, do:
 trainable_vars = tf.trainable_variables()
 vars_vals = sess.run(trainable_vars)
 vars_and_names = [(val, var.name) for val, var in zip(vars_vals, trainable_vars)]


for val, name in vars_and_names:
 print(name, type(val), 'n', val)

# dense/kernel:0 <class 'numpy.ndarray'> 
# [[ 0.23275916 0.7079906 ]
# [-1.0366516 1.9141678 ]]
# dense/bias:0 <class 'numpy.ndarray'> 
# [0. 0.]
# dense_1/kernel:0 <class 'numpy.ndarray'> 
# [[-0.55649596 -1.4910121 ]
# [ 0.54917735 0.39449152]]
# dense_1/bias:0 <class 'numpy.ndarray'> 
# [0. 0.]

If you want access to specific variables in you network you may add them to collection via tf.add_to_collection() and later access them via tf.get_collection() OR you can just filter by variable name from the list of all variables (e.g. [v if 'conv' in v.name for v in tf.trainable_variables()])