python - Autoencoder not learning while training -

python 3.5.2, tensorflow 1.0.0

somewhat new in programming autoencoders. trying implement simple network familiarize here. have used same input data in cnn able classify accuracy of 98%. data have 2000 row data , each row signal. trying 3 stacked layers of auto encoders 512 256 , 64 nodes.

class dimensions: input_width, input_height = 1,1024 batch_size = 50 layer = [input_width*input_height, 512, 256, 64] learningrate = 0.001  def myencoder(x,corrupt_prob,dimensions): current_input = corrupt(x) * corrupt_prob + x * (1 - corrupt_prob) encoder = [] layer_i, n_output in enumerate(dimensions.layer[1:]):     n_input = int(current_input.get_shape()[1])     w = tf.variable(         tf.random_uniform([n_input, n_output],                           -1.0 / math.sqrt(n_input),                           1.0 / math.sqrt(n_input)))     b = tf.variable(tf.zeros([n_output]))     encoder.append(w)     output = tf.nn.tanh(tf.matmul(current_input, w) + b)      current_input = output  z = current_input encoder.reverse() # build decoder using same weights layer_i, n_output in enumerate(model.layer[:-1][::-1]):     w = tf.transpose(encoder[layer_i])     b = tf.variable(tf.zeros([n_output]))     output = tf.nn.tanh(tf.matmul(current_input, w) + b)      current_input = output # have reconstruction through network y = current_input # cost function measures pixel-wise difference cost = tf.sqrt(tf.reduce_mean(tf.square(y - x)))  return z,y,cost  sess = tf.session() model = dimensions() data_train,data_test,label_train,label_test = load_data(datainfo,folder)  x = tf.placeholder(tf.float32,[model.batch_size,model.input_height*model.input_width]) corrupt_prob = tf.placeholder(tf.float32,[1]) z,y,cost = myencoder(x,corrupt_prob,dimensions) train_step = tf.train.adamoptimizer(model.learningrate).minimize(cost) lossfun = np.zeros(steps) sess.run(tf.global_variables_initializer())  in range(steps):     train_data = batchdata(data_train, model.batch_size)     epoch_loss = 0     j in range(model.batch_size):         sess.run(train_step,feed_dict={x:train_data,corrupt_prob:[1.0]})         c = sess.run(cost, feed_dict={x: train_data, corrupt_prob: [1.0]})         epoch_loss += c     lossfun[i] = epoch_loss     print('epoch', i, 'completed out of', steps, 'loss:', epoch_loss) 

my loss function appears this xaxis - no of iterations, y axis - loss

the loss doesn't decrease , network doesn't learn anything. appreciated !

in function myencoder, weight variables w , b initialized in every training step.