v_dimen = 300
n_samples = 10000
batch_size = 32
X = tf.random_normal([n_samples, v_dimen], mean=0, stddev=1)
Y = tf.random_normal([n_samples, 1], mean=0, stddev=1)

q_in = tf.FIFOQueue(capacity=5, dtypes=tf.float32) # enqueue 5 batches
enqueue_op = q_in.enqueue(X)
numberOfThreads = 1
qr = tf.train.QueueRunner(q_in, [enqueue_op] * numberOfThreads)
tf.train.add_queue_runner(qr)
X_batch = q_in.dequeue()

q_out = tf.FIFOQueue(capacity=5, dtypes=tf.float32)  # enqueue 5 batches
enqueue_op = q_out.enqueue(Y)
numberOfThreads = 1
qr = tf.train.QueueRunner(q_out, [enqueue_op] * numberOfThreads)
tf.train.add_queue_runner(qr)
Y_batch = q_out.dequeue()

W = tf.Variable(tf.random.truncated_normal((v_dimen, 1), mean=0.0,stddev=0.001))
predicted_Y = f(X_batch) # some function on X, like tf.matmul(X_batch,W)
loss = tf.nn.l2_loss(Y_batch - predicted_Y)
optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.01).minimize(loss, var_list=[W])
init = tf.global_variables_initializer()

with tf.Session() as sess:
    sess.run(init)
    coord = tf.train.Coordinator()
    threads = tf.train.start_queue_runners(coord=coord)
    for i in range(1000):
        sess.run([optimizer]) # would like to run on mini batches

    coord.request_stop()
    coord.join(threads)