Using a RBM with midi files in Tensor Flow, receiv

I'm trying to follow this notebook, problem is it's written for Py 2.7 and I'm trying to port it to Py 3.6. Luckily someone had ported the midi library to Py 3 https://github.com/louisabraham/python3-midi and I was successfully able to use this to parse the midi files into a numpy array. Now my problem is I'm receiving these errors

https://github.com/bhaktipriya/Blues/blob/master/Music.ipynb

TypeError                                 Traceback (most recent call last)
<ipython-input-62-f35c20bfe55b> in <module>()
      1 #backward pass, x samples drawn from prob distribution defn by (hk,w,bv)
----> 2 x_sample=gibbs_sample(2)
      3 print(x_sample)
      4 #h sampled from prob distrib defn by (x,w,bh)
      5 h=sample(tf.sigmoid(tf.matmul(x, W) + bh))

<ipython-input-57-943cbc813622> in gibbs_sample(k)
     13     #Gibbs sample(done for k iterations) is used to approximate the distribution of the RBM(defined by W, bh, bv)
     14     ct=tf.constant(0)
---> 15     [_, _, x_sample]=control_flow_ops.while_loop(lambda count, num_iter, *args: count < num_iter,gibbs_step, [ct, tf.constant(k), x], 1, False)
     16     #to stop tensorflow from propagating gradients back through the gibbs step
     17     x_sample=tf.stop_gradient(x_sample)

c:\users\ali\appdata\local\programs\python\python36\lib\site-packages\tensorflow\python\ops\control_flow_ops.py in while_loop(cond, body, loop_vars, shape_invariants, parallel_iterations, back_prop, swap_memory, name, maximum_iterations)
   3051       raise TypeError("body must be callable.")
   3052     if parallel_iterations < 1:
-> 3053       raise TypeError("parallel_iterations must be a positive integer.")
   3054 
   3055     if maximum_iterations is not None:

TypeError: parallel_iterations must be a positive integer.

I'm also getting strange errors with the shape of the numpy array in the training step

size_tr=tf.cast(tf.shape(x)[0], tf.float32)
eta=lr/size_tr
W_upd=tf.multiply(eta, tf.subtract(tf.matmul(tf.transpose(x), h), tf.matmul(tf.transpose(x_sample), h_sample)))
bv_upd=tf.multiply(eta, tf.reduce_sum(tf.subtract(x, x_sample), 0, True))
bh_upd=tf.multiply(eta, tf.reduce_sum(tf.subtract(h, h_sample), 0, True))
updt=[W.assign_add(W_upd), bv.assign_add(bv_upd), bh.assign_add(bh_upd)]
sess=tf.Session()
init=tf.initialize_all_variables()
sess.run(init)
for epoch in tqdm(range(epochs)):
            for song in songs:
                song=np.array(song)
                #reshaping song into chunks of timestep size
                chunks=song.shape[0]/timesteps
                chunks = int(np.floor(chunks))
                dur=chunks*timesteps
                dur = int(np.floor(dur))

                song=song[:dur]
                song=np.reshape(song, [chunks, song.shape[1]*timesteps])
                #Train the RBM on batch_size examples at a time
                for i in range(1, len(song), batch_size): 
                    tr_x=song[i:i+batch_size]
                    sess.run(updt, feed_dict={x: tr_x})
Error is:
    InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor 'x_7' with dtype float and shape [?,2340]
         [[Node: x_7 = Placeholder[dtype=DT_FLOAT, shape=[?,2340], _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]

This error message means that the sess.run() call depends on a placeholder that has not been fed. Looking at your code, there is only one placeholder, x. However, the "_7" in the error message suggests that the placeholder x has been created multiple times, for example by running the notebook cell that creates it multiple times, and it's possible that something in your graph structure depends on a previous instance of the placeholder. For example, if you re-executed some of the cells in the notebook out of order, it would be easy to end up in this situation.

You should be able to fix this error by executing tf.reset_default_graph() and then re-executing each of the cells in your notebook in order from top to bottom.