0

I make denoising autoencoder by tensorflow.

I use 799x161 matrix as input data.

here is my trainingg code

training_epochs = 100
batch_size      = 799
display_step    = 10

# Training
if do_train:
print ("Training Start")
for epoch in range(training_epochs):
    avg_cost = 0.
    num_batch = int(X_train.shape[0]/batch_size)
    for i in range(num_batch): 
        batch = X_train[i*batch_size : i*batch_size+batch_size]
        batch_noise = batch + 0.3*np.random.randn(batch.shape[0], 161) #addnoise
        feed1 = {x: batch_noise, y_: batch, keep_prob: 0.5}
        sess.run(optimizer, feed_dict = feed1)
        feed2 = {x: batch_noise, y_: batch, keep_prob: 1}
        avg_cost += sess.run(cost, feed_dict=feed2)/num_batch

    if epoch % display_step == 0:
        print ("Epoch: %03d/%03d cost: %.9f" % (epoch, training_epochs, avg_cost))

and test code

# TEST
testspeech = scipy.io.loadmat('data/test_cep.mat')
Y_test = testspeech['ans']
Y_test = np.array(Y_test)  # 799x161 cepstrum matrix
noisyspeech = scipy.io.loadmat('data/reverb_cep.mat')
Y_noisy = noisyspeech['ans']
Y_noisy = np.array(Y_noisy)  # 799x161 cepstrum addnoise matrix

batch = Y_test
batch_noise = Y_noisy

avg_cost += sess.run(cost, feed_dict=feed2)/num_batch

print ("cost: %.9f" % (avg_cost))

after test, i want to save output file as 799x161 matrix to compare with clean data and handle it in matlab.

My problem : But I don't know how to save it as matrix. I mean i want to save matrix as readable file in my PC. and i'm not sure matlab can read it.

Kim.Y
  • 1
  • 1

1 Answers1

0

Not sure I understand right
you want to save numpy array so that you can read it by matlab?

you are using scipy, I think it can do it
Assume you want to save Y_test and Y_noisy 

scipy.io.savemat('test.mat', dict('data'=Y_test, 'res'=Y_noisy))

then use matlab load test.mat, same question

Interesting, you are using scipy.io.loadmat but you don't know scipy.io.savemat?

Community
  • 1
  • 1
xxi
  • 1,350
  • 10
  • 23