python - How should i feed this input into my regression network in tensorflow -

i working tensorflow, trying implement neural network regression purposes. regression consist of mapping input output. input in case samples , framed audio files, , output has mapped set of mfcc features each frame should correspond to.

the input stored this.

#one audio set [array([[frame],[frame],...,[frame]],dtype=float32)] 

and output stored this

[array([[feature1,  feature2,  feature3,          feature4,  feature5,  feature6,          feature7,  feature8,  feature9,          feature10,   feature11,   feature12,          feature13],....,[...]])] 

the model trying input simple linear model. since input or output data isn't 1 dimensional dataset, have provide in way such capable of handling vector sizes.

# set model weights w = tf.variable(rng.randn(), name="weight") b = tf.variable(rng.randn(), name="bias")   # construct linear model pred = tf.add(tf.mul(x, w), b) 

evaluated solutions

one solution flatten both input, , output , make use of fact each frame , feature vector consistent in length, , make weight w matrix has size [frame_length, feature_length], , change length of bias length of feature_length.

here attempt of doing this.

############################### training setup ################################## # parameters learning_rate = 0.01 training_epochs = 1000 display_step = 50  # tf graph input x = tf.placeholder(tf.float32, [none]) y = tf.placeholder(tf.float32, [none])  x_flatten = tf.reshape(x,[1,-1]) y_flatten = tf.reshape(y,[1,-1])  # set model weights w = tf.variable(rng.randn(), name="weight") w = tf.get_variable(name="w", shape=[train_set_data[0].shape[0],train_set_output[0].shape[0]])  b = tf.variable(rng.randn(), name="bias") b = tf.get_variable(name="b",shape=[1,train_set_output[0].shape[0]])  # construct linear model pred = tf.add(tf.matmul(x, w), b)  # mean squared error cost = tf.nn.softmax(pred)  # gradient descent optimizer = tf.train.gradientdescentoptimizer(learning_rate).minimize(cost)  # initializing variables init = tf.initialize_all_variables()  # launch graph tf.session() sess:     sess.run(init)     # fit training data     epoch in range(training_epochs):         (x, y) in zip(train_set_data, train_set_output):             sess.run(optimizer, feed_dict={x: x, y: y})          #display logs per epoch step         if (epoch+1) % display_step == 0:             c = sess.run(cost, feed_dict={x: train_set_data, y:train_set_output})             print "epoch:", '%04d' % (epoch+1), "cost=", "{:.9f}".format(c), \                 "w=", sess.run(w), "b=", sess.run(b)      print "optimization finished!"     training_cost = sess.run(cost, feed_dict={x: train_set_data, y: train_set_output})     print "training cost=", training_cost, "w=", sess.run(w), "b=", sess.run(b), '\n'      #graphic display     plt.plot(train_set_data, train_set_output, 'ro', label='original data')     plt.plot(train_set_data, sess.run(w) * train_set_data + sess.run(b), label='fitted line')     plt.legend()     plt.show() 

problem here getting error message not sure understand..

traceback (most recent call last):   file "tensorflow_datapreprocess_mfcc_extraction_rnn.py", line 177, in <module>     pred = tf.add(tf.matmul(x, w), b)   file "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/math_ops.py", line 1036, in matmul     name=name)   file "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_math_ops.py", line 911, in _mat_mul     transpose_b=transpose_b, name=name)   file "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/op_def_library.py", line 655, in apply_op     op_def=op_def)   file "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2156, in create_op     set_shapes_for_outputs(ret)   file "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1612, in set_shapes_for_outputs     shapes = shape_func(op)   file "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/common_shapes.py", line 81, in matmul_shape     a_shape = op.inputs[0].get_shape().with_rank(2)   file "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/tensor_shape.py", line 625, in with_rank     raise valueerror("shape %s must have rank %d" % (self, rank)) valueerror: shape (?,) must have rank 2 

could explain why getting error, or different solution 1 i've provided. not fond of solution, changing initial input/output structure, rather using 1 created prior preprocessing.