コード例 #1
0
ファイル: Main.py プロジェクト: danielso/ORNNs
else:
    print 'unknown optimization method'

angle=T.constant(0)        
#            angle=theano.typed_list.TypedListType(T.dscalar)('angle')
for param in all_params:
    if param in param2orthogonlize:
        delta=updates[param]-param
        tan_grad=tangent_grad(param,delta)
        angle=angle+T.sqrt((tan_grad**2).sum() / (delta**2).sum())/len(param2orthogonlize)
        if PROJ_GRAD==True:            
            updates[param] = param + tan_grad 
                
retract_updates=[]
for p in param2orthogonlize:
    retract_updates.append((p,GAIN*retraction(p)))

J=theano.gradient.jacobian(loss,param2orthogonlize) 
hidden=lasagne.layers.get_output(layers_to_concat) 

# Compile functions for training and computing output
train = theano.function([l_in.input_var, target], [loss,angle,grad_norm], updates=updates,allow_input_downcast=True)
probe_loss = theano.function([l_in.input_var, target], loss,allow_input_downcast=True)
probe_J = theano.function([l_in.input_var, target], J,allow_input_downcast=True)
retract_w = theano.function([], [], updates=retract_updates,allow_input_downcast=True)
get_output = theano.function([l_in.input_var], network_output,allow_input_downcast=True)
probe_hidden  = theano.function([l_in.input_var], hidden,allow_input_downcast=True)

track_train_error=[]
track_valid_error=[] 
track_test_error=[] 
コード例 #2
0
ファイル: toy_problems.py プロジェクト: danielso/ORNNs
         updates[l_rec.W_hid_to_hid] - l_rec.W_hid_to_hid)
     updates[l_rec.W_hid_to_hid] = l_rec.W_hid_to_hid + new_update
 # Theano functions for training and computing cost
 train = theano.function(
     [l_in.input_var, target_values, l_mask.input_var],
     loss, updates=updates)
 # Accuracy is defined as the proportion of examples whose absolute
 # error is less than .04
 accuracy = T.mean(abs(predicted_values - target_values) < .04)
 # Theano function for computing accuracy
 compute_accuracy = theano.function(
     [l_in.input_var, target_values, l_mask.input_var], accuracy)
 # Function for orthogonalizing weight matrix
 retract_w = theano.function(
     [], [],
     updates={l_rec.W_hid_to_hid: util.retraction(l_rec.W_hid_to_hid)})
 # Keep track of the number of samples used to train
 samples_trained = 0
 # Did we converge?
 success = True
 # Store cost over minibatches
 cost = 0
 while samples_trained < N_SAMPLES:
     # Generate a batch of data
     X, y, mask = task_options[task](sequence_length, BATCH_SIZE)
     cost += train(X.astype(theano.config.floatX),
                   y.astype(theano.config.floatX),
                   mask.astype(theano.config.floatX))
     # Quit when a non-finite value is found
     if any([not np.isfinite(cost),
             any([not np.all(np.isfinite(p.get_value()))