state_vec = [ [PhoneIdx[PhoneState[i] ] ] for i in mem_label[start:end] ]
extended_out = [[0]]*(mask_max-utter_len)
utter_mask = [ np.ones((utter_len,1)),
np.zeros((mask_max-utter_len,1)) ]
val_inputs.append( np.vstack(extended_in) )
val_outputs.append(state_vec+extended_out)
masks.append( np.vstack(utter_mask) )
x_seq = np.dstack(val_inputs)
x_seq = np.asarray([ x.T for x in x_seq ],'float32')
y_hat_seq = np.hstack(val_outputs)
mask_seq = np.dstack(masks)
mask_seq = np.asarray([ m.T for m in mask_seq ],'float32')
val_result = nn.test(x_seq,mask_seq)
nequal = (np.argmax(val_result, axis=2) != y_hat_seq[:,0,:])
total_count += nequal.shape[0] * nequal.shape[1]
val_error_count += np.sum(nequal)
#val_maxpositions = np.ravel(np.argmax(val_result,axis=2).T)
#total_count += val_maxpositions.shape[0]
#val_error_count += len([ i \
# for i,j in zip(val_maxpositions,y_hat_seq) if i!=j])
valerror = float(val_error_count)/total_count
tStartR = time.time()
if VAL_SET_RATIO != 1:
prev_3, prev_2, prev_err = prev_2, prev_err, 100*valerror
print "Epoch:",epoch+1,"| Cost:",cost,"| Val Error:", 100*valerror,'%', "| Epoch time:",tEnd-tStart
zeros = np.zeros((mask_max-utter_len, mem_pgram.shape[1]))
extended_in = [ i for i in mem_pgram[start:end,:], zeros]
utter_mask = [ np.ones((utter_len,1)),
np.zeros((mask_max-utter_len,1)) ]
batched_inputs.append( np.vstack(extended_in) )
masks.append( np.vstack(utter_mask) )
x_seq = np.dstack(batched_inputs)
x_seq = np.asarray([ x.T for x in x_seq ],'float32')
mask_seq = np.dstack(masks)
mask_seq = np.asarray([ m.T for m in mask_seq ],'float32')
y_seq = nn.test(x_seq, mask_seq)
y_seq = np.argmax(y_seq, axis=2)
for one_seq, one_mask, utter_idx \
in zip(y_seq.T, mask_seq[:,:,0].T, pickList[p_s:p_e]) :
utter_len = IDs_utter[utter_idx][1]
one_seq = [ PhoneMap48to39[ PhoneMapIdxtoPh48[ph]] \
for ph in one_seq[:utter_len] ]
final_seq = []
if FIX:
# open a window of size 3, a|b|c
# if a == c and b != a, then directly change b to a :P
final_seq.append( one_seq[0] )
for i in xrange(1,len(one_seq)-1):
zeros = np.zeros((mask_max-utter_len, mem_pgram.shape[1]))
extended_in = [ i for i in mem_pgram[start:end,:], zeros]
utter_mask = [ np.ones((utter_len,1)),
np.zeros((mask_max-utter_len,1)) ]
batched_inputs.append( np.vstack(extended_in) )
masks.append( np.vstack(utter_mask) )
x_seq = np.dstack(batched_inputs)
x_seq = np.asarray([ x.T for x in x_seq ],'float32')
mask_seq = np.dstack(masks)
mask_seq = np.asarray([ m.T for m in mask_seq ],'float32')
y_seq = nn.test(x_seq, mask_seq)
y_seq = np.argmax(y_seq, axis=2)
for one_seq, one_mask, utter_idx \
in zip(y_seq.T, mask_seq[:,:,0].T, pickList[p_s:p_e]) :
utter_len = IDs_utter[utter_idx][1]
one_seq = [ PhoneMap48to39[ PhoneMapIdxtoPh48[ph]] \
for ph in one_seq[:utter_len] ]
final_seq = []
if FIX:
# open a window of size 3, a|b|c
# if a == c and b != a, then directly change b to a :P
final_seq.append( one_seq[0] )
for i in xrange(1,len(one_seq)-1):
utter_mask = [
np.ones((utter_len, 1)),
np.zeros((mask_max - utter_len, 1))
]
val_inputs.append(np.vstack(extended_in))
val_outputs.append(state_vec + extended_out)
masks.append(np.vstack(utter_mask))
x_seq = np.dstack(val_inputs)
x_seq = np.asarray([x.T for x in x_seq], 'float32')
y_hat_seq = np.dstack(val_outputs)
mask_seq = np.dstack(masks)
mask_seq = np.asarray([m.T for m in mask_seq], 'float32')
val_result = nn.test(x_seq, mask_seq)
nequal = (np.argmax(val_result, axis=2) != y_hat_seq[:, 0, :])
total_count += nequal.shape[0] * nequal.shape[1]
val_error_count += np.sum(nequal)
#pdb.set_trace()
#val_maxpositions = np.ravel(np.argmax(val_result,axis=2).T)
#total_count += val_maxpositions.shape[0]
#val_error_count += len([ i \
# for i,j in zip(val_maxpositions,y_hat_seq) if i!=j])
valerror = float(val_error_count) / total_count
tStartR = time.time()
if VAL_SET_RATIO != 1:
prev_3, prev_2, prev_err = prev_2, prev_err, 100 * valerror
print "Epoch:", epoch + 1, "| Cost:", cost, "| Val Error:", 100 * valerror, '%', "| Epoch time:", tEnd - tStart
zeros = np.zeros((mask_max-utter_len, mem_pgram.shape[1]))
extended_in = [ i for i in mem_pgram[start:end,:], zeros]
utter_mask = [ np.ones((utter_len,1)),
np.zeros((mask_max-utter_len,1)) ]
batched_inputs.append( np.vstack(extended_in) )
masks.append( np.vstack(utter_mask) )
x_seq = np.dstack(batched_inputs)
x_seq = np.asarray([ x.T for x in x_seq ],'float32')
mask_seq = np.dstack(masks)
mask_seq = np.asarray([ m.T for m in mask_seq ],'float32')
y1_seq = nn.test(x_seq, mask_seq)
y2_seq = nn.test(y1_seq, mask_seq)
y_seq = np.argmax(y2_seq, axis=2)
for one_seq, one_mask, utter_idx \
in zip(y_seq.T, mask_seq[:,:,0].T, pickList[p_s:p_e]) :
utter_len = IDs_utter[utter_idx][1]
one_seq = [ PhoneMap48to39[ PhoneMapIdxtoPh48[ph]] \
for ph in one_seq[:utter_len] ]
final_seq = []
if FIX:
# open a window of size 3, a|b|c
# if a == c and b != a, then directly change b to a :P
final_seq.append( one_seq[0] )
zeros = np.zeros((mask_max - utter_len, mem_pgram.shape[1]))
extended_in = [i for i in mem_pgram[start:end, :], zeros]
utter_mask = [
np.ones((utter_len, 1)),
np.zeros((mask_max - utter_len, 1))
]
batched_inputs.append(np.vstack(extended_in))
masks.append(np.vstack(utter_mask))
x_seq = np.dstack(batched_inputs)
x_seq = np.asarray([x.T for x in x_seq], 'float32')
mask_seq = np.dstack(masks)
mask_seq = np.asarray([m.T for m in mask_seq], 'float32')
result = nn.test(x_seq, mask_seq)
result = result.reshape(end - start, 48)
posteriorgram[start:end] += result[:]
#posteriorgram[start:end,:] /= phone_map_freq
# normalize to porb.
#ph_sum = np.zeros((BATCH_SIZE,1))
#ph_sum[:,0] = np.sum(posteriorgram[begin:end,:], axis=1)[:]
#posteriorgram[start:end,:] /= ph_sum
print result
#posteriorgram[begin:end,:] = result[:,:].T
del result