x_shared.set_value(x_valid)
y_shared.set_value(y_valid)
print " compute losses"
losses = []
for b in xrange(num_batches_valid):
# if b % 1000 == 0:
# print " batch %d/%d" % (b + 1, num_batches_valid)
loss = compute_loss(b)
losses.append(loss)
mean_valid_loss = np.sqrt(np.mean(losses))
print " mean validation loss (RMSE):\t\t%.6f" % mean_valid_loss
losses_valid.append(mean_valid_loss)
layers.dump_params(l6, e=e)
now = time.time()
time_since_start = now - start_time
time_since_prev = now - prev_time
prev_time = now
est_time_left = time_since_start * (float(NUM_CHUNKS - (e + 1)) / float(e + 1))
eta = datetime.now() + timedelta(seconds=est_time_left)
eta_str = eta.strftime("%c")
print " %s since start (%.2f s)" % (load_data.hms(time_since_start), time_since_prev)
print " estimated %s to go (ETA: %s)" % (load_data.hms(est_time_left), eta_str)
print
del chunk_data, xs_chunk, x_chunk, y_chunk, xs_valid, x_valid # memory cleanup
x_shared.set_value(x_valid)
y_shared.set_value(y_valid)
print " compute losses"
losses = []
for b in xrange(num_batches_valid):
# if b % 1000 == 0:
# print " batch %d/%d" % (b + 1, num_batches_valid)
loss = compute_loss(b)
losses.append(loss)
mean_valid_loss = np.sqrt(np.mean(losses))
print " mean validation loss (RMSE):\t\t%.6f" % mean_valid_loss
losses_valid.append(mean_valid_loss)
layers.dump_params(l6, e=e)
now = time.time()
time_since_start = now - start_time
time_since_prev = now - prev_time
prev_time = now
est_time_left = time_since_start * (float(NUM_CHUNKS -
(e + 1)) / float(e + 1))
eta = datetime.now() + timedelta(seconds=est_time_left)
eta_str = eta.strftime("%c")
print " %s since start (%.2f s)" % (load_data.hms(time_since_start),
time_since_prev)
print " estimated %s to go (ETA: %s)" % (load_data.hms(est_time_left),
eta_str)
print