else:
hidden_states, states = swapping_rnn(input_features,
initial_state=initial_state,
layers=args.layers,
sequence_lengths=None,
state_index=None)
# evaluate on selected outputs from rnn
eval_vecs = [tf.placeholder(tf.int32, [None], name='eval_%s' % i)
for i in range(args.num_steps - args.use_next_time_step)]
hidden_states = [tf.nn.embedding_lookup(hidden_state, state_indices)
for hidden_state, state_indices in zip(hidden_states, eval_vecs)]
hidden_matrix = tf.concat(hidden_states, 0)
loss_spec = make_loss_spec(dataspecs, mvn)
loss_matrix = multivariate_loss(hidden_matrix, loss_spec, ph_dict)
loss_vector = tf.reduce_sum(loss_matrix, reduction_indices=1) # is MB x 1
loss = tf.reduce_mean(loss_vector) # is scalar
loss_names = get_multivariate_loss_names(loss_spec)
eval_tensors = [loss, loss_vector, loss_matrix] + np.array(states).flatten().tolist()
# Create an object to train on this graph
initial_state = np.array(initial_state).flatten().tolist()
ph_dict.update({'initial_state': initial_state,
'eval_indices': eval_vecs})
trainer = ModelRunner(loss, ph_dict, args.learnrate, debug=args.debug)
data = StateTrackingBatcher(args.datafile, dataspecs,
batchsize=args.mb,
def run_dnn_test(args):
data_file, data_spec_file, outdir = args
"""Run DNN model on data file given parameters."""
nl = config.dnn.num_layers
hs = config.dnn.hidden_size
# io and state
print('running DNN with nl={}, hs={}'.format(nl, hs))
start = time.time()
dataspecs = json.load(open(data_spec_file, 'r'))
feature_spec = make_feature_spec(dataspecs)
datastart_index = dataspecs['counts']['index'][0]
normalizers = {'none': None, 'layer': layer_norm, 'batch': batch_normalize}
tf.set_random_seed(config.state.random_seed)
data = OnlineBatcher(data_file,
config.dnn.batch_size,
skipheader=True,
delimiter=' ')
# activation
if config.dnn.activation == 'tanh':
activation = tf.tanh
elif config.dnn.activation == 'relu':
activation = tf.nn.relu
else:
raise ValueError('Activation must be "relu", or "tanh"')
# mvn
if config.dnn.dist == "ident":
mvn = eyed_mvn_loss
elif config.dnn.dist == "diag":
mvn = diag_mvn_loss
elif config.dnn.dist == "full":
mvn = full_mvn_loss
raise ValueError('dnn.dist must be "ident", "diag", or "full"')
# setup tf model
x, ph_dict = join_multivariate_inputs(feature_spec, dataspecs, 0.75, 1000,
2)
h = dnn(x,
layers=[hs for i in range(nl)],
act=activation,
keep_prob=None,
norm=normalizers[config.dnn.normalizer],
scale_range=1.0)
loss_spec = make_loss_spec(dataspecs, mvn)
loss_matrix = multivariate_loss(h, loss_spec, ph_dict, variance_floor=0.01)
loss_vector = tf.reduce_sum(loss_matrix, reduction_indices=1) # is MB x 1
loss = tf.reduce_mean(loss_vector) # is scalar
loss_names = get_multivariate_loss_names(loss_spec)
eval_tensors = [loss, loss_vector, loss_matrix]
model = ModelRunner(loss,
ph_dict,
learnrate=config.dnn.lr,
opt='adam',
debug=config.dnn.debug,
decay_rate=1.0,
decay_steps=20)
raw_batch = data.next_batch()
current_loss = sys.float_info.max
not_early_stop = EarlyStop(20)
loss_feats = [triple[0] for triple in loss_spec]
# start training
start_time = time.time()
continue_training = not_early_stop(raw_batch, current_loss)
# mat is not None and self.badcount < self.badlimit and loss != inf, nan:
rst = []
while continue_training:
datadict = split_batch(raw_batch, dataspecs)
targets = {'target_' + name: datadict[name] for name in loss_feats}
datadict.update(targets)
current_loss, pointloss, contrib = model.eval(datadict, eval_tensors)
model.train_step(datadict)
for user, day, score, red in zip(
datadict['user'].flatten().tolist(),
datadict['time'].flatten().tolist(),
pointloss.flatten().tolist(),
datadict['redteam'].flatten().tolist()):
rst.append((user, int(day), score, red))
if data.index % 10000 == 1:
print('index: %s loss: %.4f' % (data.index, current_loss))
sys.stdout.flush()
raw_batch = data.next_batch()
continue_training = not_early_stop(raw_batch, current_loss)
if continue_training < 0:
break
# save the (user, day, score, red).
train_rst, test_rst = split_train_test(rst)
outfile1, outfile2 = FileName.get_dnn_rst_name()
save_rst(train_rst, outfile1)
save_rst(test_rst, outfile2)
print('')
eval_cr(test_rst, 'dnn')
dt = time.time() - start
print("run_dnn_test Done. Elapsed time is %.2f seconds." % dt)