def train(epoch):
metrics = ' '.join(
['\r[{}]', '{:.1f}%', '{}/{}', 'accu={:.3f}', 'loss={:.3f}', '{}/{}'])
for epoch_index in range(1, epoch + 1):
print('Epoch {}:'.format(epoch_index))
time_start = time.time()
epoch_trained = 0
right_ratio = []
bars_max = 20
batch_loss = []
batch_generator = data_util.get_batch(asks, answers)
for encoder, decoder, target, weights in batch_generator:
feed_dict = {}
for i in range(len(encoder_inputs)):
feed_dict[encoder_inputs[i]] = encoder[i]
for i in range(len(decoder_inputs)):
feed_dict[decoder_inputs[i]] = decoder[i]
feed_dict[decoder_targets[i]] = target[i]
feed_dict[decoder_weights[i]] = weights[i]
_, output, loss = sess.run(ops, feed_dict)
right = (target == np.asarray(output).argmax(axis=2))
right = right * weights
right = np.sum(right) / np.sum(weights)
right_ratio.append(right)
epoch_trained += data_util.batch_size
batch_loss.append(loss)
time_now = time.time()
time_spend = time_now - time_start
time_estimate = time_spend / (epoch_trained / samples_per_epoch)
percent = min(100, epoch_trained / samples_per_epoch) * 100
bars = math.floor(percent / 100 * bars_max)
sys.stdout.write(
metrics.format('=' * bars + '-' * (bars_max - bars), percent,
epoch_trained, samples_per_epoch,
np.mean(right_ratio), np.mean(batch_loss),
data_util.time(time_spend),
data_util.time(time_estimate)))
sys.stdout.flush()
if epoch_trained >= samples_per_epoch:
break
print('\n')
def train(noise_size, data_shape, batch_size, n_samples):
"""
@Author: Nelson Zhao
--------------------
@param noise_size: 噪声size
@param data_shape: 真实图像shape
@batch_size:
@n_samples: 显示示例图片数量
"""
tf_img_batch = data_util.get_batch(image=img_files,
image_W=IMAGE_W,
image_H=IMAGE_H,
batch_size=batch_size,
capacity=INPUT_CAPACITY)
# 存储loss
losses = []
steps = 0
inputs_real, inputs_noise = get_inputs(noise_size, data_shape[1],
data_shape[2], data_shape[3])
g_loss, d_loss = get_loss(inputs_real, inputs_noise, data_shape[-1])
g_train_opt, d_train_opt = get_optimizer(g_loss, d_loss, beta1,
learning_rate)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
try:
# for e in range(epochs):
for step in np.arange(max_steps):
step = step
if coord.should_stop():
break
batch_images = sess.run(tf_img_batch)
# print(batch_images)
# scale to -1, 1
# print(batch_images)
# batch_images = batch_images * 2 - 1
# noise
batch_noise = np.random.uniform(-1,
1,
size=(batch_size, noise_size))
# run optimizer
_ = sess.run(g_train_opt,
feed_dict={
inputs_real: batch_images,
inputs_noise: batch_noise
})
_ = sess.run(d_train_opt,
feed_dict={
inputs_real: batch_images,
inputs_noise: batch_noise
})
if step % 5000 == 0 or (step + 1) == max_steps:
# if steps % 101 == 0:
train_loss_d = d_loss.eval({
inputs_real: batch_images,
inputs_noise: batch_noise
})
train_loss_g = g_loss.eval({
inputs_real: batch_images,
inputs_noise: batch_noise
})
losses.append((train_loss_d, train_loss_g))
# 显示图片
samples = show_generator_output(sess, n_samples,
inputs_noise,
data_shape[-1])
plot_images(samples)
print(
"Epoch {}/{}....".format(step + 1, max_steps),
"Discriminator Loss: {:.4f}....".format(train_loss_d),
"Generator Loss: {:.4f}....".format(train_loss_g))
except tf.errors.OutOfRangeError:
print('Done training -- epoch limit reached')
finally:
coord.request_stop()
coord.join(threads)
# pred = tf.boolean_mask(pred_, mask)
# accuracy = tf.reduce_mean(tf.cast(tf.equal(pred, true), tf.float32))
with tf.Session(graph=graph) as sess:
if params.isTrain:
saver = tf.train.Saver(tf.global_variables())
try:
ckpt_path = tf.train.latest_checkpoint('./checkpoint/')
saver.restore(sess, ckpt_path)
except ValueError:
init = tf.global_variables_initializer()
sess.run(init)
for epoch in range(params.epoch_num):
for res_seq, res_labels, sentence_legth in data_util.get_batch(
train_set,
params.batch_size,
word2id,
tag2id,
shuffle=params.shuffle):
_, l, acc, global_nums, logits_, labels_ = sess.run(
[train_op, loss, accuracy, global_add, pred_, true_], {
word_ids: res_seq,
labels: res_labels,
sequence_lengths: sentence_legth,
dropout_pl: params.dropout
})
if global_nums % 20 == 0:
saver.save(sess,
'./checkpoint/model.ckpt',
global_step=global_nums)
print(
'epoch {}, global_step {}, loss: {:.4}, accuracy: {:.4} '
def decode():
# Load vocabularies.
doc_dict = data_util.load_dict(FLAGS.data_dir + "/doc_dict.txt")
sum_dict = data_util.load_dict(FLAGS.data_dir + "/sum_dict.txt")
if doc_dict is None or sum_dict is None:
logging.warning("Dict not found.")
docs, data = data_util.load_test_data(FLAGS.test_file, doc_dict)
with tf.Session() as sess:
# Create model and load parameters.
logging.info("Creating %d layers of %d units." %
(FLAGS.num_layers, FLAGS.size))
model = create_model(sess, True)
class_model = create_class_model(sess, True)
result = []
for idx, token_ids in enumerate(data):
# Get a 1-element batch to feed the sentence to the model.
encoder_inputs, decoder_inputs, encoder_len, decoder_len, class_output, class_len =\
data_util.get_batch(
{0: [(token_ids, [data_util.ID_GO, data_util.ID_EOS],[0,0])]}, _buckets, 0, FLAGS.batch_size, False, 0)
if FLAGS.batch_size == 1 and FLAGS.geneos:
loss, outputs = model.step(sess, encoder_inputs,
decoder_inputs, encoder_len,
decoder_len, True)
outputs = [np.argmax(item) for item in outputs[0]]
else:
outputs = model.step_beam(sess,
encoder_inputs,
encoder_len,
geneos=FLAGS.geneos)
# If there is an EOS symbol in outputs, cut them at that point.
if data_util.ID_EOS in outputs:
outputs = outputs[:outputs.index(data_util.ID_EOS)]
gen_sum = " ".join(data_util.sen_map2tok(outputs, sum_dict[1]))
gen_sum = data_util.sen_postprocess(gen_sum)
result.append(gen_sum)
logging.info("Finish {} samples. :: {}".format(idx, gen_sum[:75]))
#Get Encoder outputs
batchidx = 0
final_inputs = []
final_outputs = []
final_len = []
while batchidx + FLAGS.batch_size <= len(data):
encoder_inputs, decoder_inputs, encoder_len, decoder_len, class_output, class_len =\
data_util.get_batch(
{0: [(token_ids, [data_util.ID_GO, data_util.ID_EOS],[0,0])]}, _buckets, 0, FLAGS.batch_size, False, 0)
_, _, enc_outputs = model.step(sess, encoder_inputs,
decoder_inputs, encoder_len,
decoder_len, True)
enc_outputs = data_util.add_pad_for_hidden(enc_outputs,
_buckets[0][0])
final_inputs.append(enc_outputs)
final_outputs.append(class_output)
final_len.append(class_len)
batchidx += FLAGS.batch_size
final_inputs = np.asarray(final_inputs)
final_inputs = np.concatenate(final_inputs, 0)
final_outputs = np.asarray(final_outputs)
final_outputs = np.concatenate(final_outputs, 0)
final_len = np.asarray(final_len)
final_len = np.concatenate(final_len, 0)
print(final_inputs.shape, final_outputs.shape, final_len.shape)
#Hidden classifier
step_loss, output = class_model.step(sess, final_inputs[:],
final_outputs[:], final_len[:],
True)
clipped = np.array(output > 0.5, dtype=np.int)
#label = data_util.hidden_label_gen(FLAGS.test_file, "data/test.1981.msg.txt")
#make confusion matrix to get precision
#tn, fp, fn, tp = confusion_matrix(label.flatten(), clipped.flatten()).ravel()
#print("Test precision : ", tp/(tp+fp))
with open(FLAGS.test_output, "w") as f:
for idx, item in enumerate(result):
print(item, file=f)
for j in range(len(docs[idx])):
if clipped[idx][j] == 1:
print("Recommended identifier: " + docs[idx][j] + " ",
file=f)
print("\n", file=f)
def train():
logging.info("Preparing summarization data.")
docid, sumid, doc_dict, sum_dict, hidden_label= \
data_util.load_data(
FLAGS.data_dir + "/train.48615.diff",
FLAGS.data_dir + "/train.48615.msg",
FLAGS.data_dir + "/doc_dict.txt",
FLAGS.data_dir + "/sum_dict.txt",
FLAGS.doc_vocab_size, FLAGS.sum_vocab_size)
val_docid, val_sumid, val_hidd_label = \
data_util.load_valid_data(
FLAGS.data_dir + "/valid.3000.diff",
FLAGS.data_dir + "/valid.3000.msg",
doc_dict, sum_dict)
with tf.Session() as sess:
# Create model.
logging.info("Creating %d layers of %d units." %
(FLAGS.num_layers, FLAGS.size))
train_writer = tf.summary.FileWriter(FLAGS.tfboard, sess.graph)
model = create_model(sess, False)
# Read data into buckets and compute their sizes.
logging.info("Create buckets.")
dev_set = create_bucket(val_docid, val_sumid, val_hidd_label)
train_set = create_bucket(docid, sumid, hidden_label)
train_bucket_sizes = [len(train_set[b]) for b in range(len(_buckets))]
train_total_size = float(sum(train_bucket_sizes))
train_buckets_scale = [
sum(train_bucket_sizes[:i + 1]) / train_total_size
for i in range(len(train_bucket_sizes))
]
for (s_size, t_size, _), nsample in zip(_buckets, train_bucket_sizes):
logging.info("Train set bucket ({}, {}) has {} samples.".format(
s_size, t_size, nsample))
# This is the training loop.
step_time, loss = 0.0, 0.0
current_step = sess.run(model.global_step)
while current_step < FLAGS.max_iter:
random_number_01 = np.random.random_sample()
bucket_id = min([
i for i in range(len(train_buckets_scale))
if train_buckets_scale[i] > random_number_01
])
# Get a batch and make a step.
start_time = time.time()
encoder_inputs, decoder_inputs, encoder_len, decoder_len, class_output, class_len = \
data_util.get_batch(train_set, _buckets, bucket_id, FLAGS.batch_size, False,0)
step_loss, _ = model.step(sess, encoder_inputs, decoder_inputs,
encoder_len, decoder_len, False,
train_writer)
step_time += (time.time() - start_time) / \
FLAGS.steps_per_validation
loss += step_loss * FLAGS.batch_size / np.sum(decoder_len) \
/ FLAGS.steps_per_validation
current_step += 1
# Once in a while, we save checkpoint.
if current_step % FLAGS.steps_per_checkpoint == 0:
# Save checkpoint and zero timer and loss.
checkpoint_path = os.path.join(FLAGS.train_dir, "model.ckpt")
model.saver.save(sess,
checkpoint_path,
global_step=model.global_step)
# Once in a while, we print statistics and run evals.
if current_step % FLAGS.steps_per_validation == 0:
# Print statistics for the previous epoch.
perplexity = np.exp(float(loss))
logging.info("global step %d step-time %.2f ppl %.2f" %
(model.global_step.eval(), step_time, perplexity))
step_time, loss = 0.0, 0.0
# Run evals on development set and print their perplexity.
for bucket_id in range(len(_buckets)):
if len(dev_set[bucket_id]) == 0:
logging.info(" eval: empty bucket %d" % (bucket_id))
continue
encoder_inputs, decoder_inputs, encoder_len, decoder_len, class_output, class_len =\
data_util.get_batch(dev_set, _buckets, bucket_id, FLAGS.batch_size, False, 0)
#cl_eval_loss, _ = class_model.step(sess, class_input, class_output, class_len, True)
eval_loss, _, _ = model.step(sess, encoder_inputs,
decoder_inputs, encoder_len,
decoder_len, True)
eval_loss = eval_loss * FLAGS.batch_size \
/ np.sum(decoder_len)
eval_ppx = np.exp(float(eval_loss))
logging.info(" eval: bucket %d ppl %.2f" %
(bucket_id, eval_ppx))
sys.stdout.flush()
#Get Encoder outputs
batchidx = 0
final_inputs = []
final_outputs = []
final_len = []
while batchidx + FLAGS.batch_size <= train_bucket_sizes[0]:
encoder_inputs, decoder_inputs, encoder_len, decoder_len, class_output, class_len = \
data_util.get_batch(train_set, _buckets, bucket_id, FLAGS.batch_size, True, batchidx)
_, _, enc_outputs = model.step(sess, encoder_inputs,
decoder_inputs, encoder_len,
decoder_len, True)
enc_outputs = data_util.add_pad_for_hidden(enc_outputs,
_buckets[0][0])
final_inputs.append(enc_outputs)
final_outputs.append(class_output)
final_len.append(class_len)
batchidx += FLAGS.batch_size
final_inputs = np.asarray(final_inputs)
final_inputs = np.concatenate(final_inputs, 0)
final_outputs = np.asarray(final_outputs)
final_outputs = np.concatenate(final_outputs, 0)
final_len = np.asarray(final_len)
final_len = np.concatenate(final_len, 0)
print(final_inputs.shape, final_outputs.shape, final_len.shape)
#Hidden classifier
class_model = create_class_model(sess, False)
classification_curr_step = sess.run(class_model.global_step)
i = 0
while classification_curr_step <= FLAGS.class_max_iter:
_, step_loss, output = class_model.step(sess,
final_inputs[i:(i + 160)],
final_outputs[i:(i + 160)],
final_len[i:(i + 160)],
False)
classification_curr_step += 1
clipped = np.array(output > 0.5, dtype=np.int)
#print("i", i)
#print("clfcurrstep",classification_curr_step)
#print("clipped", clipped.flatten())
#print("final_outputs", final_outputs[i:(i+160)].flatten())
tn, fp, fn, tp = confusion_matrix(
final_outputs[i:(i + 160)].flatten(),
clipped.flatten()).ravel()
if (classification_curr_step % 40 == 0):
print("Train Precision", tp / (tp + fp + 0.1))
print("Train Accuracy", (tp + tn) / (tp + fp + tn + fn))
if (i + 160 == len(final_len)):
i = 0
else:
i += 160
# Once in a while, we save checkpoint.
if classification_curr_step % FLAGS.steps_per_checkpoint == 0:
# Save checkpoint and zero timer and loss.
checkpoint_path = os.path.join(FLAGS.class_train_dir,
"class_model.ckpt")
class_model.saver.save(sess,
checkpoint_path,
global_step=class_model.global_step)
print("test_file", FLAGS.test_file)
docs, data = data_util.load_test_data(FLAGS.test_file, doc_dict)
#test
# Create model and load parameters.
'''
logging.info("Creating %d layers of %d units." %
(FLAGS.num_layers, FLAGS.size))
result = []
for idx, token_ids in enumerate(data):
# Get a 1-element batch to feed the sentence to the model.
encoder_inputs, decoder_inputs, encoder_len, decoder_len, class_output, class_len =\
data_util.get_batch(
{0: [(token_ids, [data_util.ID_GO, data_util.ID_EOS],[0,0])]}, _buckets, 0, FLAGS.batch_size, False, 0)
if FLAGS.batch_size == 1 and FLAGS.geneos:
loss, outputs = model.step(sess,
encoder_inputs, decoder_inputs,
encoder_len, decoder_len, False)
outputs = [np.argmax(item) for item in outputs[0]]
else:
outputs = model.step_beam(
sess, encoder_inputs, encoder_len, geneos=FLAGS.geneos)
# If there is an EOS symbol in outputs, cut them at that point.
if data_util.ID_EOS in outputs:
outputs = outputs[:outputs.index(data_util.ID_EOS)]
gen_sum = " ".join(data_util.sen_map2tok(outputs, sum_dict[1]))
gen_sum = data_util.sen_postprocess(gen_sum)
result.append(gen_sum)
logging.info("Finish {} samples. :: {}".format(idx, gen_sum[:75]))
'''
#Get Encoder outputs
docid, sumid, doc_dict, sum_dict, hidden_label= \
data_util.load_data(
FLAGS.data_dir + "/test.1981.diff.txt",
FLAGS.data_dir + "/test.1981.msg.txt",
FLAGS.data_dir + "/doc_dict.txt",
FLAGS.data_dir + "/sum_dict.txt",
FLAGS.doc_vocab_size, FLAGS.sum_vocab_size)
test_set = create_bucket(docid, sumid, hidden_label)
test_bucket_sizes = [len(test_set[b]) for b in range(len(_buckets))]
test_total_size = float(sum(test_bucket_sizes))
test_buckets_scale = [
sum(test_bucket_sizes[:i + 1]) / test_total_size
for i in range(len(test_bucket_sizes))
]
batchidx = 0
final_inputs = []
final_outputs = []
final_len = []
#data.shape == (1, 158, 3) so I changed FLAGS.batch_size
FLAGS.batch_size = 158
while batchidx + FLAGS.batch_size <= len(data):
#bucket_id = (i for i in range(len(test_buckets_scale))
encoder_inputs, decoder_inputs, encoder_len, decoder_len, class_output, class_len = \
data_util.get_batch(test_set, _buckets, bucket_id, FLAGS.batch_size, True, batchidx)
_, _, enc_outputs = model.step(sess, encoder_inputs,
decoder_inputs, encoder_len,
decoder_len, True)
enc_outputs = data_util.add_pad_for_hidden(enc_outputs,
_buckets[0][0])
final_inputs.append(enc_outputs)
final_outputs.append(class_output)
final_len.append(class_len)
batchidx += 1
final_inputs = np.asarray(final_inputs)
final_inputs = np.concatenate(final_inputs, 0)
final_outputs = np.asarray(final_outputs)
final_outputs = np.concatenate(final_outputs, 0)
final_len = np.asarray(final_len)
final_len = np.concatenate(final_len, 0)
print(final_inputs.shape, final_outputs.shape, final_len.shape)
#Hidden classifier
step_loss, output = class_model.step(sess, final_inputs[:],
final_outputs[:], final_len[:],
True)
clipped = np.array(output > 0.5, dtype=np.int)
tn, fp, fn, tp = confusion_matrix(final_outputs[:].flatten(),
clipped.flatten()).ravel()
#with open('data/test.1981.msg.txt')as reader:
# testmsg=[]
# for i in range(1981):
# testmsg.append(reader.readline())
#sums = list(map(lambda x: x.split(), testmsg))
#labels = data_util.hidden_label_gen(FLAGS.test_file, sums)
#tn, fp, fn, tp = confusion_matrix(labels.flatten(), clipped.flatten())
print("Test Precision : ", tp / (tp + fp + 0.1))
print("Test Accuracy", (tp + tn) / (tp + fp + tn + fn))
with open(FLAGS.test_output, "w") as f:
for idx in range(1981):
for j in range(len(docs[idx])):
if clipped[idx][j] == 1:
print("Recommended identifier: " + docs[idx][j] + " ",
file=f)
print("\n", file=f)
# config loading
config = Config()
# data loading
train_source, train_source_length, \
train_target, train_target_length = load_data(
FLAGS.train_source_file, FLAGS.train_target_file,
config.source_max, config.target_max)
test_source, test_source_length, \
test_target, test_target_length = load_data(
FLAGS.test_source_file, FLAGS.test_target_file,
config.source_max, config.target_max)
batch_generator = get_batch(train_source, train_source_length, train_target,
train_target_length, config.batch_size,
config.num_epochs)
# model build
model = Seq2Seq(config, mode='train')
model.build()
sess = tf.Session()
if FLAGS.keep_training:
checkpoint_file = tf.train.latest_checkpoint(FLAGS.model_dir)
saver = tf.train.Saver()
saver.restore(sess, checkpoint_file)
else:
sess.run(tf.global_variables_initializer())
# summaries & saver
summary_writer = tf.summary.FileWriter(FLAGS.summary_dir)
