def train():
# prepare dataset
print("Starting to train from " + working_directory)
enc_train, dec_train, _, _ = data_utils.prepare_custom_data(working_directory,train_enc,train_dec,enc_vocab_size,dec_vocab_size)
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.666)
config = tf.ConfigProto(gpu_options=gpu_options)
config.gpu_options.allocator_type = 'BFC'
with tf.Session(config=config) as sess:
print("Creating model with %d layers and %d cells." % (num_layers, layer_size))
model = create_model(sess, False)
train_set = read_data(enc_train, dec_train, max_train_data_size)
train_bucket_sizes = [len(train_set[b]) for b in xrange(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 xrange(len(train_bucket_sizes))]
step_time, loss = 0.0, 0.0
current_step = 0
previous_losses = []
while True:
random_number_01 = np.random.random_sample()
bucket_id = min([i for i in xrange(len(train_buckets_scale))
if train_buckets_scale[i] > random_number_01])
start_time = time.time()
encoder_inputs, decoder_inputs, target_weights = model.get_batch(
train_set, bucket_id)
_, step_loss, _ = model.step(sess, encoder_inputs, decoder_inputs,
target_weights, bucket_id, False)
step_time += (time.time() - start_time) / steps_per_checkpoint
loss += step_loss / steps_per_checkpoint
current_step += 1
if current_step % steps_per_checkpoint == 0:
#perplexity = math.exp(loss) if loss < 300 else float('inf')
print ("Saved model at step %d with time %.2f "
% (model.global_step.eval(),
step_time))
if len(previous_losses) > 2 and loss > max(previous_losses[-3:]):
sess.run(model.learning_rate_decay_op)
previous_losses.append(loss)
checkpoint_path = os.path.join(working_directory, "seq2seq.ckpt")
model.saver.save(sess, checkpoint_path, global_step=model.global_step)
step_time, loss = 0.0, 0.0
sys.stdout.flush()
python类prepare_custom_data()的实例源码
def train():
# prepare dataset
print("Starting to train from " + working_directory)
enc_train, dec_train, _, _ = data_utils.prepare_custom_data(working_directory,train_enc,train_dec,enc_vocab_size,dec_vocab_size)
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.666)
config = tf.ConfigProto(gpu_options=gpu_options)
config.gpu_options.allocator_type = 'BFC'
with tf.Session(config=config) as sess:
print("Creating model with %d layers and %d cells." % (num_layers, layer_size))
model = create_model(sess, False)
train_set = read_data(enc_train, dec_train, max_train_data_size)
train_bucket_sizes = [len(train_set[b]) for b in xrange(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 xrange(len(train_bucket_sizes))]
step_time, loss = 0.0, 0.0
current_step = 0
previous_losses = []
count = 0
while True:
count += 1
print('Step: ' + str(count))
random_number_01 = np.random.random_sample()
bucket_id = min([i for i in xrange(len(train_buckets_scale))
if train_buckets_scale[i] > random_number_01])
start_time = time.time()
encoder_inputs, decoder_inputs, target_weights = model.get_batch(
train_set, bucket_id)
_, step_loss, _ = model.step(sess, encoder_inputs, decoder_inputs,
target_weights, bucket_id, False)
step_time += (time.time() - start_time) / steps_per_checkpoint
loss += step_loss / steps_per_checkpoint
current_step += 1
if current_step % steps_per_checkpoint == 0:
perplexity = math.exp(loss) if loss < 300 else float('inf')
print ("Saved model at step %d with perplexity %.2f "
% (model.global_step.eval(),
perplexity))
if len(previous_losses) > 2 and loss > max(previous_losses[-3:]):
sess.run(model.learning_rate_decay_op)
previous_losses.append(loss)
checkpoint_path = os.path.join(working_directory, "seq2seq.ckpt")
model.saver.save(sess, checkpoint_path, global_step=model.global_step)
step_time, loss = 0.0, 0.0
sys.stdout.flush()
def train():
# prepare dataset
print("Starting to train from " + working_directory)
enc_train, dec_train, _, _ = data_utils.prepare_custom_data(working_directory,train_enc,train_dec,enc_vocab_size,dec_vocab_size)
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.666)
config = tf.ConfigProto(gpu_options=gpu_options)
config.gpu_options.allocator_type = 'BFC'
with tf.Session(config=config) as sess:
print("Creating model with %d layers and %d cells." % (num_layers, layer_size))
model = create_model(sess, False)
train_set = read_data(enc_train, dec_train, max_train_data_size)
train_bucket_sizes = [len(train_set[b]) for b in xrange(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 xrange(len(train_bucket_sizes))]
step_time, loss = 0.0, 0.0
current_step = 0
previous_losses = []
while True:
random_number_01 = np.random.random_sample()
bucket_id = min([i for i in xrange(len(train_buckets_scale))
if train_buckets_scale[i] > random_number_01])
start_time = time.time()
encoder_inputs, decoder_inputs, target_weights = model.get_batch(
train_set, bucket_id)
_, step_loss, _ = model.step(sess, encoder_inputs, decoder_inputs,
target_weights, bucket_id, False)
step_time += (time.time() - start_time) / steps_per_checkpoint
loss += step_loss / steps_per_checkpoint
current_step += 1
if current_step % steps_per_checkpoint == 0:
#perplexity = math.exp(loss) if loss < 300 else float('inf')
print ("Saved model at step %d with time %.2f "
% (model.global_step.eval(),
step_time))
if len(previous_losses) > 2 and loss > max(previous_losses[-3:]):
sess.run(model.learning_rate_decay_op)
previous_losses.append(loss)
checkpoint_path = os.path.join(working_directory, "seq2seq.ckpt")
model.saver.save(sess, checkpoint_path, global_step=model.global_step)
step_time, loss = 0.0, 0.0
sys.stdout.flush()
