def _prepare(self):
# prepare reader
self.test_reader = paddle.batch(
reader=self.test_reader.create_reader(),
batch_size=self.args.batch_size)
# init paddle
paddle.init(use_gpu=self.args.use_gpu,
trainer_count=self.args.trainer_count)
# create parameters and trainer
model_out = self.model()
out_names = [x.name for x in model_out] \
if isinstance(model_out, collections.Iterable) \
else model_out.name
self.logger.info("out type: {}".format(model_out))
self.logger.info("out names: {}".format(out_names))
try:
self.parameters = paddle.parameters.Parameters.from_tar(
gzip.open(self.args.model_file, 'r'))
except IOError:
raise IOError('can not find: {}'.format(self.args.model_file))
self.inferer = paddle.inference.Inference(
output_layer=model_out,
parameters=self.parameters)
def main():
# init
paddle.init(use_gpu=False, trainer_count=1)
# network config
x = paddle.layer.data(name='x', type=paddle.data_type.dense_vector(13))
y_predict = paddle.layer.fc(input=x,
param_attr=paddle.attr.Param(name='w'),
size=1,
act=paddle.activation.Linear(),
bias_attr=paddle.attr.Param(name='b'))
y = paddle.layer.data(name='y', type=paddle.data_type.dense_vector(1))
cost = paddle.layer.mse_cost(input=y_predict, label=y)
# create parameters
parameters = paddle.parameters.create(cost)
# create optimizer of new remote updater to pserver
optimizer = paddle.optimizer.Momentum(momentum=0, learning_rate=1e-3)
trainer = paddle.trainer.SGD(cost=cost,
parameters=parameters,
update_equation=optimizer,
is_local=False,
pserver_spec=etcd_endpoints,
use_etcd=True)
# event_handler to print training and testing info
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
# FIXME: for cloud data reader, pass number is managed by master
# should print the server side pass number
if event.batch_id % 100 == 0:
print "Pass %d, Batch %d, Cost %f" % (
event.pass_id, event.batch_id, event.cost)
if isinstance(event, paddle.event.EndPass):
if (event.pass_id + 1) % 10 == 0:
result = trainer.test(
reader=paddle.batch(
uci_housing.test(), batch_size=2),
feeding={'x': 0,
'y': 1})
print "Test %d, %.2f" % (event.pass_id, result.cost)
# training
# NOTE: use uci_housing.train() as reader for non-paddlecloud training
trainer.train(
reader=paddle.batch(
paddle.reader.shuffle(
cloud_reader(
["/pfs/dlnel/public/dataset/uci_housing/uci_housing*"],
etcd_endpoints),
buf_size=500),
batch_size=2),
feeding={'x': 0,
'y': 1},
event_handler=event_handler,
num_passes=30)
def main():
paddle.init(use_gpu=False, trainer_count=1)
word_dict = paddle.dataset.imikolov.build_dict()
dict_size = len(word_dict)
firstword = paddle.layer.data(
name="firstw", type=paddle.data_type.integer_value(dict_size))
secondword = paddle.layer.data(
name="secondw", type=paddle.data_type.integer_value(dict_size))
thirdword = paddle.layer.data(
name="thirdw", type=paddle.data_type.integer_value(dict_size))
fourthword = paddle.layer.data(
name="fourthw", type=paddle.data_type.integer_value(dict_size))
nextword = paddle.layer.data(
name="fifthw", type=paddle.data_type.integer_value(dict_size))
Efirst = wordemb(firstword)
Esecond = wordemb(secondword)
Ethird = wordemb(thirdword)
Efourth = wordemb(fourthword)
contextemb = paddle.layer.concat(input=[Efirst, Esecond, Ethird, Efourth])
hidden1 = paddle.layer.fc(input=contextemb,
size=hiddensize,
act=paddle.activation.Sigmoid(),
layer_attr=paddle.attr.Extra(drop_rate=0.5),
bias_attr=paddle.attr.Param(learning_rate=2),
param_attr=paddle.attr.Param(
initial_std=1. / math.sqrt(embsize * 8),
learning_rate=1))
predictword = paddle.layer.fc(input=hidden1,
size=dict_size,
bias_attr=paddle.attr.Param(learning_rate=2),
act=paddle.activation.Softmax())
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 100 == 0:
result = trainer.test(
paddle.batch(
paddle.dataset.imikolov.test(word_dict, N), 32))
print "Pass %d, Batch %d, Cost %f, %s, Testing metrics %s" % (
event.pass_id, event.batch_id, event.cost, event.metrics,
result.metrics)
cost = paddle.layer.classification_cost(input=predictword, label=nextword)
parameters = paddle.parameters.create(cost)
adam_optimizer = paddle.optimizer.Adam(
learning_rate=3e-3,
regularization=paddle.optimizer.L2Regularization(8e-4))
trainer = paddle.trainer.SGD(cost, parameters, adam_optimizer)
trainer.train(
paddle.batch(paddle.dataset.imikolov.train(word_dict, N), 32),
num_passes=30,
event_handler=event_handler)
def main():
# init
paddle.init(use_gpu=False, trainer_count=1)
# network config
x = paddle.layer.data(name='x', type=paddle.data_type.dense_vector(13))
y_predict = paddle.layer.fc(input=x,
param_attr=paddle.attr.Param(name='w'),
size=1,
act=paddle.activation.Linear(),
bias_attr=paddle.attr.Param(name='b'))
y = paddle.layer.data(name='y', type=paddle.data_type.dense_vector(1))
cost = paddle.layer.mse_cost(input=y_predict, label=y)
# create parameters
parameters = paddle.parameters.create(cost)
# create optimizer
optimizer = paddle.optimizer.Momentum(momentum=0)
trainer = paddle.trainer.SGD(cost=cost,
parameters=parameters,
update_equation=optimizer)
# event_handler to print training and testing info
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 100 == 0:
print "Pass %d, Batch %d, Cost %f" % (
event.pass_id, event.batch_id, event.cost)
if isinstance(event, paddle.event.EndPass):
if (event.pass_id + 1) % 10 == 0:
result = trainer.test(
reader=paddle.batch(
uci_housing.test(), batch_size=2),
feeding={'x': 0,
'y': 1})
print "Test %d, %.2f" % (event.pass_id, result.cost)
# training
trainer.train(
reader=paddle.batch(
paddle.reader.shuffle(
uci_housing.train(), buf_size=500),
batch_size=2),
feeding={'x': 0,
'y': 1},
event_handler=event_handler,
num_passes=30)
def test_param_conf_order(self):
paddle.init()
cost = train()
parameters = paddle.parameters.create(cost)
adagrad = paddle.optimizer.AdaGrad(
learning_rate=3e-3,
regularization=paddle.optimizer.L2Regularization(rate=8e-4))
trainer = paddle.trainer.SGD(cost, parameters, adagrad)
for p in trainer.get_topology_proto().parameters:
if p.name == "_fc1.w0":
self.assertEqual(p.decay_rate, 6e-4)
else:
self.assertEqual(p.decay_rate, 8e-4)
def main():
paddle.init(use_gpu=False, trainer_count=1)
# define network topology
crf_cost, crf_dec = db_lstm()
# create parameters
parameters = paddle.parameters.create([crf_cost, crf_dec])
# create optimizer
optimizer = paddle.optimizer.Momentum(
momentum=0,
learning_rate=2e-2,
regularization=paddle.optimizer.L2Regularization(rate=8e-4),
model_average=paddle.optimizer.ModelAverage(
average_window=0.5, max_average_window=10000), )
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 100 == 0:
print "Pass %d, Batch %d, Cost %f, %s" % (
event.pass_id, event.batch_id, event.cost, event.metrics)
trainer = paddle.trainer.SGD(cost=crf_cost,
parameters=parameters,
update_equation=optimizer)
parameters.set('emb', load_parameter(conll05.get_embedding(), 44068, 32))
trn_reader = paddle.batch(
paddle.reader.shuffle(
conll05.test(), buf_size=8192), batch_size=10)
feeding = {
'word_data': 0,
'ctx_n2_data': 1,
'ctx_n1_data': 2,
'ctx_0_data': 3,
'ctx_p1_data': 4,
'ctx_p2_data': 5,
'verb_data': 6,
'mark_data': 7,
'target': 8
}
trainer.train(
reader=trn_reader,
event_handler=event_handler,
num_passes=10000,
feeding=feeding)
def main(task="train", use_gpu=False, trainer_count=1, save_dir="models"):
if task == "train":
if not os.path.exists(save_dir):
os.mkdir(save_dir)
paddle.init(use_gpu=use_gpu, trainer_count=trainer_count)
cost = network()
parameters = paddle.parameters.create(cost)
optimizer = paddle.optimizer.Momentum(
learning_rate=0.1 / 128.0,
momentum=0.9,
regularization=paddle.optimizer.L2Regularization(rate=0.0005 * 128))
trainer = paddle.trainer.SGD(cost=cost,
parameters=parameters,
update_equation=optimizer)
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 100 == 0:
logger.info("Pass %d, Batch %d, Cost %f, %s" %
(event.pass_id, event.batch_id, event.cost,
event.metrics))
if isinstance(event, paddle.event.EndPass):
with gzip.open(
os.path.join(save_dir, "params_pass_%d.tar" %
event.pass_id), "w") as f:
trainer.save_parameter_to_tar(f)
trainer.train(
reader=paddle.batch(
paddle.reader.shuffle(
paddle.dataset.mnist.train(), buf_size=8192),
batch_size=128),
event_handler=event_handler,
num_passes=5)
elif task == "dump_config":
predict = network(is_infer=True)
dump_v2_config(predict, "trainer_config.bin", True)
else:
raise RuntimeError(("Error value for parameter task. "
"Available options are: train and dump_config."))
def _prepare(self):
# prepare reader
self.train_reader = paddle.batch(
reader=self.train_reader.create_reader(),
batch_size=self.args.batch_size)
self.test_reader = paddle.batch(
reader=self.test_reader.create_reader(),
batch_size=self.args.batch_size)
# init paddle
paddle.init(use_gpu=self.args.use_gpu,
trainer_count=self.args.trainer_count)
# create optimizer
optimizer = paddle.optimizer.RMSProp(
learning_rate=self.args.learning_rate,
regularization=opt.L2Regularization(rate=self.args.l2))
# create parameters and trainer
model_out = self.model()
if self.args.init_from:
self.parameters = paddle.parameters.Parameters.from_tar(
gzip.open(self.args.init_from, 'r'))
else:
self.parameters = paddle.parameters.create(model_out)
if self.args.pre_emb.strip() != '':
embeddings = np.loadtxt(self.args.pre_emb,
dtype=float)[:self.args.vocab_size]
self.parameters.set(self.model.name + '.embs', embeddings)
self.logger.info('init emb from {} to {}'.format(
self.args.pre_emb,
self.model.name + '.embs'))
self.trainer = paddle.trainer.SGD(cost=model_out,
parameters=self.parameters,
update_equation=optimizer)
def test_demo():
# PaddlePaddle init
paddle.init(use_gpu=True, gpu_id=FLAGS.gpu_id)
params = sun3d.set_params()
inputs = d_net.get_demon_inputs(params)
# Add neural network config
outputs_bs = d_net.bootstrap_net(inputs, params)
outputs_it = d_net.iterative_net(inputs, params)
outputs_re = d_net.refine_net(inputs, params)
out_fields = ['flow', 'depth_inv', 'normal', 'rotation', 'translation']
my_g_layer_map = {}
parameters_bs, topo_bs = paddle.parameters.create(
[outputs_bs[x] for x in out_fields])
my_g_layer_map.update(cp.g_layer_map)
parameters_it, topo_it = paddle.parameters.create(
[outputs_it[x] for x in out_fields])
my_g_layer_map.update(cp.g_layer_map)
parameters_re, topo_re = paddle.parameters.create(outputs_re['depth_0'])
my_g_layer_map.update(cp.g_layer_map)
print('load parameters')
with gzip.open(FLAGS.model, 'r') as f:
parameters_init = paddle.parameters.Parameters.from_tar(f)
for name in parameters_bs.names():
parameters_bs.set(name, parameters_init.get(name))
for name in parameters_it.names():
parameters_it.set(name, parameters_init.get(name))
for name in parameters_re.names():
parameters_re.set(name, parameters_init.get(name))
# Read image pair 1, 2 flow
for scene_name in params['train_scene'][1:]:
image_list = preprocess_util.list_files(params['flow_path'] +
scene_name + '/flow/')
image2depth = sun3d.get_image_depth_matching(scene_name)
for pair_name in image_list[0:2]:
image1, image2, flow_gt, depth1_gt, normal1_gt = \
sun3d.load_image_pair(scene_name, pair_name, image2depth)
#transform and yield
image1_new = uts.transform(image1.copy(),
height=params['size'][0],
width=params['size'][1])
image2_new = uts.transform(image2.copy(),
height=params['size'][0],
width=params['size'][1])
intrinsic = np.array([0.89115971, 1.18821287, 0.5, 0.5])
test_data_bs = [(image1_new, image2_new)]
feeding_bs = {'image1': 0, 'image2': 1}
flow, depth_inv, normal, rotation, translation = paddle.infer(
output=topo_bs,
parameters=parameters_bs,
input=test_data_bs,
feeding=feeding_bs)
for i in range(3):
test_data_it = [(image1_new, image2_new, intrinsic, rotation,
translation, depth_inv, normal)]
feeding_it = {
'image1': 0,
'image2': 1,
'intrinsic': 2,
'rotation': 3,
'translation': 4,
'depth_inv': 5,
'normal': 6
}
flow, depth_inv, normal, rotation, translation = paddle.infer(
output=topo_it,
parameters=parameters_it,
input=test_data_it,
feeding=feeding_it)
test_data_re = [(image1_new, image2_new, depth_inv)]
feeding_re = {'image1': 0, 'image2': 1, 'depth_inv': 2}
depth = paddle.infer(output=topo_re,
parameters=parameters_re,
input=test_data_re,
feeding=feeding_re)
layer_names = [
outputs_it['flow'].name, outputs_it['normal'].name,
outputs_re['depth_0'].name
]
height_list = [my_g_layer_map[x].height for x in layer_names]
width_list = [my_g_layer_map[x].width for x in layer_names]
flow, normal, depth = vec2img(inputs=[flow, normal, depth],
height=height_list,
width=width_list)
# visualize depth in 3D
# image1_down = cv2.resize(image1,
# (depth.shape[1], depth.shape[0]))
# visualize_prediction(
# depth=depth,
# image=np.uint8(image1_down.transpose([2, 0, 1])),
# rotation=rotation,
# translation=translation)
with open('./test/depth_gt.npy', 'wb') as f:
np.save(f, depth1_gt)
with open('./test/depth_res.npy', 'wb') as f:
np.save(f, depth)
uts.plot_images(OrderedDict([
('image1', image1), ('image2', image2), ('flow', flow),
('flow_gt', flow_gt), ('depth', depth),
('depth_gt', depth1_gt), ('normal', (normal + 1.0) / 2.),
('normal_gt', (normal1_gt + 1.0) / 2)
]),
layout=[4, 2])
def main():
datadim = 3 * 32 * 32
classdim = 10
# PaddlePaddle init
paddle.init(use_gpu=False, trainer_count=1)
image = paddle.layer.data(
name="image", type=paddle.data_type.dense_vector(datadim))
# Add neural network config
# option 1. resnet
# net = resnet_cifar10(image, depth=32)
# option 2. vgg
net = vgg_bn_drop(image)
out = paddle.layer.fc(input=net,
size=classdim,
act=paddle.activation.Softmax())
lbl = paddle.layer.data(
name="label", type=paddle.data_type.integer_value(classdim))
cost = paddle.layer.classification_cost(input=out, label=lbl)
# Create parameters
parameters = paddle.parameters.create(cost)
# Create optimizer
momentum_optimizer = paddle.optimizer.Momentum(
momentum=0.9,
regularization=paddle.optimizer.L2Regularization(rate=0.0002 * 128),
learning_rate=0.1 / 128.0,
learning_rate_decay_a=0.1,
learning_rate_decay_b=50000 * 100,
learning_rate_schedule='discexp',
batch_size=128)
# End batch and end pass event handler
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 100 == 0:
print "\nPass %d, Batch %d, Cost %f, %s" % (
event.pass_id, event.batch_id, event.cost, event.metrics)
else:
sys.stdout.write('.')
sys.stdout.flush()
if isinstance(event, paddle.event.EndPass):
result = trainer.test(
reader=paddle.batch(
paddle.dataset.cifar.test10(), batch_size=128),
feeding={'image': 0,
'label': 1})
print "\nTest with Pass %d, %s" % (event.pass_id, result.metrics)
# Create trainer
trainer = paddle.trainer.SGD(cost=cost,
parameters=parameters,
update_equation=momentum_optimizer)
trainer.train(
reader=paddle.batch(
paddle.reader.shuffle(
paddle.dataset.cifar.train10(), buf_size=50000),
batch_size=128),
num_passes=5,
event_handler=event_handler,
feeding={'image': 0,
'label': 1})
seq = []
prob = beam_result[0]
for i in xrange(gen_num):
print "\n*******************************************************\n"
print "src:", ' '.join([src_dict.get(w) for w in gen_data[i][0]]), "\n"
for j in xrange(beam_size):
print "prob = %f:" % (prob[i][j]), seq_list[i * beam_size + j]
if __name__ == '__main__':
args = parse_args()
dict_size = 30000
paddle.init(use_gpu=args.use_gpu, trainer_count=args.trainer_count)
# use the first 3 samples for generation
gen_creator = paddle.dataset.wmt14.gen(dict_size)
gen_data = []
gen_num = 3
for item in gen_creator():
gen_data.append((item[0], ))
if len(gen_data) == gen_num:
break
generate(gen_data,
dict_size=dict_size,
model_path=args.model_path,
beam_size=args.beam_size)
lstm_last = paddle.layer.pooling(input=inputs[1],
pooling_type=paddle.pooling.Max())
output = paddle.layer.fc(input=[fc_last, lstm_last],
size=class_dim,
act=paddle.activation.Softmax(),
bias_attr=bias_attr,
param_attr=para_attr)
lbl = paddle.layer.data("label", paddle.data_type.integer_value(2))
cost = paddle.layer.classification_cost(input=output, label=lbl)
return cost
if __name__ == '__main__':
# init
paddle.init(use_gpu=False)
#data
print 'load dictionary...'
word_dict = paddle.dataset.imdb.word_dict()
dict_dim = len(word_dict)
class_dim = 2
train_reader = paddle.batch(paddle.reader.shuffle(
lambda: paddle.dataset.imdb.train(word_dict), buf_size=1000),
batch_size=100)
test_reader = paddle.batch(lambda: paddle.dataset.imdb.test(word_dict),
batch_size=100)
feeding = {'word': 0, 'label': 1}
# network config
def main():
# 初始化定义跑模型的设备
paddle.init(use_gpu=with_gpu, trainer_count=1)
# 读取数据
images = paddle.layer.data(
name='pixel', type=paddle.data_type.dense_vector(784))
label = paddle.layer.data(
name='label', type=paddle.data_type.integer_value(10))
# 调用之前定义的网络结构
predict = convolutional_neural_network_org(images)#原网络结构
# predict = convolutional_neural_network(images)
# 定义损失函数
cost = paddle.layer.classification_cost(input=predict, label=label)
# 指定训练相关的参数
parameters = paddle.parameters.create(cost)
# 定义训练方法
optimizer = paddle.optimizer.Momentum(
learning_rate=0.1 / 128.0,
momentum=0.9,
regularization=paddle.optimizer.L2Regularization(rate=0.0005 * 128))
# 训练模型
trainer = paddle.trainer.SGD(
cost=cost, parameters=parameters, update_equation=optimizer)
lists = []
# 定义event_handler，输出训练过程中的结果
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 100 == 0:
print "Pass %d, Batch %d, Cost %f, %s" % (
event.pass_id, event.batch_id, event.cost, event.metrics)
if isinstance(event, paddle.event.EndPass):
# 保存参数
with open('params_pass_%d.tar' % event.pass_id, 'w') as f:
parameters.to_tar(f)
result = trainer.test(reader=paddle.batch(
paddle.dataset.mnist.test(), batch_size=128))
print "Test with Pass %d, Cost %f, %s\n" % (
event.pass_id, result.cost, result.metrics)
lists.append((event.pass_id, result.cost,
result.metrics['classification_error_evaluator']))
trainer.train(
reader=paddle.batch(
paddle.reader.shuffle(paddle.dataset.mnist.train(), buf_size=8192),
batch_size=64),
event_handler=event_handler,
num_passes=50)
# 找到训练误差最小的一次结果
best = sorted(lists, key=lambda list: float(list[1]))[0]
print 'Best pass is %s, testing Avgcost is %s' % (best[0], best[1])
print 'The classification accuracy is %.2f%%' % (100 - float(best[2]) * 100)
# 加载数据
def load_image(file):
im = Image.open(file).convert('L')
im = im.resize((28, 28), Image.ANTIALIAS)
im = np.array(im).astype(np.float32).flatten()
im = im / 255.0
return im
# 测试结果
test_data = []
cur_dir = os.path.dirname(os.path.realpath(__file__))
test_data.append((load_image(cur_dir + '/image/infer_3.png'), ))
probs = paddle.infer(
output_layer=predict, parameters=parameters, input=test_data)
lab = np.argsort(-probs) # probs and lab are the results of one batch data
print "Label of image/infer_3.png is: %d" % lab[0][0]
def main(train_data_file,
test_data_file,
vocab_file,
target_file,
emb_file,
model_save_dir,
num_passes=100,
batch_size=64):
if not os.path.exists(model_save_dir):
os.mkdir(model_save_dir)
word_dict = load_dict(vocab_file)
label_dict = load_dict(target_file)
word_vector_values = get_embedding(emb_file)
word_dict_len = len(word_dict)
label_dict_len = len(label_dict)
paddle.init(use_gpu=False, trainer_count=1)
# define network topology
crf_cost, crf_dec, target = ner_net(word_dict_len, label_dict_len)
evaluator.sum(name="error", input=crf_dec)
evaluator.chunk(name="ner_chunk",
input=crf_dec,
label=target,
chunk_scheme="IOB",
num_chunk_types=(label_dict_len - 1) / 2)
# create parameters
parameters = paddle.parameters.create(crf_cost)
parameters.set("emb", word_vector_values)
# create optimizer
optimizer = paddle.optimizer.Momentum(
momentum=0,
learning_rate=2e-4,
regularization=paddle.optimizer.L2Regularization(rate=8e-4),
gradient_clipping_threshold=25,
model_average=paddle.optimizer.ModelAverage(average_window=0.5,
max_average_window=10000),
)
trainer = paddle.trainer.SGD(cost=crf_cost,
parameters=parameters,
update_equation=optimizer,
extra_layers=crf_dec)
train_reader = paddle.batch(paddle.reader.shuffle(reader.data_reader(
train_data_file, word_dict, label_dict),
buf_size=1000),
batch_size=batch_size)
test_reader = paddle.batch(paddle.reader.shuffle(reader.data_reader(
test_data_file, word_dict, label_dict),
buf_size=1000),
batch_size=batch_size)
feeding = {"word": 0, "mark": 1, "target": 2}
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 5 == 0:
logger.info(
"Pass %d, Batch %d, Cost %f, %s" %
(event.pass_id, event.batch_id, event.cost, event.metrics))
if event.batch_id % 50 == 0:
result = trainer.test(reader=test_reader, feeding=feeding)
logger.info("\nTest with Pass %d, Batch %d, %s" %
(event.pass_id, event.batch_id, result.metrics))
if isinstance(event, paddle.event.EndPass):
# save parameters
with gzip.open(
os.path.join(model_save_dir,
"params_pass_%d.tar.gz" % event.pass_id),
"w") as f:
trainer.save_parameter_to_tar(f)
result = trainer.test(reader=test_reader, feeding=feeding)
logger.info("\nTest with Pass %d, %s" %
(event.pass_id, result.metrics))
trainer.train(reader=train_reader,
event_handler=event_handler,
num_passes=num_passes,
feeding=feeding)
def main():
paddle.init(use_gpu=False, trainer_count=1)
# define network topology
images = paddle.layer.data(
name='pixel', type=paddle.data_type.dense_vector(784))
label = paddle.layer.data(
name='label', type=paddle.data_type.integer_value(10))
# Here we can build the prediction network in different ways. Please
# choose one by uncomment corresponding line.
predict = softmax_regression(images)
#predict = multilayer_perceptron(images)
#predict = convolutional_neural_network(images)
cost = paddle.layer.classification_cost(input=predict, label=label)
parameters = paddle.parameters.create(cost)
optimizer = paddle.optimizer.Momentum(
learning_rate=0.1 / 128.0,
momentum=0.9,
regularization=paddle.optimizer.L2Regularization(rate=0.0005 * 128))
trainer = paddle.trainer.SGD(cost=cost,
parameters=parameters,
update_equation=optimizer,
is_local=False,
pserver_spec="localhost:3000")
lists = []
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 1000 == 0:
print "Pass %d, Batch %d, Cost %f, %s" % (
event.pass_id, event.batch_id, event.cost, event.metrics)
elif isinstance(event, paddle.event.EndPass):
result = trainer.test(reader=paddle.batch(
paddle.dataset.mnist.test(), batch_size=128))
print "Test with Pass %d, Cost %f, %s\n" % (
event.pass_id, result.cost, result.metrics)
lists.append((event.pass_id, result.cost,
result.metrics['classification_error_evaluator']))
trainer.train(
reader=paddle.batch(
paddle.reader.shuffle(
paddle.dataset.mnist.train(), buf_size=8192),
batch_size=128),
event_handler=event_handler,
num_passes=100)
# find the best pass
best = sorted(lists, key=lambda list: float(list[1]))[0]
print 'Best pass is %s, testing Avgcost is %s' % (best[0], best[1])
print 'The classification accuracy is %.2f%%' % (100 - float(best[2]) * 100)
test_creator = paddle.dataset.mnist.test()
test_data = []
for item in test_creator():
test_data.append((item[0], ))
if len(test_data) == 100:
break
# output is a softmax layer. It returns probabilities.
# Shape should be (100, 10)
probs = paddle.infer(
output_layer=predict, parameters=parameters, input=test_data)
print probs.shape
def main():
# get arguments from env
# for local training
TRUTH = ["true", "True", "TRUE", "1", "yes", "Yes", "YES"]
cluster_train = os.getenv('PADDLE_CLUSTER_TRAIN', "False") in TRUTH
use_gpu = os.getenv('PADDLE_INIT_USE_GPU', "False")
if not cluster_train:
paddle.init(
use_gpu=use_gpu,
trainer_count=int(os.getenv("PADDLE_INIT_TRAINER_COUNT", "1")))
else:
paddle.init(
use_gpu=use_gpu,
trainer_count=int(os.getenv("PADDLE_INIT_TRAINER_COUNT", "1")),
port=int(os.getenv("PADDLE_INIT_PORT", "7164")),
ports_num=int(os.getenv("PADDLE_INIT_PORTS_NUM", "1")),
ports_num_for_sparse=int(
os.getenv("PADDLE_INIT_PORTS_NUM_FOR_SPARSE", "1")),
num_gradient_servers=int(
os.getenv("PADDLE_INIT_NUM_GRADIENT_SERVERS", "1")),
trainer_id=int(os.getenv("PADDLE_INIT_TRAINER_ID", "0")),
pservers=os.getenv("PADDLE_INIT_PSERVERS", "127.0.0.1"))
fn = open("thirdparty/wuyi_train_thdpty/word_dict.pickle", "r")
word_dict = pickle.load(fn)
fn.close()
dict_size = len(word_dict)
firstword = paddle.layer.data(
name="firstw", type=paddle.data_type.integer_value(dict_size))
secondword = paddle.layer.data(
name="secondw", type=paddle.data_type.integer_value(dict_size))
thirdword = paddle.layer.data(
name="thirdw", type=paddle.data_type.integer_value(dict_size))
fourthword = paddle.layer.data(
name="fourthw", type=paddle.data_type.integer_value(dict_size))
nextword = paddle.layer.data(
name="fifthw", type=paddle.data_type.integer_value(dict_size))
Efirst = wordemb(firstword)
Esecond = wordemb(secondword)
Ethird = wordemb(thirdword)
Efourth = wordemb(fourthword)
contextemb = paddle.layer.concat(input=[Efirst, Esecond, Ethird, Efourth])
hidden1 = paddle.layer.fc(input=contextemb,
size=hiddensize,
act=paddle.activation.Sigmoid(),
layer_attr=paddle.attr.Extra(drop_rate=0.5),
bias_attr=paddle.attr.Param(learning_rate=2),
param_attr=paddle.attr.Param(
initial_std=1. / math.sqrt(embsize * 8),
learning_rate=1))
predictword = paddle.layer.fc(input=hidden1,
size=dict_size,
bias_attr=paddle.attr.Param(learning_rate=2),
act=paddle.activation.Softmax())
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 100 == 0:
result = trainer.test(
paddle.batch(
cluster_reader_cluster(cluster_test_file, node_id), 32))
print "Pass %d, Batch %d, Cost %f, %s, Testing metrics %s" % (
event.pass_id, event.batch_id, event.cost, event.metrics,
result.metrics)
cost = paddle.layer.classification_cost(input=predictword, label=nextword)
parameters = paddle.parameters.create(cost)
adagrad = paddle.optimizer.AdaGrad(
learning_rate=3e-3,
regularization=paddle.optimizer.L2Regularization(8e-4))
trainer = paddle.trainer.SGD(cost,
parameters,
adagrad,
is_local=not cluster_train)
trainer.train(
paddle.batch(cluster_reader_cluster(cluster_train_file, node_id), 32),
num_passes=30,
event_handler=event_handler)
def main():
datadim = 3 * 32 * 32
classdim = 10
# PaddlePaddle init
paddle.init(use_gpu=with_gpu, trainer_count=7)
image = paddle.layer.data(
name="image", type=paddle.data_type.dense_vector(datadim))
# Add neural network config
# option 1. resnet
# net = resnet_cifar10(image, depth=32)
# option 2. vgg
net = simple_cnn(image)
out = paddle.layer.fc(
input=net, size=classdim, act=paddle.activation.Softmax())
lbl = paddle.layer.data(
name="label", type=paddle.data_type.integer_value(classdim))
cost = paddle.layer.classification_cost(input=out, label=lbl)
# Create parameters
parameters = paddle.parameters.create(cost)
# Create optimizer
momentum_optimizer = paddle.optimizer.Momentum(
momentum=0.9,
regularization=paddle.optimizer.L2Regularization(rate=0.0002 * 128),
learning_rate=0.1 / 128.0,
learning_rate_decay_a=0.1,
learning_rate_decay_b=50000 * 100,
learning_rate_schedule='discexp')
# End batch and end pass event handler
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 100 == 0:
print "\nPass %d, Batch %d, Cost %f, %s" % (
event.pass_id, event.batch_id, event.cost, event.metrics)
else:
sys.stdout.write('.')
sys.stdout.flush()
if isinstance(event, paddle.event.EndPass):
# save parameters
with open('params_pass_%d.tar' % event.pass_id, 'w') as f:
parameters.to_tar(f)
result = trainer.test(
reader=paddle.batch(
paddle.dataset.cifar.test10(), batch_size=128),
feeding={'image': 0,
'label': 1})
print "\nTest with Pass %d, %s" % (event.pass_id, result.metrics)
# Create trainer
trainer = paddle.trainer.SGD(
cost=cost, parameters=parameters, update_equation=momentum_optimizer)
# Save the inference topology to protobuf.
inference_topology = paddle.topology.Topology(layers=out)
with open("inference_topology.pkl", 'wb') as f:
inference_topology.serialize_for_inference(f)
trainer.train(
reader=paddle.batch(
paddle.reader.shuffle(
paddle.dataset.cifar.train10(), buf_size=50000),
batch_size=128),
num_passes=200,
event_handler=event_handler,
feeding={'image': 0,
'label': 1})
# inference
from PIL import Image
import numpy as np
import os
def load_image(file):
im = Image.open(file)
im = im.resize((32, 32), Image.ANTIALIAS)
im = np.array(im).astype(np.float32)
# The storage order of the loaded image is W(widht),
# H(height), C(channel). PaddlePaddle requires
# the CHW order, so transpose them.
im = im.transpose((2, 0, 1)) # CHW
# In the training phase, the channel order of CIFAR
# image is B(Blue), G(green), R(Red). But PIL open
# image in RGB mode. It must swap the channel order.
im = im[(2, 1, 0), :, :] # BGR
im = im.flatten()
im = im / 255.0
return im
test_data = []
cur_dir = os.path.dirname(os.path.realpath(__file__))
test_data.append((load_image(cur_dir + '/image/dog.png'), ))
# users can remove the comments and change the model name
# with open('params_pass_50.tar', 'r') as f:
# parameters = paddle.parameters.Parameters.from_tar(f)
probs = paddle.infer(
output_layer=out, parameters=parameters, input=test_data)
lab = np.argsort(-probs) # probs and lab are the results of one batch data
print "Label of image/dog.png is: %d" % lab[0][0]
def train(train_file_list_path, test_file_list_path, label_dict_path,
model_save_dir):
# 获取训练列表
train_file_list = get_file_list(train_file_list_path)
# 获取测试列表
test_file_list = get_file_list(test_file_list_path)
# 使用训练数据生成标记字典
if not os.path.exists(label_dict_path):
print(("Label dictionary is not given, the dictionary "
"is automatically built from the training data."))
build_label_dict(train_file_list, label_dict_path)
# 获取标签字典
char_dict = load_dict(label_dict_path)
# 获取字典大小
dict_size = len(char_dict)
# 定义网络拓扑
model = Model(dict_size, IMAGE_SHAPE, is_infer=False)
# 初始化PaddlePaddle
paddle.init(use_gpu=True, trainer_count=1)
# 创建优化方法
optimizer = paddle.optimizer.Momentum(momentum=0)
# 创建训练参数
params = paddle.parameters.create(model.cost)
# 定义训练器
trainer = paddle.trainer.SGD(cost=model.cost,
parameters=params,
update_equation=optimizer,
extra_layers=model.eval)
# 获取reader
my_reader = Reader(char_dict=char_dict, image_shape=IMAGE_SHAPE)
# 说明数据层之间的关系
feeding = {'image': 0, 'label': 1}
# 训练事件
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 100 == 0:
print("Pass %d, batch %d, Samples %d, Cost %f, Eval %s" %
(event.pass_id, event.batch_id,
event.batch_id * BATCH_SIZE, event.cost, event.metrics))
if isinstance(event, paddle.event.EndPass):
# 这里由于训练和测试数据共享相同的格式
# 我们仍然使用reader.train_reader来读取测试数据
test_reader = paddle.batch(my_reader.train_reader(test_file_list),
batch_size=BATCH_SIZE)
result = trainer.test(reader=test_reader, feeding=feeding)
print("Test %d, Cost %f, Eval %s" %
(event.pass_id, result.cost, result.metrics))
# 检查保存model的路径是否存在，如果不存在就创建
if not os.path.exists(model_save_dir):
os.mkdir(model_save_dir)
with gzip.open(os.path.join(model_save_dir, "params_pass.tar.gz"),
"w") as f:
trainer.save_parameter_to_tar(f)
# 获取训练数据的reader
train_reader = paddle.batch(paddle.reader.shuffle(
my_reader.train_reader(train_file_list), buf_size=1000),
batch_size=BATCH_SIZE)
# 开始训练
trainer.train(reader=train_reader,
feeding=feeding,
event_handler=event_handler,
num_passes=5000)
def train():
paddle.init(use_gpu=False, trainer_count=1)
# define network topology
feature_out = db_lstm()
target = paddle.layer.data(name='target', type=d_type(label_dict_len))
crf_cost = paddle.layer.crf(size=label_dict_len,
input=feature_out,
label=target,
param_attr=paddle.attr.Param(
name='crfw',
initial_std=default_std,
learning_rate=mix_hidden_lr))
crf_dec = paddle.layer.crf_decoding(
size=label_dict_len,
input=feature_out,
label=target,
param_attr=paddle.attr.Param(name='crfw'))
evaluator.sum(input=crf_dec)
# create parameters
parameters = paddle.parameters.create(crf_cost)
parameters.set('emb', load_parameter(conll05.get_embedding(), 44068, 32))
# create optimizer
optimizer = paddle.optimizer.Momentum(
momentum=0,
learning_rate=2e-2,
regularization=paddle.optimizer.L2Regularization(rate=8e-4),
model_average=paddle.optimizer.ModelAverage(average_window=0.5,
max_average_window=10000),
)
trainer = paddle.trainer.SGD(cost=crf_cost,
parameters=parameters,
update_equation=optimizer,
extra_layers=crf_dec)
reader = paddle.batch(paddle.reader.shuffle(conll05.test(), buf_size=8192),
batch_size=10)
feeding = {
'word_data': 0,
'ctx_n2_data': 1,
'ctx_n1_data': 2,
'ctx_0_data': 3,
'ctx_p1_data': 4,
'ctx_p2_data': 5,
'verb_data': 6,
'mark_data': 7,
'target': 8
}
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 100 == 0:
logger.info(
"Pass %d, Batch %d, Cost %f, %s" %
(event.pass_id, event.batch_id, event.cost, event.metrics))
if event.batch_id and event.batch_id % 1000 == 0:
result = trainer.test(reader=reader, feeding=feeding)
logger.info("\nTest with Pass %d, Batch %d, %s" %
(event.pass_id, event.batch_id, result.metrics))
if isinstance(event, paddle.event.EndPass):
# save parameters
with gzip.open('params_pass_%d.tar.gz' % event.pass_id, 'w') as f:
parameters.to_tar(f)
result = trainer.test(reader=reader, feeding=feeding)
logger.info("\nTest with Pass %d, %s" %
(event.pass_id, result.metrics))
trainer.train(reader=reader,
event_handler=event_handler,
num_passes=10,
feeding=feeding)
def cbow_main(cost_config, window_size=5, prefix="./output/cbow_softmax/",
cpu_num=3,
word_dict_limit=20000, emb_size=32,
num_passes=2,
batch_size_per_cpu=2000):
assert word_dict_limit < MAX_WORDS
assert window_size % 2 == 1
paddle.init(use_gpu=False, trainer_count=cpu_num)
words = []
word_limit = word_dict_limit + 2
for i in xrange(window_size):
words.append(paddle.layer.data(name='word_%d' % i,
type=paddle.data_type.integer_value(
word_limit)))
embs = []
for w in words[:window_size / 2] + words[-window_size / 2 + 1:]:
embs.append(
paddle.layer.embedding(input=w, size=emb_size, param_attr=
paddle.attr.Param(name='emb', sparse_update=True)))
with paddle.layer.mixed(size=emb_size) as sum_emb:
for emb in embs:
sum_emb += paddle.layer.identity_projection(input=emb)
label = words[window_size / 2]
cost = cost_config(sum_emb, label, word_limit)
parameters = paddle.parameters.create(cost)
adam_optimizer = paddle.optimizer.RMSProp(
learning_rate=1e-3)
trainer = paddle.trainer.SGD(cost, parameters, adam_optimizer)
counter = [0]
total_cost = [0.0]
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
total_cost[0] += event.cost
counter[0] += 1
sys.stdout.write('.')
if event.batch_id % 100 == 0:
print "Pass %d, Batch %d, AvgCost %f" % (
event.pass_id, event.batch_id, total_cost[0] / counter[0])
if event.batch_id % 1000000 == 0:
with gzip.open(os.path.join(prefix, "model_%d_%d.tar.gz" % (
event.pass_id,
event.batch_id)),
'w') as f:
parameters.to_tar(f)
if isinstance(event, paddle.event.EndPass):
print "Pass %d" % event.pass_id
with gzip.open(os.path.join(prefix, "model_%d.tar.gz" %
event.pass_id), 'w') as f:
parameters.to_tar(f)
trainer.train(
paddle.batch(
paddle.reader.buffered(
reader_creator(window_size=window_size,
word_limit=word_dict_limit,
path="./preprocessed"), 16 * cpu_num * 4000),
batch_size_per_cpu*cpu_num),
num_passes=num_passes,
event_handler=event_handler,
feeding=[w.name for w in words])
def test_demo():
# PaddlePaddle init
paddle.init(use_gpu=True, gpu_id=FLAGS.gpu_id)
params = sun3d.set_params()
inputs = d_net.get_demon_inputs(params)
params['stage'] = 2
# Add neural network config
outputs, out_field = d_net.get_demon_outputs(inputs,
params,
ext_inputs=None)
parameters = paddle.parameters.create(outputs[out_field])
print('load parameters')
with gzip.open(FLAGS.model, 'r') as f:
parameters_init = paddle.parameters.Parameters.from_tar(f)
for name in parameters.names():
parameters.set(name, parameters_init.get(name))
# Read image pair 1, 2 flow
for scene_name in params['train_scene'][1:]:
image_list = preprocess_util.list_files(params['flow_path'] +
scene_name + '/flow/')
image2depth = sun3d.get_image_depth_matching(scene_name)
for pair_name in image_list[0:2]:
image1, image2, flow_gt, depth1_gt, normal1_gt = \
sun3d.load_image_pair(scene_name, pair_name, image2depth)
#transform and yield
image1_new = uts.transform(image1.copy(),
height=params['size'][0],
width=params['size'][1])
image2_new = uts.transform(image2.copy(),
height=params['size'][0],
width=params['size'][1])
intrinsic = np.array([0.89115971, 1.18821287, 0.5, 0.5])
test_data = [(image1_new, image2_new, intrinsic)]
depth_name = 'depth' if params['stage'] < 5 else 'depth_0'
out_fields = [
'flow', depth_name, 'normal', 'rotation', 'translation'
]
output_list = [outputs[x] for x in out_fields]
flow, depth, normal, rotation, translation = paddle.infer(
output_layer=output_list,
parameters=parameters,
input=test_data,
feeding={
'image1': 0,
'image2': 1,
'intrinsic': 2
})
height_list = [cp.g_layer_map[outputs[x].name].height \
for x in ['flow', 'depth','normal']]
width_list = [cp.g_layer_map[outputs[x].name].width \
for x in ['flow', 'depth','normal']]
flow, depth, normal = vec2img(inputs=[flow, depth, normal],
height=height_list,
width=width_list)
# visualize depth in 3D
image1_down = cv2.resize(image1, (depth.shape[1], depth.shape[0]))
visualize_prediction(depth=depth,
image=np.uint8(
image1_down.transpose([2, 0, 1])),
rotation=rotation,
translation=translation)
uts.plot_images(OrderedDict([
('image1', image1), ('image2', image2), ('flow', flow),
('flow_gt', flow_gt), ('depth', depth),
('depth_gt', depth1_gt), ('normal', (normal + 1.0) / 2.),
('normal_gt', (normal1_gt + 1.0) / 2)
]),
layout=[4, 2])
def main():
paddle.init(use_gpu=False, trainer_count=1)
is_generating = False
# source and target dict dim.
dict_size = 30000
source_dict_dim = target_dict_dim = dict_size
# train the network
if not is_generating:
cost = seqToseq_net(source_dict_dim, target_dict_dim)
parameters = paddle.parameters.create(cost)
# define optimize method and trainer
optimizer = paddle.optimizer.Adam(
learning_rate=5e-5,
regularization=paddle.optimizer.L2Regularization(rate=8e-4))
trainer = paddle.trainer.SGD(cost=cost,
parameters=parameters,
update_equation=optimizer)
# define data reader
wmt14_reader = paddle.batch(
paddle.reader.shuffle(
paddle.dataset.wmt14.train(dict_size), buf_size=8192),
batch_size=5)
# define event_handler callback
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 10 == 0:
print "\nPass %d, Batch %d, Cost %f, %s" % (
event.pass_id, event.batch_id, event.cost,
event.metrics)
else:
sys.stdout.write('.')
sys.stdout.flush()
# start to train
trainer.train(
reader=wmt14_reader, event_handler=event_handler, num_passes=2)
# generate a english sequence to french
else:
# use the first 3 samples for generation
gen_creator = paddle.dataset.wmt14.gen(dict_size)
gen_data = []
gen_num = 3
for item in gen_creator():
gen_data.append((item[0], ))
if len(gen_data) == gen_num:
break
beam_gen = seqToseq_net(source_dict_dim, target_dict_dim, is_generating)
# get the pretrained model, whose bleu = 26.92
parameters = paddle.dataset.wmt14.model()
# prob is the prediction probabilities, and id is the prediction word.
beam_result = paddle.infer(
output_layer=beam_gen,
parameters=parameters,
input=gen_data,
field=['prob', 'id'])
# get the dictionary
src_dict, trg_dict = paddle.dataset.wmt14.get_dict(dict_size)
# the delimited element of generated sequences is -1,
# the first element of each generated sequence is the sequence length
seq_list = []
seq = []
for w in beam_result[1]:
if w != -1:
seq.append(w)
else:
seq_list.append(' '.join([trg_dict.get(w) for w in seq[1:]]))
seq = []
prob = beam_result[0]
beam_size = 3
for i in xrange(gen_num):
print "\n*******************************************************\n"
print "src:", ' '.join(
[src_dict.get(w) for w in gen_data[i][0]]), "\n"
for j in xrange(beam_size):
print "prob = %f:" % (prob[i][j]), seq_list[i * beam_size + j]
import paddle.v2 as paddle
# Initialize PaddlePaddle.
paddle.init(use_gpu=False, trainer_count=1)
# Configure the neural network.
x = paddle.layer.data(name='x', type=paddle.data_type.dense_vector(13))
y_predict = paddle.layer.fc(input=x, size=1, act=paddle.activation.Linear())
with open('fit_a_line.tar', 'r') as f:
parameters = paddle.parameters.Parameters.from_tar(f)
# Infer using provided test data.
probs = paddle.infer(
output_layer=y_predict,
parameters=parameters,
input=[item for item in paddle.dataset.uci_housing.test()()])
for i in xrange(len(probs)):
print 'Predicted price: ${:,.2f}'.format(probs[i][0] * 1000)
beam_size = 500
num_proc_bsearch = 1
num_proc_data = 1
alpha = 2.5
beta = 0.3
cutoff_prob = 1.0
cutoff_top_n = 40
decoding_method = 'ctc_beam_search'
error_rate_type = 'wer'
num_conv_layers = 2
num_rnn_layers = 3
rnn_layer_size = 2048
share_rnn_weights = True
specgram_type = 'linear'
paddle.init(use_gpu=USING_GPU, rnn_use_batch=True, trainer_count=trainer_count)
data_generator = DataGenerator(vocab_filepath=vocab_path,
mean_std_filepath=mean_std_path,
augmentation_config='{}',
specgram_type=specgram_type,
num_threads=num_proc_data,
keep_transcription_text=True)
batch_reader = data_generator.batch_reader_creator(manifest_path=test_manifest,
batch_size=batch_size,
min_batch_size=1,
sortagrad=False,
shuffle_method=None)
print('Loading inference model from files {}'.format(model_path))
log_file.write('Loading inference model from files {}'.format(model_path))
def main():
# get arguments from env
# for local training
TRUTH = ["true", "True", "TRUE", "1", "yes", "Yes", "YES"]
cluster_train = os.getenv('PADDLE_CLUSTER_TRAIN', "False") in TRUTH
use_gpu = os.getenv('PADDLE_INIT_USE_GPU', "False")
if not cluster_train:
paddle.init(use_gpu=use_gpu,
trainer_count=int(
os.getenv("PADDLE_INIT_TRAINER_COUNT", "1")))
else:
paddle.init(use_gpu=use_gpu,
trainer_count=int(
os.getenv("PADDLE_INIT_TRAINER_COUNT", "1")),
port=int(os.getenv("PADDLE_INIT_PORT", "7164")),
ports_num=int(os.getenv("PADDLE_INIT_PORTS_NUM", "1")),
ports_num_for_sparse=int(
os.getenv("PADDLE_INIT_PORTS_NUM_FOR_SPARSE", "1")),
num_gradient_servers=int(
os.getenv("PADDLE_INIT_NUM_GRADIENT_SERVERS", "1")),
trainer_id=int(os.getenv("PADDLE_INIT_TRAINER_ID", "0")),
pservers=os.getenv("PADDLE_INIT_PSERVERS", "127.0.0.1"))
fn = open("thirdparty/wuyi_train_thdpty/word_dict.pickle", "r")
word_dict = pickle.load(fn)
fn.close()
dict_size = len(word_dict)
firstword = paddle.layer.data(
name="firstw", type=paddle.data_type.integer_value(dict_size))
secondword = paddle.layer.data(
name="secondw", type=paddle.data_type.integer_value(dict_size))
thirdword = paddle.layer.data(
name="thirdw", type=paddle.data_type.integer_value(dict_size))
fourthword = paddle.layer.data(
name="fourthw", type=paddle.data_type.integer_value(dict_size))
nextword = paddle.layer.data(
name="fifthw", type=paddle.data_type.integer_value(dict_size))
Efirst = wordemb(firstword)
Esecond = wordemb(secondword)
Ethird = wordemb(thirdword)
Efourth = wordemb(fourthword)
contextemb = paddle.layer.concat(input=[Efirst, Esecond, Ethird, Efourth])
hidden1 = paddle.layer.fc(input=contextemb,
size=hiddensize,
act=paddle.activation.Sigmoid(),
layer_attr=paddle.attr.Extra(drop_rate=0.5),
bias_attr=paddle.attr.Param(learning_rate=2),
param_attr=paddle.attr.Param(
initial_std=1. / math.sqrt(embsize * 8),
learning_rate=1))
predictword = paddle.layer.fc(input=hidden1,
size=dict_size,
bias_attr=paddle.attr.Param(learning_rate=2),
act=paddle.activation.Softmax())
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 100 == 0:
result = trainer.test(
paddle.batch(
cluster_reader_cluster(cluster_test_file, node_id),
32))
print "Pass %d, Batch %d, Cost %f, %s, Testing metrics %s" % (
event.pass_id, event.batch_id, event.cost, event.metrics,
result.metrics)
cost = paddle.layer.classification_cost(input=predictword, label=nextword)
parameters = paddle.parameters.create(cost)
adagrad = paddle.optimizer.AdaGrad(
learning_rate=3e-3,
regularization=paddle.optimizer.L2Regularization(8e-4))
trainer = paddle.trainer.SGD(cost,
parameters,
adagrad,
is_local=not cluster_train)
trainer.train(paddle.batch(
cluster_reader_cluster(cluster_train_file, node_id), 32),
num_passes=30,
event_handler=event_handler)
def infer(data_path, model_path, word_dict_path, batch_size, label_dict_path):
def _infer_a_batch(inferer, test_batch, ids_2_word, ids_2_label):
probs = inferer.infer(input=test_batch, field=["value"])
assert len(probs) == len(test_batch)
for word_ids, prob in zip(test_batch, probs):
sent_ids = []
for sent in word_ids[0]:
sent_ids.extend(sent)
word_text = " ".join([ids_2_word[id] for id in sent_ids])
print("%s\t%s\t%s" % (ids_2_label[prob.argmax()],
" ".join(["{:0.4f}".format(p)
for p in prob]), word_text))
assert os.path.exists(model_path), "The trained model does not exist."
logger.info("Begin to predict...")
use_default_data = (data_path is None)
if use_default_data:
word_dict = reader.imdb_word_dict()
word_reverse_dict = dict((value, key)
for key, value in word_dict.iteritems())
# The reversed label dict of the imdb dataset
label_reverse_dict = {0: "positive", 1: "negative"}
test_reader = reader.imdb_test(word_dict)
class_num = 2
else:
assert os.path.exists(
word_dict_path), "The word dictionary file does not exist"
assert os.path.exists(
label_dict_path), "The label dictionary file does not exist"
word_dict = load_dict(word_dict_path)
word_reverse_dict = dict((value, key)
for key, value in word_dict.iteritems())
label_reverse_dict = load_reverse_dict(label_dict_path)
class_num = len(label_reverse_dict)
test_reader = reader.infer_reader(data_path, word_dict)()
dict_dim = len(word_dict)
# initialize PaddlePaddle.
paddle.init(use_gpu=False, trainer_count=1)
prob_layer = nested_net(dict_dim, class_num, is_infer=True)
# load the trained models.
parameters = paddle.parameters.Parameters.from_tar(
gzip.open(model_path, "r"))
inferer = paddle.inference.Inference(
output_layer=prob_layer, parameters=parameters)
test_batch = []
for idx, item in enumerate(test_reader):
test_batch.append([item[0]])
if len(test_batch) == batch_size:
_infer_a_batch(inferer, test_batch, word_reverse_dict,
label_reverse_dict)
test_batch = []
if len(test_batch):
_infer_a_batch(inferer, test_batch, word_reverse_dict,
label_reverse_dict)
test_batch = []
def main():
paddle.init(use_gpu=False)
movie_title_dict = paddle.dataset.movielens.get_movie_title_dict()
uid = paddle.layer.data(
name='user_id',
type=paddle.data_type.integer_value(
paddle.dataset.movielens.max_user_id() + 1))
usr_emb = paddle.layer.embedding(input=uid, size=32)
usr_gender_id = paddle.layer.data(
name='gender_id', type=paddle.data_type.integer_value(2))
usr_gender_emb = paddle.layer.embedding(input=usr_gender_id, size=16)
usr_age_id = paddle.layer.data(
name='age_id',
type=paddle.data_type.integer_value(
len(paddle.dataset.movielens.age_table)))
usr_age_emb = paddle.layer.embedding(input=usr_age_id, size=16)
usr_job_id = paddle.layer.data(
name='job_id',
type=paddle.data_type.integer_value(paddle.dataset.movielens.max_job_id(
) + 1))
usr_job_emb = paddle.layer.embedding(input=usr_job_id, size=16)
usr_combined_features = paddle.layer.fc(
input=[usr_emb, usr_gender_emb, usr_age_emb, usr_job_emb],
size=200,
act=paddle.activation.Tanh())
mov_id = paddle.layer.data(
name='movie_id',
type=paddle.data_type.integer_value(
paddle.dataset.movielens.max_movie_id() + 1))
mov_emb = paddle.layer.embedding(input=mov_id, size=32)
mov_categories = paddle.layer.data(
name='category_id',
type=paddle.data_type.sparse_binary_vector(
len(paddle.dataset.movielens.movie_categories())))
mov_categories_hidden = paddle.layer.fc(input=mov_categories, size=32)
mov_title_id = paddle.layer.data(
name='movie_title',
type=paddle.data_type.integer_value_sequence(len(movie_title_dict)))
mov_title_emb = paddle.layer.embedding(input=mov_title_id, size=32)
mov_title_conv = paddle.networks.sequence_conv_pool(
input=mov_title_emb, hidden_size=32, context_len=3)
mov_combined_features = paddle.layer.fc(
input=[mov_emb, mov_categories_hidden, mov_title_conv],
size=200,
act=paddle.activation.Tanh())
inference = paddle.layer.cos_sim(
a=usr_combined_features, b=mov_combined_features, size=1, scale=5)
cost = paddle.layer.mse_cost(
input=inference,
label=paddle.layer.data(
name='score', type=paddle.data_type.dense_vector(1)))
parameters = paddle.parameters.create(cost)
trainer = paddle.trainer.SGD(cost=cost,
parameters=parameters,
update_equation=paddle.optimizer.Adam(
learning_rate=1e-4))
feeding = {
'user_id': 0,
'gender_id': 1,
'age_id': 2,
'job_id': 3,
'movie_id': 4,
'category_id': 5,
'movie_title': 6,
'score': 7
}
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 100 == 0:
print "Pass %d Batch %d Cost %.2f" % (
event.pass_id, event.batch_id, event.cost)
trainer.train(
reader=paddle.batch(
paddle.reader.shuffle(
paddle.dataset.movielens.train(), buf_size=8192),
batch_size=256),
event_handler=event_handler,
feeding=feeding,
num_passes=1)
user_id = 234
movie_id = 345
user = paddle.dataset.movielens.user_info()[user_id]
movie = paddle.dataset.movielens.movie_info()[movie_id]
feature = user.value() + movie.value()
def reader():
yield feature
infer_dict = copy.copy(feeding)
del infer_dict['score']
prediction = paddle.infer(
output=inference,
parameters=parameters,
reader=paddle.batch(
reader, batch_size=32),
feeding=infer_dict)
print(prediction + 5) / 2
def train():
"""
model train
"""
# init
use_gpu_flag = os.getenv("PADDLE_USE_GPU", "0")
print("use_gpu_flag", use_gpu_flag)
trainer_id_str = os.getenv("PADDLE_TRAINER_ID", "0")
paddle.init(
use_gpu=use_gpu_flag,
trainer_count=int(os.getenv("PADDLE_TRAINER_COUNT", "1")),
port=int(os.getenv("PADDLE_PORT", "7164")),
ports_num=int(os.getenv("PADDLE_PORTS_NUM", "1")),
ports_num_for_sparse=int(os.getenv("PADDLE_PORTS_NUM_FOR_SPARSE",
"1")),
num_gradient_servers=int(os.getenv("PADDLE_NUM_GRADIENT_SERVERS",
"1")),
trainer_id=int(trainer_id_str),
pservers=os.getenv("PADDLE_PSERVERS", "127.0.0.1"))
# network config
x = paddle.layer.data(name='x', type=paddle.data_type.dense_vector(13))
y_predict = paddle.layer.fc(input=x,
size=1,
act=paddle.activation.Linear())
y = paddle.layer.data(name='y', type=paddle.data_type.dense_vector(1))
cost = paddle.layer.square_error_cost(input=y_predict, label=y)
# Save the inference topology to protobuf.
inference_topology = paddle.topology.Topology(layers=y_predict)
with open("./output/inference_topology.pkl", 'wb') as f:
inference_topology.serialize_for_inference(f)
# create parameters
parameters = paddle.parameters.create(cost)
# create optimizer
optimizer = paddle.optimizer.Momentum(momentum=0)
trainer = paddle.trainer.SGD(cost=cost,
parameters=parameters,
update_equation=optimizer,
is_local=False)
feeding = {'x': 0, 'y': 1}
#create reader
train_reader = paddle.batch(paddle.reader.shuffle(
cluster_data_reader(cluster_train_dir), buf_size=500),
batch_size=2)
# event_handler to print training and testing info
def event_handler(event):
"""
handle paddle event
"""
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 100 == 0:
print "Pass %d, Batch %d, Cost %f" % (
event.pass_id, event.batch_id, event.cost)
if isinstance(event, paddle.event.EndPass):
if event.pass_id % 10 == 0:
filename = './output/model/params_pass_%d_%s.tar' % (
event.pass_id, trainer_id_str)
with open(filename, "w") as f:
trainer.save_parameter_to_tar(f)
test_reader = paddle.batch(paddle.reader.shuffle(
cluster_data_reader(cluster_test_dir), buf_size=500),
batch_size=2)
result = trainer.test(reader=test_reader, feeding=feeding)
print "Test %d, Cost %f" % (event.pass_id, result.cost)
# training
trainer.train(reader=train_reader,
feeding=feeding,
event_handler=event_handler,
num_passes=30)
#encoding=utf8 import paddle.v2 as paddle import paddle.v2.dataset.uci_housing as uci_housing # 模型初始化 paddle.init(use_gpu=False, trainer_count=1) # 数据 x = paddle.layer.data(name='x', type=paddle.data_type.dense_vector(13)) y_predict = paddle.layer.fc(input=x, size=1, act=paddle.activation.Linear()) y = paddle.layer.data(name='y', type=paddle.data_type.dense_vector(1)) # cost = paddle.layer.mse_cost(input=y_predict, label=y) cost = paddle.layer.square_error_cost(input=y_predict, label=y) # 参数，优化器，训练器 parameters = paddle.parameters.create(cost) optimizer = paddle.optimizer.Momentum(momentum=0) trainer = paddle.trainer.SGD(cost=cost, parameters=parameters, update_equation=optimizer)
def main():
# parse the argument
parser = argparse.ArgumentParser()
parser.add_argument(
'model',
help='The model for image classification',
choices=['alexnet', 'vgg13', 'vgg16', 'vgg19', 'resnet', 'googlenet'])
args = parser.parse_args()
# PaddlePaddle init
paddle.init(use_gpu=True, trainer_count=7)
image = paddle.layer.data(
name="image", type=paddle.data_type.dense_vector(DATA_DIM))
lbl = paddle.layer.data(
name="label", type=paddle.data_type.integer_value(CLASS_DIM))
extra_layers = None
learning_rate = 0.01
if args.model == 'alexnet':
out = alexnet.alexnet(image, class_dim=CLASS_DIM)
elif args.model == 'vgg13':
out = vgg.vgg13(image, class_dim=CLASS_DIM)
elif args.model == 'vgg16':
out = vgg.vgg16(image, class_dim=CLASS_DIM)
elif args.model == 'vgg19':
out = vgg.vgg19(image, class_dim=CLASS_DIM)
elif args.model == 'resnet':
out = resnet.resnet_imagenet(image, class_dim=CLASS_DIM)
learning_rate = 0.1
elif args.model == 'googlenet':
out, out1, out2 = googlenet.googlenet(image, class_dim=CLASS_DIM)
loss1 = paddle.layer.cross_entropy_cost(
input=out1, label=lbl, coeff=0.3)
paddle.evaluator.classification_error(input=out1, label=lbl)
loss2 = paddle.layer.cross_entropy_cost(
input=out2, label=lbl, coeff=0.3)
paddle.evaluator.classification_error(input=out2, label=lbl)
extra_layers = [loss1, loss2]
cost = paddle.layer.classification_cost(input=out, label=lbl)
# Create parameters
parameters = paddle.parameters.create(cost)
# Create optimizer
optimizer = paddle.optimizer.Momentum(
momentum=0.9,
regularization=paddle.optimizer.L2Regularization(rate=0.0005 *
BATCH_SIZE),
learning_rate=learning_rate / BATCH_SIZE,
learning_rate_decay_a=0.1,
learning_rate_decay_b=128000 * 35,
learning_rate_schedule="discexp", )
train_reader = paddle.batch(
paddle.reader.shuffle(
flowers.train(),
# To use other data, replace the above line with:
# reader.train_reader('train.list'),
buf_size=1000),
batch_size=BATCH_SIZE)
test_reader = paddle.batch(
flowers.valid(),
# To use other data, replace the above line with:
# reader.test_reader('val.list'),
batch_size=BATCH_SIZE)
# Create trainer
trainer = paddle.trainer.SGD(
cost=cost,
parameters=parameters,
update_equation=optimizer,
extra_layers=extra_layers)
# End batch and end pass event handler
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 1 == 0:
print "\nPass %d, Batch %d, Cost %f, %s" % (
event.pass_id, event.batch_id, event.cost, event.metrics)
if isinstance(event, paddle.event.EndPass):
with gzip.open('params_pass_%d.tar.gz' % event.pass_id, 'w') as f:
trainer.save_parameter_to_tar(f)
result = trainer.test(reader=test_reader)
print "\nTest with Pass %d, %s" % (event.pass_id, result.metrics)
trainer.train(
reader=train_reader, num_passes=200, event_handler=event_handler)
lstm_last = paddle.layer.pooling(
input=inputs[1], pooling_type=paddle.pooling.Max())
output = paddle.layer.fc(input=[fc_last, lstm_last],
size=class_dim,
act=paddle.activation.Softmax(),
bias_attr=bias_attr,
param_attr=para_attr)
lbl = paddle.layer.data("label", paddle.data_type.integer_value(2))
cost = paddle.layer.classification_cost(input=output, label=lbl)
return cost
if __name__ == '__main__':
# init
paddle.init(use_gpu=False)
#data
print 'load dictionary...'
word_dict = paddle.dataset.imdb.word_dict()
dict_dim = len(word_dict)
class_dim = 2
train_reader = paddle.batch(
paddle.reader.shuffle(
lambda: paddle.dataset.imdb.train(word_dict), buf_size=1000),
batch_size=100)
test_reader = paddle.batch(
lambda: paddle.dataset.imdb.test(word_dict), batch_size=100)
feeding = {'word': 0, 'label': 1}
def main():
# parse the argument
parser = argparse.ArgumentParser()
parser.add_argument(
'model',
help='The model for image classification',
choices=['alexnet', 'vgg13', 'vgg16', 'vgg19', 'resnet', 'googlenet'])
args = parser.parse_args()
# PaddlePaddle init
paddle.init(use_gpu=True, trainer_count=7)
image = paddle.layer.data(name="image",
type=paddle.data_type.dense_vector(DATA_DIM))
lbl = paddle.layer.data(name="label",
type=paddle.data_type.integer_value(CLASS_DIM))
extra_layers = None
learning_rate = 0.01
if args.model == 'alexnet':
out = alexnet.alexnet(image, class_dim=CLASS_DIM)
elif args.model == 'vgg13':
out = vgg.vgg13(image, class_dim=CLASS_DIM)
elif args.model == 'vgg16':
out = vgg.vgg16(image, class_dim=CLASS_DIM)
elif args.model == 'vgg19':
out = vgg.vgg19(image, class_dim=CLASS_DIM)
elif args.model == 'resnet':
out = resnet.resnet_imagenet(image, class_dim=CLASS_DIM)
learning_rate = 0.1
elif args.model == 'googlenet':
out, out1, out2 = googlenet.googlenet(image, class_dim=CLASS_DIM)
loss1 = paddle.layer.cross_entropy_cost(input=out1,
label=lbl,
coeff=0.3)
paddle.evaluator.classification_error(input=out1, label=lbl)
loss2 = paddle.layer.cross_entropy_cost(input=out2,
label=lbl,
coeff=0.3)
paddle.evaluator.classification_error(input=out2, label=lbl)
extra_layers = [loss1, loss2]
cost = paddle.layer.classification_cost(input=out, label=lbl)
# Create parameters
parameters = paddle.parameters.create(cost)
# Create optimizer
optimizer = paddle.optimizer.Momentum(
momentum=0.9,
regularization=paddle.optimizer.L2Regularization(rate=0.0005 *
BATCH_SIZE),
learning_rate=learning_rate / BATCH_SIZE,
learning_rate_decay_a=0.1,
learning_rate_decay_b=128000 * 35,
learning_rate_schedule="discexp",
)
train_reader = paddle.batch(
paddle.reader.shuffle(
flowers.train(),
# To use other data, replace the above line with:
# reader.train_reader('train.list'),
buf_size=1000),
batch_size=BATCH_SIZE)
test_reader = paddle.batch(
flowers.valid(),
# To use other data, replace the above line with:
# reader.test_reader('val.list'),
batch_size=BATCH_SIZE)
# Create trainer
trainer = paddle.trainer.SGD(cost=cost,
parameters=parameters,
update_equation=optimizer,
extra_layers=extra_layers)
# End batch and end pass event handler
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 1 == 0:
print "\nPass %d, Batch %d, Cost %f, %s" % (
event.pass_id, event.batch_id, event.cost, event.metrics)
if isinstance(event, paddle.event.EndPass):
with gzip.open('params_pass_%d.tar.gz' % event.pass_id, 'w') as f:
trainer.save_parameter_to_tar(f)
result = trainer.test(reader=test_reader)
print "\nTest with Pass %d, %s" % (event.pass_id, result.metrics)
trainer.train(reader=train_reader,
num_passes=200,
event_handler=event_handler)
