def run1(self):
# test distributed training
print('local rank', get_local_rank())
set_rng_seed(100)
data_set = prepare_fake_dataset()
data_set.set_input("x", flag=True)
data_set.set_target("y", flag=True)
model = NaiveClassifier(2, 2)
trainer = DistTrainer(
model=model,
train_data=data_set,
optimizer=SGD(lr=0.1),
loss=CrossEntropyLoss(pred="predict", target="y"),
batch_size_per_gpu=8,
n_epochs=3,
print_every=50,
save_path=self.save_path,
)
trainer.train()
"""
# 应该正确运行
"""
if trainer.is_master and os.path.exists(self.save_path):
shutil.rmtree(self.save_path)
def run4(self):
set_rng_seed(100)
data_set, model = prepare_env()
train_set, dev_set = data_set.split(0.3)
model = NaiveClassifier(2, 1)
trainer = DistTrainer(
train_set,
model,
optimizer=SGD(lr=0.1),
loss=BCELoss(pred="predict", target="y"),
batch_size_per_gpu=32,
n_epochs=3,
print_every=50,
dev_data=dev_set,
metrics=AccuracyMetric(pred="predict", target="y"),
validate_every=-1,
save_path=self.save_path,
)
trainer.train()
"""
# 应该正确运行
"""
if trainer.is_master and os.path.exists(self.save_path):
shutil.rmtree(self.save_path)
def test_case(self):
def prepare_fake_dataset():
mean = np.array([-3, -3])
cov = np.array([[1, 0], [0, 1]])
class_A = np.random.multivariate_normal(mean, cov, size=(1000,))
mean = np.array([3, 3])
cov = np.array([[1, 0], [0, 1]])
class_B = np.random.multivariate_normal(mean, cov, size=(1000,))
data_set = DataSet([Instance(x=[float(item[0]), float(item[1])], y=[0.0]) for item in class_A] +
[Instance(x=[float(item[0]), float(item[1])], y=[1.0]) for item in class_B])
return data_set
data_set = prepare_fake_dataset()
data_set.set_input("x")
data_set.set_target("y")
model = NaiveClassifier(2, 1)
trainer = Trainer(data_set, model,
loss=BCELoss(pred="predict", target="y"),
n_epochs=1,
batch_size=32,
print_every=50,
optimizer=SGD(lr=0.1),
check_code_level=2,
use_tqdm=False,
callbacks=[EchoCallback()])
trainer.train()
def test_save_path(self):
data_set = prepare_fake_dataset()
data_set.set_input("x", flag=True)
data_set.set_target("y", flag=True)
train_set, dev_set = data_set.split(0.3)
model = NaiveClassifier(2, 1)
save_path = 'test_save_models'
trainer = Trainer(train_set,
model,
optimizer=SGD(lr=0.1),
loss=BCELoss(pred="predict", target="y"),
batch_size=32,
n_epochs=10,
print_every=50,
dev_data=dev_set,
metrics=AccuracyMetric(pred="predict", target="y"),
validate_every=-1,
save_path=save_path,
use_tqdm=True,
check_code_level=2)
trainer.train()
def prepare_env():
mean = np.array([-3, -3])
cov = np.array([[1, 0], [0, 1]])
class_A = np.random.multivariate_normal(mean, cov, size=(1000,))
mean = np.array([3, 3])
cov = np.array([[1, 0], [0, 1]])
class_B = np.random.multivariate_normal(mean, cov, size=(1000,))
data_set = DataSet([Instance(x=[float(item[0]), float(item[1])], y=[0.0]) for item in class_A] +
[Instance(x=[float(item[0]), float(item[1])], y=[1.0]) for item in class_B])
data_set.set_input("x")
data_set.set_target("y")
model = NaiveClassifier(2, 1)
return data_set, model