mirror of
https://github.com/wassname/pytorch-lightning.git
synced 2026-09-09 11:32:07 +08:00
added gradient clipping
This commit is contained in:
William Falcon
@@ -1 +0,0 @@
|
||||
from .example_model import ExampleModel
|
||||
@@ -1,74 +0,0 @@
|
||||
import os
|
||||
import sys
|
||||
|
||||
from test_tube import HyperOptArgumentParser, Experiment
|
||||
from pytorch_lightning.models.trainer import Trainer
|
||||
from pytorch_lightning.utils.arg_parse import add_default_args
|
||||
from pytorch_lightning.callbacks.pt_callbacks import EarlyStopping, ModelCheckpoint
|
||||
from docs.source.examples.example_model import ExampleModel
|
||||
|
||||
|
||||
def main(hparams):
|
||||
"""
|
||||
Main training routine specific for this project
|
||||
:param hparams:
|
||||
:return:
|
||||
"""
|
||||
# init experiment
|
||||
exp = Experiment(
|
||||
name=hparams.tt_name,
|
||||
debug=hparams.debug,
|
||||
save_dir=hparams.tt_save_path,
|
||||
version=hparams.hpc_exp_number,
|
||||
autosave=False,
|
||||
description=hparams.tt_description
|
||||
)
|
||||
|
||||
exp.argparse(hparams)
|
||||
exp.save()
|
||||
|
||||
# build model
|
||||
model = ExampleModel(hparams)
|
||||
|
||||
# callbacks
|
||||
early_stop = EarlyStopping(
|
||||
monitor='val_acc',
|
||||
patience=3,
|
||||
mode='min',
|
||||
verbose=True,
|
||||
)
|
||||
|
||||
model_save_path = '{}/{}/{}'.format(hparams.model_save_path, exp.name, exp.version)
|
||||
checkpoint = ModelCheckpoint(
|
||||
filepath=model_save_path,
|
||||
save_function=None,
|
||||
save_best_only=True,
|
||||
verbose=True,
|
||||
monitor='val_acc',
|
||||
mode='min'
|
||||
)
|
||||
|
||||
# configure trainer
|
||||
trainer = Trainer(
|
||||
experiment=exp,
|
||||
checkpoint_callback=checkpoint,
|
||||
early_stop_callback=early_stop,
|
||||
)
|
||||
|
||||
# train model
|
||||
trainer.fit(model)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
|
||||
# use default args given by lightning
|
||||
root_dir = os.path.split(os.path.dirname(sys.modules['__main__'].__file__))[0]
|
||||
parent_parser = HyperOptArgumentParser(strategy='random_search', add_help=False)
|
||||
add_default_args(parent_parser, root_dir)
|
||||
|
||||
# allow model to overwrite or extend args
|
||||
parser = ExampleModel.add_model_specific_args(parent_parser)
|
||||
hyperparams = parser.parse_args()
|
||||
|
||||
# train model
|
||||
main(hyperparams)
|
||||
@@ -1,211 +0,0 @@
|
||||
import torch.nn as nn
|
||||
import numpy as np
|
||||
from pytorch_lightning.root_module.root_module import LightningModule
|
||||
from test_tube import HyperOptArgumentParser
|
||||
from torchvision.datasets import MNIST
|
||||
import torchvision.transforms as transforms
|
||||
import torch
|
||||
import torch.nn.functional as F
|
||||
import os, pdb
|
||||
from collections import OrderedDict
|
||||
|
||||
|
||||
class ExampleModel(LightningModule):
|
||||
"""
|
||||
Sample model to show how to define a template
|
||||
"""
|
||||
|
||||
def __init__(self, hparams):
|
||||
# init superclass
|
||||
super(ExampleModel, self).__init__(hparams)
|
||||
|
||||
self.batch_size = hparams.batch_size
|
||||
|
||||
# build model
|
||||
self.__build_model()
|
||||
|
||||
# ---------------------
|
||||
# MODEL SETUP
|
||||
# ---------------------
|
||||
def __build_model(self):
|
||||
"""
|
||||
Layout model
|
||||
:return:
|
||||
"""
|
||||
self.c_d1 = nn.Linear(in_features=self.hparams.in_features, out_features=self.hparams.hidden_dim)
|
||||
self.c_d1_bn = nn.BatchNorm1d(self.hparams.hidden_dim)
|
||||
self.c_d1_drop = nn.Dropout(self.hparams.drop_prob)
|
||||
|
||||
self.c_d2 = nn.Linear(in_features=self.hparams.hidden_dim, out_features=self.hparams.out_features)
|
||||
|
||||
# ---------------------
|
||||
# TRAINING
|
||||
# ---------------------
|
||||
def forward(self, x):
|
||||
|
||||
x = self.c_d1(x)
|
||||
x = torch.tanh(x)
|
||||
x = self.c_d1_bn(x)
|
||||
x = self.c_d1_drop(x)
|
||||
|
||||
x = self.c_d2(x)
|
||||
logits = F.log_softmax(x, dim=1)
|
||||
|
||||
return logits
|
||||
|
||||
def loss(self, labels, logits):
|
||||
nll = F.nll_loss(logits, labels)
|
||||
return nll
|
||||
|
||||
def training_step(self, data_batch, batch_i):
|
||||
"""
|
||||
Called inside the training loop
|
||||
:param data_batch:
|
||||
:return:
|
||||
"""
|
||||
# forward pass
|
||||
x, y = data_batch
|
||||
x = x.view(x.size(0), -1)
|
||||
y_hat = self.forward(x)
|
||||
|
||||
# calculate loss
|
||||
loss_val = self.loss(y, y_hat)
|
||||
|
||||
output = OrderedDict({
|
||||
'loss': loss_val,
|
||||
'tqdm_metrics': {}
|
||||
})
|
||||
return output
|
||||
|
||||
def validation_step(self, data_batch, batch_i):
|
||||
"""
|
||||
Called inside the validation loop
|
||||
:param data_batch:
|
||||
:return:
|
||||
"""
|
||||
x, y = data_batch
|
||||
x = x.view(x.size(0), -1)
|
||||
y_hat = self.forward(x)
|
||||
|
||||
loss_val = self.loss(y, y_hat)
|
||||
|
||||
# acc
|
||||
labels_hat = torch.argmax(y_hat, dim=1)
|
||||
val_acc = torch.sum(y == labels_hat).item() / (len(y) * 1.0)
|
||||
|
||||
output = OrderedDict({
|
||||
'val_loss': loss_val,
|
||||
'val_acc': torch.tensor(val_acc),
|
||||
})
|
||||
return output
|
||||
|
||||
|
||||
def validation_end(self, outputs):
|
||||
"""
|
||||
Called at the end of validation to aggregate outputs
|
||||
:param outputs: list of individual outputs of each validation step
|
||||
:return:
|
||||
"""
|
||||
val_loss_mean = 0
|
||||
val_acc_mean = 0
|
||||
for output in outputs:
|
||||
val_loss_mean += output['val_loss']
|
||||
val_acc_mean += output['val_acc']
|
||||
|
||||
val_loss_mean /= len(outputs)
|
||||
val_acc_mean /= len(outputs)
|
||||
tqdm_dic = {'val_loss': val_loss_mean.item(), 'val_acc': val_acc_mean.item()}
|
||||
return tqdm_dic
|
||||
|
||||
def update_tng_log_metrics(self, logs):
|
||||
return logs
|
||||
|
||||
# ---------------------
|
||||
# MODEL SAVING
|
||||
# ---------------------
|
||||
def get_save_dict(self):
|
||||
checkpoint = {'state_dict': self.state_dict()}
|
||||
return checkpoint
|
||||
|
||||
def load_model_specific(self, checkpoint):
|
||||
self.load_state_dict(checkpoint['state_dict'])
|
||||
pass
|
||||
|
||||
# ---------------------
|
||||
# TRAINING SETUP
|
||||
# ---------------------
|
||||
def configure_optimizers(self):
|
||||
"""
|
||||
return whatever optimizers we want here
|
||||
:return: list of optimizers
|
||||
"""
|
||||
optimizer = self.choose_optimizer(self.hparams.optimizer_name, self.parameters(), {'lr': self.hparams.learning_rate}, 'optimizer')
|
||||
self.optimizers = [optimizer]
|
||||
return self.optimizers
|
||||
|
||||
def __dataloader(self, train):
|
||||
# init data generators
|
||||
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (1.0,))])
|
||||
|
||||
dataset = MNIST(root=self.hparams.data_root, train=train, transform=transform, download=True)
|
||||
|
||||
loader = torch.utils.data.DataLoader(
|
||||
dataset=dataset,
|
||||
batch_size=self.hparams.batch_size,
|
||||
shuffle=True
|
||||
)
|
||||
|
||||
return loader
|
||||
|
||||
@property
|
||||
def tng_dataloader(self):
|
||||
if self._tng_dataloader is None:
|
||||
try:
|
||||
self._tng_dataloader = self.__dataloader(train=True)
|
||||
except Exception as e:
|
||||
print(e)
|
||||
raise e
|
||||
return self._tng_dataloader
|
||||
|
||||
@property
|
||||
def val_dataloader(self):
|
||||
if self._val_dataloader is None:
|
||||
try:
|
||||
self._val_dataloader = self.__dataloader(train=False)
|
||||
except Exception as e:
|
||||
print(e)
|
||||
raise e
|
||||
return self._val_dataloader
|
||||
|
||||
@property
|
||||
def test_dataloader(self):
|
||||
if self._test_dataloader is None:
|
||||
try:
|
||||
self._test_dataloader = self.__dataloader(train=False)
|
||||
except Exception as e:
|
||||
print(e)
|
||||
raise e
|
||||
return self._test_dataloader
|
||||
|
||||
@staticmethod
|
||||
def add_model_specific_args(parent_parser, root_dir):
|
||||
parser = HyperOptArgumentParser(strategy=parent_parser.strategy, parents=[parent_parser])
|
||||
|
||||
# param overwrites
|
||||
# parser.set_defaults(gradient_clip=5.0)
|
||||
|
||||
# network params
|
||||
parser.opt_list('--drop_prob', default=0.2, options=[0.2, 0.5], type=float, tunable=False)
|
||||
parser.add_argument('--in_features', default=28*28)
|
||||
parser.add_argument('--out_features', default=10)
|
||||
parser.add_argument('--hidden_dim', default=50000) # use 500 for CPU, 50000 for GPU to see speed difference
|
||||
|
||||
# data
|
||||
parser.add_argument('--data_root', default=os.path.join(root_dir, 'mnist'), type=str)
|
||||
|
||||
# training params (opt)
|
||||
parser.opt_list('--learning_rate', default=0.001, type=float, options=[0.0001, 0.0005, 0.001, 0.005],
|
||||
tunable=False)
|
||||
parser.opt_list('--batch_size', default=256, type=int, options=[32, 64, 128, 256], tunable=False)
|
||||
parser.opt_list('--optimizer_name', default='adam', type=str, options=['adam'], tunable=False)
|
||||
return parser
|
||||
@@ -1,210 +0,0 @@
|
||||
import os
|
||||
import sys
|
||||
import numpy as np
|
||||
from time import sleep
|
||||
import torch
|
||||
|
||||
from test_tube import HyperOptArgumentParser, Experiment, SlurmCluster
|
||||
from pytorch_lightning.models.trainer import Trainer
|
||||
from pytorch_lightning.utils.arg_parse import add_default_args
|
||||
|
||||
from pytorch_lightning.callbacks import EarlyStopping, ModelCheckpoint
|
||||
|
||||
SEED = 2334
|
||||
torch.manual_seed(SEED)
|
||||
np.random.seed(SEED)
|
||||
|
||||
# ---------------------
|
||||
# DEFINE MODEL HERE
|
||||
# ---------------------
|
||||
from docs.source.examples.example_model import ExampleModel
|
||||
# ---------------------
|
||||
|
||||
AVAILABLE_MODELS = {
|
||||
'model_template': ExampleModel
|
||||
}
|
||||
|
||||
|
||||
"""
|
||||
Allows training by using command line arguments
|
||||
Run by:
|
||||
# TYPE YOUR RUN COMMAND HERE
|
||||
"""
|
||||
|
||||
|
||||
def main_local(hparams):
|
||||
main(hparams, None, None)
|
||||
|
||||
|
||||
def main(hparams, cluster, results_dict):
|
||||
"""
|
||||
Main training routine specific for this project
|
||||
:param hparams:
|
||||
:return:
|
||||
"""
|
||||
on_gpu = hparams.gpus is not None and torch.cuda.is_available()
|
||||
|
||||
device = 'cuda' if on_gpu else 'cpu'
|
||||
hparams.__setattr__('device', device)
|
||||
hparams.__setattr__('on_gpu', on_gpu)
|
||||
hparams.__setattr__('nb_gpus', torch.cuda.device_count())
|
||||
hparams.__setattr__('inference_mode', hparams.model_load_weights_path is not None)
|
||||
|
||||
# delay each training start to not overwrite logs
|
||||
process_position, current_gpu = TRAINING_MODEL.get_process_position(hparams.gpus)
|
||||
sleep(process_position + 1)
|
||||
|
||||
# init experiment
|
||||
log_dir = os.path.dirname(os.path.realpath(__file__))
|
||||
exp = Experiment(
|
||||
name='test_tube_exp',
|
||||
debug=True,
|
||||
save_dir=log_dir,
|
||||
version=0,
|
||||
autosave=False,
|
||||
description='test demo'
|
||||
)
|
||||
|
||||
exp.argparse(hparams)
|
||||
exp.save()
|
||||
|
||||
# build model
|
||||
print('loading model...')
|
||||
model = TRAINING_MODEL(hparams)
|
||||
print('model built')
|
||||
|
||||
# callbacks
|
||||
early_stop = EarlyStopping(
|
||||
monitor=hparams.early_stop_metric,
|
||||
patience=hparams.early_stop_patience,
|
||||
verbose=True,
|
||||
mode=hparams.early_stop_mode
|
||||
)
|
||||
|
||||
model_save_path = '{}/{}/{}'.format(hparams.model_save_path, exp.name, exp.version)
|
||||
checkpoint = ModelCheckpoint(
|
||||
filepath=model_save_path,
|
||||
save_function=None,
|
||||
save_best_only=True,
|
||||
verbose=True,
|
||||
monitor=hparams.model_save_monitor_value,
|
||||
mode=hparams.model_save_monitor_mode
|
||||
)
|
||||
|
||||
# gpus are ; separated for inside a node and , within nodes
|
||||
gpu_list = None
|
||||
if hparams.gpus is not None:
|
||||
gpu_list = [int(x) for x in hparams.gpus.split(';')]
|
||||
|
||||
# configure trainer
|
||||
trainer = Trainer(
|
||||
experiment=exp,
|
||||
cluster=cluster,
|
||||
checkpoint_callback=checkpoint,
|
||||
early_stop_callback=early_stop,
|
||||
gpus=gpu_list
|
||||
)
|
||||
|
||||
# train model
|
||||
trainer.fit(model)
|
||||
|
||||
|
||||
def get_default_parser(strategy, root_dir):
|
||||
|
||||
possible_model_names = list(AVAILABLE_MODELS.keys())
|
||||
parser = HyperOptArgumentParser(strategy=strategy, add_help=False)
|
||||
add_default_args(parser, root_dir, possible_model_names=possible_model_names, rand_seed=SEED)
|
||||
return parser
|
||||
|
||||
|
||||
def get_model_name(args):
|
||||
for i, arg in enumerate(args):
|
||||
if 'model_name' in arg:
|
||||
return args[i+1]
|
||||
|
||||
|
||||
def optimize_on_cluster(hyperparams):
|
||||
# enable cluster training
|
||||
cluster = SlurmCluster(
|
||||
hyperparam_optimizer=hyperparams,
|
||||
log_path=hyperparams.tt_save_path,
|
||||
test_tube_exp_name=hyperparams.tt_name
|
||||
)
|
||||
|
||||
# email for cluster coms
|
||||
cluster.notify_job_status(email='add_email_here', on_done=True, on_fail=True)
|
||||
|
||||
# configure cluster
|
||||
cluster.per_experiment_nb_gpus = hyperparams.per_experiment_nb_gpus
|
||||
cluster.job_time = '48:00:00'
|
||||
cluster.gpu_type = '1080ti'
|
||||
cluster.memory_mb_per_node = 48000
|
||||
|
||||
# any modules for code to run in env
|
||||
cluster.add_command('source activate pytorch_lightning')
|
||||
|
||||
# name of exp
|
||||
job_display_name = hyperparams.tt_name.split('_')[0]
|
||||
job_display_name = job_display_name[0:3]
|
||||
|
||||
# run hopt
|
||||
print('submitting jobs...')
|
||||
cluster.optimize_parallel_cluster_gpu(
|
||||
main,
|
||||
nb_trials=hyperparams.nb_hopt_trials,
|
||||
job_name=job_display_name
|
||||
)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
|
||||
model_name = get_model_name(sys.argv)
|
||||
if model_name is None:
|
||||
model_name = 'model_template'
|
||||
|
||||
# use default args
|
||||
root_dir = os.path.dirname(os.path.realpath(__file__))
|
||||
parent_parser = get_default_parser(strategy='random_search', root_dir=root_dir)
|
||||
|
||||
# allow model to overwrite or extend args
|
||||
TRAINING_MODEL = AVAILABLE_MODELS[model_name]
|
||||
parser = TRAINING_MODEL.add_model_specific_args(parent_parser, root_dir)
|
||||
hyperparams = parser.parse_args()
|
||||
|
||||
# format GPU layout
|
||||
os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
|
||||
|
||||
# ---------------------
|
||||
# RUN TRAINING
|
||||
# ---------------------
|
||||
|
||||
# cluster and CPU
|
||||
if hyperparams.on_cluster:
|
||||
# run on HPC cluster
|
||||
print('RUNNING ON SLURM CLUSTER')
|
||||
gpu_ids = hyperparams.gpus.split(';')
|
||||
os.environ["CUDA_VISIBLE_DEVICES"] = ','.join(gpu_ids)
|
||||
optimize_on_cluster(hyperparams)
|
||||
|
||||
elif hyperparams.gpus is None:
|
||||
# run on cpu
|
||||
print('RUNNING ON CPU')
|
||||
main(hyperparams, None, None)
|
||||
|
||||
# single or multiple GPUs on same machine
|
||||
gpu_ids = hyperparams.gpus.split(';')
|
||||
if hyperparams.interactive:
|
||||
# run on 1 gpu
|
||||
print(f'RUNNING INTERACTIVE MODE ON GPUS. gpu ids: {gpu_ids}')
|
||||
os.environ["CUDA_VISIBLE_DEVICES"] = ','.join(gpu_ids)
|
||||
main(hyperparams, None, None)
|
||||
|
||||
else:
|
||||
# multiple GPUs on same machine
|
||||
print(f'RUNNING MULTI GPU. GPU ids: {gpu_ids}')
|
||||
hyperparams.optimize_parallel_gpu(
|
||||
main_local,
|
||||
gpu_ids=gpu_ids,
|
||||
nb_trials=hyperparams.nb_hopt_trials,
|
||||
nb_workers=len(gpu_ids)
|
||||
)
|
||||
Reference in New Issue
Block a user