mirror of
https://github.com/wassname/pytorch-lightning.git
synced 2026-09-10 12:21:57 +08:00
added example and verified
This commit is contained in:
William Falcon
@@ -0,0 +1,76 @@
|
||||
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.utils.pt_callbacks import EarlyStopping, ModelCheckpoint
|
||||
from demo.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
|
||||
print('loading model...')
|
||||
model = ExampleModel(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
|
||||
)
|
||||
|
||||
# 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)
|
||||
@@ -0,0 +1,200 @@
|
||||
import torch.nn as nn
|
||||
import numpy as np
|
||||
from pytorch_lightning.root_module.root_module import RootModule
|
||||
from test_tube import HyperOptArgumentParser
|
||||
from torchvision.datasets import MNIST
|
||||
import torchvision.transforms as transforms
|
||||
import torch
|
||||
import torch.nn.functional as F
|
||||
|
||||
|
||||
class ExampleModel(RootModule):
|
||||
"""
|
||||
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 = F.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):
|
||||
"""
|
||||
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)
|
||||
|
||||
tqdm_dic = {'tng_loss': loss_val.item()}
|
||||
return loss_val, tqdm_dic
|
||||
|
||||
def validation_step(self, data_batch):
|
||||
"""
|
||||
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 = {'y_hat': y_hat, 'val_loss': loss_val.item(), 'val_acc': 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
|
||||
accs = []
|
||||
for output in outputs:
|
||||
val_loss_mean += output['val_loss']
|
||||
accs.append(output['val_acc'])
|
||||
|
||||
val_loss_mean /= len(outputs)
|
||||
tqdm_dic = {'val_loss': val_loss_mean, 'val_acc': np.mean(accs)}
|
||||
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):
|
||||
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('--hidden_dim', default=500)
|
||||
parser.add_argument('--out_features', default=10)
|
||||
|
||||
# data
|
||||
parser.add_argument('--data_root', default='/Users/williamfalcon/Developer/personal/research_lib/research_proj/datasets/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
|
||||
|
||||
@@ -1,12 +1,12 @@
|
||||
import os
|
||||
import sys
|
||||
|
||||
import torch
|
||||
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 time import sleep
|
||||
|
||||
from pytorch_lightning.utils.pt_callbacks import EarlyStopping, ModelCheckpoint
|
||||
|
||||
@@ -17,11 +17,11 @@ np.random.seed(SEED)
|
||||
# ---------------------
|
||||
# DEFINE MODEL HERE
|
||||
# ---------------------
|
||||
from pytorch_lightning.models.sample_model_template.model_template import ExampleModel1
|
||||
from demo.example_model import ExampleModel
|
||||
# ---------------------
|
||||
|
||||
AVAILABLE_MODELS = {
|
||||
'model_1': ExampleModel1
|
||||
'model_template': ExampleModel
|
||||
}
|
||||
|
||||
|
||||
@@ -95,28 +95,9 @@ def main(hparams, cluster, results_dict):
|
||||
# configure trainer
|
||||
trainer = Trainer(
|
||||
experiment=exp,
|
||||
on_gpu=on_gpu,
|
||||
cluster=cluster,
|
||||
enable_tqdm=hparams.enable_tqdm,
|
||||
overfit_pct=hparams.overfit,
|
||||
track_grad_norm=hparams.track_grad_norm,
|
||||
fast_dev_run=hparams.fast_dev_run,
|
||||
check_val_every_n_epoch=hparams.check_val_every_n_epoch,
|
||||
accumulate_grad_batches=hparams.accumulate_grad_batches,
|
||||
process_position=process_position,
|
||||
current_gpu_name=current_gpu,
|
||||
checkpoint_callback=checkpoint,
|
||||
early_stop_callback=early_stop,
|
||||
enable_early_stop=hparams.enable_early_stop,
|
||||
max_nb_epochs=hparams.max_nb_epochs,
|
||||
min_nb_epochs=hparams.min_nb_epochs,
|
||||
train_percent_check=hparams.train_percent_check,
|
||||
val_percent_check=hparams.val_percent_check,
|
||||
test_percent_check=hparams.test_percent_check,
|
||||
val_check_interval=hparams.val_check_interval,
|
||||
log_save_interval=hparams.log_save_interval,
|
||||
add_log_row_interval=hparams.add_log_row_interval,
|
||||
lr_scheduler_milestones=hparams.lr_scheduler_milestones
|
||||
)
|
||||
|
||||
# train model
|
||||
@@ -173,6 +154,8 @@ def optimize_on_cluster(hyperparams):
|
||||
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.split(os.path.dirname(sys.modules['__main__'].__file__))[0]
|
||||
@@ -181,7 +164,6 @@ if __name__ == '__main__':
|
||||
# allow model to overwrite or extend args
|
||||
TRAINING_MODEL = AVAILABLE_MODELS[model_name]
|
||||
parser = TRAINING_MODEL.add_model_specific_args(parent_parser)
|
||||
parser.json_config('-c', '--config', default=root_dir + '/run_configs/local.json')
|
||||
hyperparams = parser.parse_args()
|
||||
|
||||
# format GPU layout
|
||||
@@ -190,25 +172,30 @@ if __name__ == '__main__':
|
||||
|
||||
# RUN TRAINING
|
||||
if hyperparams.on_cluster:
|
||||
# Gets called when running via HPC cluster
|
||||
print('RUNNING ON SLURM CLUSTER')
|
||||
os.environ["CUDA_VISIBLE_DEVICES"] = ','.join(gpu_ids)
|
||||
optimize_on_cluster(hyperparams)
|
||||
|
||||
elif hyperparams.single_run_gpu:
|
||||
# run on 1 gpu
|
||||
print(f'RUNNING 1 TRIAL ON GPU. gpu: {gpu_ids[0]}')
|
||||
os.environ["CUDA_VISIBLE_DEVICES"] = gpu_ids[0]
|
||||
main(hyperparams, None, None)
|
||||
|
||||
elif hyperparams.local or hyperparams.single_run:
|
||||
# run 1 trial but on CPU
|
||||
os.environ["CUDA_VISIBLE_DEVICES"] = '0'
|
||||
print('RUNNING LOCALLY')
|
||||
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)
|
||||
)
|
||||
)
|
||||
|
||||
@@ -1,9 +1,9 @@
|
||||
import torch
|
||||
import tqdm
|
||||
import numpy as np
|
||||
from research_lib.root_module.memory import get_gpu_memory_map
|
||||
from pytorch_lightning.root_module.memory import get_gpu_memory_map
|
||||
import traceback
|
||||
from research_lib.root_module.model_saving import TrainerIO
|
||||
from pytorch_lightning.root_module.model_saving import TrainerIO
|
||||
from torch.optim.lr_scheduler import MultiStepLR
|
||||
|
||||
|
||||
@@ -11,17 +11,17 @@ class Trainer(TrainerIO):
|
||||
|
||||
def __init__(self,
|
||||
experiment,
|
||||
cluster,
|
||||
checkpoint_callback, early_stop_callback,
|
||||
cluster=None,
|
||||
process_position=0,
|
||||
current_gpu_name=0,
|
||||
on_gpu=False,
|
||||
enable_tqdm=True,
|
||||
overfit_pct=None,
|
||||
overfit_pct=0.0,
|
||||
track_grad_norm=-1,
|
||||
check_val_every_n_epoch=1,
|
||||
fast_dev_run=False,
|
||||
accumulate_grad_batches=False,
|
||||
accumulate_grad_batches=1,
|
||||
enable_early_stop=True, max_nb_epochs=5, min_nb_epochs=1,
|
||||
train_percent_check=1.0, val_percent_check=1.0, test_percent_check=1.0, val_check_interval=0.95,
|
||||
log_save_interval=1, add_log_row_interval=1,
|
||||
@@ -226,7 +226,8 @@ class Trainer(TrainerIO):
|
||||
self.experiment.save()
|
||||
|
||||
# enable cluster checkpointing
|
||||
self.enable_auto_hpc_walltime_manager()
|
||||
if self.cluster is not None:
|
||||
self.enable_auto_hpc_walltime_manager()
|
||||
|
||||
# ---------------------------
|
||||
# CORE TRAINING LOOP
|
||||
|
||||
@@ -14,7 +14,7 @@ class RootModule(GradInformation, ModelIO, OptimizerConfig, ModelHooks):
|
||||
def __init__(self, hparams):
|
||||
super(RootModule, self).__init__()
|
||||
self.hparams = hparams
|
||||
self.on_gpu = hparams.on_gpu
|
||||
|
||||
self.dtype = torch.FloatTensor
|
||||
self.exp_save_path = None
|
||||
self.current_epoch = 0
|
||||
@@ -25,6 +25,13 @@ class RootModule(GradInformation, ModelIO, OptimizerConfig, ModelHooks):
|
||||
self.gradient_clip = hparams.gradient_clip
|
||||
self.num = 2
|
||||
|
||||
# track if gpu was requested for checkpointing
|
||||
self.on_gpu = False
|
||||
try:
|
||||
self.on_gpu = hparams.on_gpu
|
||||
except Exception as e:
|
||||
pass
|
||||
|
||||
# computed vars for the dataloaders
|
||||
self._tng_dataloader = None
|
||||
self._val_dataloader = None
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
def add_default_args(parser, root_dir, possible_model_names, rand_seed):
|
||||
def add_default_args(parser, root_dir, rand_seed=None, possible_model_names=None):
|
||||
|
||||
# tng, test, val check intervals
|
||||
parser.add_argument('--eval_test_set', dest='eval_test_set', action='store_true', help='true = run test set also')
|
||||
@@ -32,7 +32,9 @@ def add_default_args(parser, root_dir, possible_model_names, rand_seed):
|
||||
|
||||
# model paths
|
||||
parser.add_argument('--model_load_weights_path', default=None, type=str)
|
||||
parser.add_argument('--model_name', default='', help=','.join(possible_model_names))
|
||||
|
||||
if possible_model_names is not None:
|
||||
parser.add_argument('--model_name', default='', help=','.join(possible_model_names))
|
||||
|
||||
# test_tube settings
|
||||
parser.add_argument('-en', '--tt_name', default='r_lib_')
|
||||
@@ -58,7 +60,9 @@ def add_default_args(parser, root_dir, possible_model_names, rand_seed):
|
||||
parser.add_argument('--overfit', default=-1, type=float, help='% of dataset to use with this option. float, or -1 for none')
|
||||
|
||||
# debug args
|
||||
parser.add_argument('--random_seed', default=rand_seed, type=int)
|
||||
if rand_seed is not None:
|
||||
parser.add_argument('--random_seed', default=rand_seed, type=int)
|
||||
|
||||
parser.add_argument('--live', dest='live', action='store_true', help='runs on gpu without cluster')
|
||||
parser.add_argument('--enable_debug', dest='debug', action='store_true', help='enables/disables test tube')
|
||||
parser.add_argument('--enable_local', dest='local', action='store_true', help='enables local tng')
|
||||
|
||||
Reference in New Issue
Block a user