def fit(self, module):
# Prepare module for training
module.trainer = self
# Update and print module configuration
prep_logger_and_checkpoint(module)
print_config(module.config)
# Send module to GPU
module = module.to('cuda')
# Configure optimizer and scheduler
module.configure_optimizers()
# Create distributed optimizer
compression = hvd.Compression.none
optimizer = hvd.DistributedOptimizer(module.optimizer,
named_parameters=module.named_parameters(), compression=compression)
scheduler = module.scheduler
# Get train and val dataloaders
train_dataloader = module.train_dataloader()
val_dataloaders = module.val_dataloader()
# Epoch loop
for epoch in range(module.current_epoch, self.max_epochs):
# Train
self.train(train_dataloader, module, optimizer)
# Validation
validation_output = self.validate(val_dataloaders, module)
# Check and save model
self.check_and_save(module, validation_output)
# Update current epoch
module.current_epoch += 1
# Take a scheduler step
scheduler.step()
def fit(self, module):
# Prepare module for training
module.trainer = self
# Update and print module configuration
prep_logger_and_checkpoint(module)
print_config(module.config)
# Send module to GPU
module = module.to('cuda')
# Configure optimizer and scheduler
module.configure_optimizers()
# Create distributed optimizer
# compression = hvd.Compression.none
optimizer = module.optimizer
scheduler = module.scheduler
# Get train and val dataloaders
train_dataloader = module.train_dataloader()
val_dataloaders = module.val_dataloader()
# Epoch loop
for epoch in range(module.current_epoch, self.max_epochs):
# Train
self.train(train_dataloader, module, optimizer)
# avg_train_loss = metrics['avg_train-loss']
# avg_train_photometric_loss = metrics['avg_train-photometric_loss']
# avg_train_smoothness_loss = metrics['avg_train-smoothness_loss']
# avg_train_supervised_loss = metrics['avg_train-supervised_loss']
# writer.add_scalar('Loss/avg_train_loss'
# , avg_train_loss, epoch)
# writer.add_scalar('Loss/avg_train_photometric_loss'
# , avg_train_photometric_loss, epoch)
# writer.add_scalar('Loss/avg_train_smoothness_loss'
# , avg_train_smoothness_loss, epoch)
# writer.add_scalar('Loss/avg_train_supervised_loss'
# , avg_train_supervised_loss, epoch)
# Validation
validation_output = self.validate(val_dataloaders, module)
# Check and save model
self.check_and_save(module, validation_output)
# Update current epoch
module.current_epoch += 1
# Take a scheduler step
scheduler.step()