mirror of
https://github.com/wassname/pytorch-lightning.git
synced 2026-09-09 11:32:07 +08:00
fix LightningTemplateModel (#1577)
* fix LightningTemplateModel * update CHANGELOG.md * update LightningTemplate * update changelog * update changelog * loss fix
This commit is contained in:
Dmitry Lipin
@@ -69,6 +69,7 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/).
|
||||
- Defines shared proc. rank, remove rank from instances (e.g. loggers) ([#1408](https://github.com/PyTorchLightning/pytorch-lightning/pull/1408))
|
||||
- Updated semantic segmentation example with custom U-Net and logging ([#1371](https://github.com/PyTorchLightning/pytorch-lightning/pull/1371))
|
||||
- Disabled val and test shuffling ([#1600](https://github.com/PyTorchLightning/pytorch-lightning/pull/1600))
|
||||
- Updated LightningTemplateModel to look more like Colab example ([#1546](https://github.com/PyTorchLightning/pytorch-lightning/pull/1577))
|
||||
|
||||
### Deprecated
|
||||
|
||||
|
||||
@@ -46,22 +46,6 @@ class LightningTemplateModel(LightningModule):
|
||||
# init superclass
|
||||
super().__init__()
|
||||
self.hparams = hparams
|
||||
|
||||
self.batch_size = hparams.batch_size
|
||||
|
||||
# if you specify an example input, the summary will show input/output for each layer
|
||||
self.example_input_array = torch.rand(5, 28 * 28)
|
||||
|
||||
# build model
|
||||
self.__build_model()
|
||||
|
||||
# ---------------------
|
||||
# MODEL SETUP
|
||||
# ---------------------
|
||||
def __build_model(self):
|
||||
"""
|
||||
Layout the model.
|
||||
"""
|
||||
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)
|
||||
@@ -70,27 +54,17 @@ class LightningTemplateModel(LightningModule):
|
||||
self.c_d2 = nn.Linear(in_features=self.hparams.hidden_dim,
|
||||
out_features=self.hparams.out_features)
|
||||
|
||||
# ---------------------
|
||||
# TRAINING
|
||||
# ---------------------
|
||||
def forward(self, x):
|
||||
"""
|
||||
No special modification required for Lightning, define it as you normally would
|
||||
in the `nn.Module` in vanilla PyTorch.
|
||||
"""
|
||||
x = self.c_d1(x)
|
||||
x = self.c_d1(x.view(x.size(0), -1))
|
||||
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
|
||||
return x
|
||||
|
||||
def training_step(self, batch, batch_idx):
|
||||
"""
|
||||
@@ -99,22 +73,10 @@ class LightningTemplateModel(LightningModule):
|
||||
"""
|
||||
# forward pass
|
||||
x, y = batch
|
||||
x = x.view(x.size(0), -1)
|
||||
|
||||
y_hat = self(x)
|
||||
|
||||
# calculate loss
|
||||
loss_val = self.loss(y, y_hat)
|
||||
|
||||
tqdm_dict = {'train_loss': loss_val}
|
||||
output = OrderedDict({
|
||||
'loss': loss_val,
|
||||
'progress_bar': tqdm_dict,
|
||||
'log': tqdm_dict
|
||||
})
|
||||
|
||||
# can also return just a scalar instead of a dict (return loss_val)
|
||||
return output
|
||||
loss = F.cross_entropy(y_hat, y)
|
||||
tensorboard_logs = {'train_loss': loss}
|
||||
return {'loss': loss, 'log': tensorboard_logs}
|
||||
|
||||
def validation_step(self, batch, batch_idx):
|
||||
"""
|
||||
@@ -122,58 +84,35 @@ class LightningTemplateModel(LightningModule):
|
||||
passed in as `batch`.
|
||||
"""
|
||||
x, y = batch
|
||||
x = x.view(x.size(0), -1)
|
||||
y_hat = self(x)
|
||||
|
||||
loss_val = self.loss(y, y_hat)
|
||||
|
||||
# acc
|
||||
val_loss = F.cross_entropy(y_hat, y)
|
||||
labels_hat = torch.argmax(y_hat, dim=1)
|
||||
val_acc = torch.sum(y == labels_hat).item() / (len(y) * 1.0)
|
||||
val_acc = torch.tensor(val_acc)
|
||||
n_correct_pred = torch.sum(y == labels_hat).item()
|
||||
return {'val_loss': val_loss, "n_correct_pred": n_correct_pred, "n_pred": len(x)}
|
||||
|
||||
if self.on_gpu:
|
||||
val_acc = val_acc.cuda(loss_val.device.index)
|
||||
|
||||
output = OrderedDict({
|
||||
'val_loss': loss_val,
|
||||
'val_acc': val_acc,
|
||||
})
|
||||
|
||||
# can also return just a scalar instead of a dict (return loss_val)
|
||||
return output
|
||||
def test_step(self, batch, batch_idx):
|
||||
x, y = batch
|
||||
y_hat = self(x)
|
||||
test_loss = F.cross_entropy(y_hat, y)
|
||||
labels_hat = torch.argmax(y_hat, dim=1)
|
||||
n_correct_pred = torch.sum(y == labels_hat).item()
|
||||
return {'test_loss': test_loss, "n_correct_pred": n_correct_pred, "n_pred": len(x)}
|
||||
|
||||
def validation_epoch_end(self, outputs):
|
||||
"""
|
||||
Called at the end of validation to aggregate outputs.
|
||||
:param outputs: list of individual outputs of each validation step.
|
||||
"""
|
||||
# if returned a scalar from validation_step, outputs is a list of tensor scalars
|
||||
# we return just the average in this case (if we want)
|
||||
# return torch.stack(outputs).mean()
|
||||
avg_loss = torch.stack([x['val_loss'] for x in outputs]).mean()
|
||||
val_acc = sum([x['n_correct_pred'] for x in outputs]) / sum(x['n_pred'] for x in outputs)
|
||||
tensorboard_logs = {'val_loss': avg_loss, 'val_acc': val_acc}
|
||||
return {'val_loss': avg_loss, 'log': tensorboard_logs}
|
||||
|
||||
val_loss_mean = 0
|
||||
val_acc_mean = 0
|
||||
for output in outputs:
|
||||
val_loss = output['val_loss']
|
||||
|
||||
# reduce manually when using dp
|
||||
if self.trainer.use_dp or self.trainer.use_ddp2:
|
||||
val_loss = torch.mean(val_loss)
|
||||
val_loss_mean += val_loss
|
||||
|
||||
# reduce manually when using dp
|
||||
val_acc = output['val_acc']
|
||||
if self.trainer.use_dp or self.trainer.use_ddp2:
|
||||
val_acc = torch.mean(val_acc)
|
||||
|
||||
val_acc_mean += val_acc
|
||||
|
||||
val_loss_mean /= len(outputs)
|
||||
val_acc_mean /= len(outputs)
|
||||
tqdm_dict = {'val_loss': val_loss_mean, 'val_acc': val_acc_mean}
|
||||
result = {'progress_bar': tqdm_dict, 'log': tqdm_dict, 'val_loss': val_loss_mean}
|
||||
return result
|
||||
def test_epoch_end(self, outputs):
|
||||
avg_loss = torch.stack([x['test_loss'] for x in outputs]).mean()
|
||||
test_acc = sum([x['n_correct_pred'] for x in outputs]) / sum(x['n_pred'] for x in outputs)
|
||||
tensorboard_logs = {'test_loss': avg_loss, 'test_acc': test_acc}
|
||||
return {'test_loss': avg_loss, 'log': tensorboard_logs}
|
||||
|
||||
# ---------------------
|
||||
# TRAINING SETUP
|
||||
@@ -187,72 +126,23 @@ class LightningTemplateModel(LightningModule):
|
||||
scheduler = optim.lr_scheduler.CosineAnnealingLR(optimizer, T_max=10)
|
||||
return [optimizer], [scheduler]
|
||||
|
||||
def __dataloader(self, train):
|
||||
# this is neede when you want some info about dataset before binding to trainer
|
||||
self.prepare_data()
|
||||
# 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=False)
|
||||
|
||||
# when using multi-node (ddp) we need to add the datasampler
|
||||
batch_size = self.hparams.batch_size
|
||||
|
||||
loader = DataLoader(
|
||||
dataset=dataset,
|
||||
batch_size=batch_size,
|
||||
num_workers=0
|
||||
)
|
||||
|
||||
return loader
|
||||
|
||||
def prepare_data(self):
|
||||
transform = transforms.Compose([transforms.ToTensor(),
|
||||
transforms.Normalize((0.5,), (1.0,))])
|
||||
_ = MNIST(root=self.hparams.data_root, train=True,
|
||||
transform=transform, download=True)
|
||||
self.mnist_train = MNIST(self.hparams.data_root, train=True, download=True, transform=transform)
|
||||
self.mnist_test = MNIST(self.hparams.data_root, train=False, download=True, transform=transform)
|
||||
|
||||
def train_dataloader(self):
|
||||
log.info('Training data loader called.')
|
||||
return self.__dataloader(train=True)
|
||||
return DataLoader(self.mnist_train, batch_size=self.hparams.batch_size, num_workers=4)
|
||||
|
||||
def val_dataloader(self):
|
||||
log.info('Validation data loader called.')
|
||||
return self.__dataloader(train=False)
|
||||
return DataLoader(self.mnist_test, batch_size=self.hparams.batch_size, num_workers=4)
|
||||
|
||||
def test_dataloader(self):
|
||||
log.info('Test data loader called.')
|
||||
return self.__dataloader(train=False)
|
||||
|
||||
def test_step(self, batch, batch_idx):
|
||||
"""
|
||||
Lightning calls this during testing, similar to `validation_step`,
|
||||
with the data from the test dataloader passed in as `batch`.
|
||||
"""
|
||||
output = self.validation_step(batch, batch_idx)
|
||||
# Rename output keys
|
||||
output['test_loss'] = output.pop('val_loss')
|
||||
output['test_acc'] = output.pop('val_acc')
|
||||
|
||||
return output
|
||||
|
||||
def test_epoch_end(self, outputs):
|
||||
"""
|
||||
Called at the end of test to aggregate outputs, similar to `validation_epoch_end`.
|
||||
:param outputs: list of individual outputs of each test step
|
||||
"""
|
||||
results = self.validation_step_end(outputs)
|
||||
|
||||
# rename some keys
|
||||
results['progress_bar'].update({
|
||||
'test_loss': results['progress_bar'].pop('val_loss'),
|
||||
'test_acc': results['progress_bar'].pop('val_acc'),
|
||||
})
|
||||
results['log'] = results['progress_bar']
|
||||
results['test_loss'] = results.pop('val_loss')
|
||||
|
||||
return results
|
||||
return DataLoader(self.mnist_test, batch_size=self.hparams.batch_size, num_workers=4)
|
||||
|
||||
@staticmethod
|
||||
def add_model_specific_args(parent_parser, root_dir): # pragma: no-cover
|
||||
|
||||
Reference in New Issue
Block a user