StyleTransfer¶
- class flash.image.style_transfer.model.StyleTransfer(style_image=None, model=None, backbone='vgg16', content_layer='relu2_2', content_weight=100000.0, style_layers=['relu1_2', 'relu2_2', 'relu3_3', 'relu4_3'], style_weight=10000000000.0, optimizer='Adam', lr_scheduler=None, learning_rate=None)[source]¶
StyleTransfer
is aTask
for transferring the style from one image onto another. For more details, see Style Transfer.- Parameters
style_image¶ (
Union
[str
,Tensor
,None
]) – Image or path to an image to derive the style from.model¶ (
Optional
[Module
]) – The model by the style transfer task.backbone¶ (
str
) – A string or model to use to compute the style loss from.content_layer¶ (
str
) – Which layer from the backbone to extract the content loss from.content_weight¶ (
float
) – The weight associated with the content loss. A lower value will lose content over style.style_layers¶ (
Union
[Sequence
[str
],str
]) – Layers from the backbone to derive the style loss from.style_weight¶ (
float
) – The weight associated with the style loss. A lower value will lose style over content.optimizer¶ (
TypeVar
(OPTIMIZER_TYPE
,str
,Callable
,Tuple
[str
,Dict
[str
,Any
]],None
)) – Optimizer to use for training.lr_scheduler¶ (
Optional
[TypeVar
(LR_SCHEDULER_TYPE
,str
,Callable
,Tuple
[str
,Dict
[str
,Any
]],Tuple
[str
,Dict
[str
,Any
],Dict
[str
,Any
]],None
)]) – The LR scheduler to use during training.learning_rate¶ (
Optional
[float
]) – Learning rate to use for training, defaults to1e-3
.
- classmethod available_finetuning_strategies(cls)¶
Returns a list containing the keys of the available Finetuning Strategies.
- classmethod available_lr_schedulers(cls)¶
Returns a list containing the keys of the available LR schedulers.
- classmethod available_optimizers(cls)¶
Returns a list containing the keys of the available Optimizers.
- classmethod available_outputs(cls)¶
Returns the list of available outputs (that can be used during prediction or serving) for this
Task
.Examples
..testsetup:
>>> from flash import Task
>>> print(Task.available_outputs()) ['preds', 'raw']
- classmethod load_from_checkpoint(cls, checkpoint_path, map_location=None, hparams_file=None, strict=True, **kwargs)¶
Primary way of loading a model from a checkpoint. When Lightning saves a checkpoint it stores the arguments passed to
__init__
in the checkpoint under"hyper_parameters"
.Any arguments specified through **kwargs will override args stored in
"hyper_parameters"
.- Parameters
checkpoint_path¶ (
Union
[str
,Path
,IO
]) – Path to checkpoint. This can also be a URL, or file-like objectmap_location¶ (
Union
[device
,str
,int
,Callable
[[Union
[device
,str
,int
]],Union
[device
,str
,int
]],Dict
[Union
[device
,str
,int
],Union
[device
,str
,int
]],None
]) – If your checkpoint saved a GPU model and you now load on CPUs or a different number of GPUs, use this to map to the new setup. The behaviour is the same as intorch.load()
.hparams_file¶ (
Union
[str
,Path
,None
]) –Optional path to a
.yaml
or.csv
file with hierarchical structure as in this example:drop_prob: 0.2 dataloader: batch_size: 32
You most likely won’t need this since Lightning will always save the hyperparameters to the checkpoint. However, if your checkpoint weights don’t have the hyperparameters saved, use this method to pass in a
.yaml
file with the hparams you’d like to use. These will be converted into adict
and passed into yourLightningModule
for use.If your model’s
hparams
argument isNamespace
and.yaml
file has hierarchical structure, you need to refactor your model to treathparams
asdict
.strict¶ (
bool
) – Whether to strictly enforce that the keys incheckpoint_path
match the keys returned by this module’s state dict.**kwargs¶ – Any extra keyword args needed to init the model. Can also be used to override saved hyperparameter values.
- Return type
Self
- Returns
LightningModule
instance with loaded weights and hyperparameters (if available).
Note
load_from_checkpoint
is a class method. You should use yourLightningModule
class to call it instead of theLightningModule
instance.Example:
# load weights without mapping ... model = MyLightningModule.load_from_checkpoint('path/to/checkpoint.ckpt') # or load weights mapping all weights from GPU 1 to GPU 0 ... map_location = {'cuda:1':'cuda:0'} model = MyLightningModule.load_from_checkpoint( 'path/to/checkpoint.ckpt', map_location=map_location ) # or load weights and hyperparameters from separate files. model = MyLightningModule.load_from_checkpoint( 'path/to/checkpoint.ckpt', hparams_file='/path/to/hparams_file.yaml' ) # override some of the params with new values model = MyLightningModule.load_from_checkpoint( PATH, num_layers=128, pretrained_ckpt_path=NEW_PATH, ) # predict pretrained_model.eval() pretrained_model.freeze() y_hat = pretrained_model(x)