Deprecated components (Will not be maintained actively)

[SeanNaren]

Related to #712

Below I've gone through all the different modules available, and come up with a list of deprecated modules. I've been lenient in my choices, primarily to allow some discussions if any should be moved around. If you think the list is wrong, please comment!

Deprecated modules will be made clear within a new documentation page containing a list of all deprecated modules (+ links eventually). This hopefully allows us to draw a line between model specific implementations + applicable research components within a field.

Also important is having a gateway for users to where they can get such implementations; i.e Flash. Any suggestions for RL based implementations? There must be a nice open source repo for Lightning + RL.

Maintained by the Lightning Team

Callbacks

• BatchGradientVerification
• ConfusedLogitCallback
• ModuleDataMonitor
• TrainingDataMonitor
• PrintTableMetricsCallback

Datamodules

• BinaryEMNISTDataModule
• BinaryMNISTDataModule
• CIFAR10DataModule
• CityscapesDataModule
• EMNISTDataModule
• FashionMNISTDataModule
• ImagenetDataModule
• KittiDataModule
• MNISTDataModule
• SklearnDataModule
• SSLImagenetDataModule
• STL10DataModule
• VisionDataModule
• VOCDetectionDataModule

Datasets

• LightDataset
• CIFAR10
• ConcatDataset
• DummyDataset
• BinaryEMNIST
• UnlabeledImagenet
• KittiDataset
• BinaryMNIST
• CIFAR10Mixed

Optimizers

• LinearWarmupCosineAnnealingLR
• linear_warmup_decay

Deprecated (Lightning Team will not be active to fix issues here, contributions welcomed)

Callbacks

• BYOLMAWeightUpdate
• SSLOnlineEvaluator
• LatentDimInterpolator
• TensorboardGenerativeModelImageSampler
• KNNOnlineEvaluator

Datamodules

• AsynchronousLoader
• ExperienceSourceDataset
• ExperienceSource
• DiscountedExperienceSource

Losses

• iou_loss
• giou_loss
• dqn_loss
• double_dqn_loss
• per_dqn_loss
• nt_xent_loss
• CPCTask
• AmdimNCELoss
• FeatureMapContrastiveTask

Metrics

• mean (use torchmetrics)
• accuracy (use torchmetrics)
• precision_at_k (use torchmetrics)
• iou (use torchmetrics)
• giou (use torchmetrics)

Models

• AE
• VAE
• FasterRCNN
• GAN
• DCGAN
• Pix2Pix
• LinearRegression
• LogisticRegression
• AdvantageActorCritic
• DoubleDQN
• DQN
• DuelingDQN
• NoisyDQN
• PERDQN
• PPO
• Reinforce
• VanillaPolicyGradient
• AMDIM
• BYOL
• CPC_v2
• Moco_v2
• SimCLR
• SimSiam
• SwAV
• SSLEvaluator
• ImageGPT
• PixelCNN
• SemSegment
• UNet
• LitMNIST

Optimizers

• LARS

  Transforms

• RandomTranslateWithReflect

• Patchify

[SeanNaren]

cc @Borda @akihironitta @tchaton @PyTorchLightning/core-bolts

[stale[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.