# Training

*Avalanche* offers significant support for *training* (with *templates*, *strategies* and *plug-ins*). Here you can find a list of **examples** related to the training and some strategies available in Avalanche (each strategy reproduces original paper results in the [CL-Baselines](https://github.com/ContinualAI/continual-learning-baselines) repository: 

* [Joint-Training](https://github.com/ContinualAI/avalanche/blob/master/examples/joint_training.py): *this example shows how to take a stream of experiences and train simultaneously on all of them. This is useful to implement the "offline"  or "multi-task" upper bound.*
* [Replay strategy](https://github.com/ContinualAI/avalanche/blob/master/examples/replay.py)*: simple example on the usage of replay in Avalanche.*
* [AR1 strategy](https://github.com/ContinualAI/avalanche/blob/master/examples/ar1.py): t*his is a simple example on how to use the AR1 strategy.*
* [CoPE Strategy](https://github.com/ContinualAI/avalanche/blob/master/examples/cope.py): *this is a simple example on how to use the CoPE plugin. It's an example in the online data incremental setting, where both learning and evaluation is completely task-agnostic.*
* [Cumulative Strategy](https://github.com/ContinualAI/avalanche/blob/master/examples/dataloader.py): h*ow to define your own cumulative strategy based on the different Data Loaders made available in Avalanche.* 
* [Deep SLDA](https://github.com/ContinualAI/avalanche/blob/master/examples/deep_slda.py)*: this is a simple example on how to use the Deep SLDA strategy.*
* [Early Stopping](https://github.com/ContinualAI/avalanche/blob/master/examples/all_mnist_early_stopping.py): *this example shows how to use early stopping to dynamically stop the training procedure when the model converged instead of training for a fixed number of epochs.*
* [Object Detection](https://github.com/ContinualAI/avalanche/blob/master/examples/detection.py): *this example shows how to run object detection/segmentation tasks.*
* [Object Detection with Elvis](https://github.com/ContinualAI/avalanche/blob/master/examples/detection_lvis.py)*: this example shows how to run object detection/segmentation tasks with a* *toy benchmark based on the LVIS dataset.*
* [Object Detection Training](https://github.com/ContinualAI/avalanche/tree/master/examples/tvdetection): *set of examples showing how you can use Avalanche for distributed training of object detector.*
* [EWC on MNIST](https://github.com/ContinualAI/avalanche/blob/master/examples/ewc_mnist.py)*: this example tests EWC on Split MNIST and Permuted MNIST.*
* [LWF on MNIST](https://github.com/ContinualAI/avalanche/blob/master/examples/lfl_mnist.py)*: this example tests LWF on Permuted MNIST.*
* [GEM and A-GEM on MNIST](https://github.com/ContinualAI/avalanche/blob/master/examples/gem_agem_mnist.py)*: this example shows how to use GEM and A-GEM strategies on MNIST.*
* [Ex-Model Continual Learning](https://github.com/ContinualAI/avalanche/blob/master/examples/ex_model_cl.py)*: this example shows how to create a stream of pre-trained model from which to learn.*
* [Generative Replay](https://github.com/ContinualAI/avalanche/blob/master/examples/generative_replay_MNIST_generator.py)*: this is a simple example on how to implement generative replay in Avalanche.*
* [iCARL strategy](https://github.com/ContinualAI/avalanche/blob/master/examples/icarl.py): *simple example to show how to use the iCARL strategy.*
* [LaMAML strategy](https://github.com/ContinualAI/avalanche/blob/master/examples/lamaml_cifar100.py)*: example on how to use a meta continual learning in Avalanche.*
* [RWalk strategy](https://github.com/ContinualAI/avalanche/blob/master/examples/rwalk_mnist.py): *example of the RWalk strategy usage.*
* [Online Naive](https://github.com/ContinualAI/avalanche/blob/6dbabb2ab787a53b59b9cbcb245ad500e984f671/examples/online_naive.py): *example to run a naive strategy in an online setting.*
* [Synaptic Intelligence](https://github.com/ContinualAI/avalanche/blob/master/examples/synaptic_intelligence.py): *this is a simple example on how to use the Synaptic Intelligence Plugin.*
* [Continual Sequence Classification](https://github.com/ContinualAI/avalanche/blob/master/examples/continual_sequence_classification.py): *sequence classification example using torchaudio and Speech Commands.*