DeepXDE v1.14.0

Areas of improvement

• dde.gradients supports 3D outputs
• Support MAE for all backends
• Backend PyTorch: Add L1 and L1+L2 regularizers
• Backend PyTorch: DeepONet supports regularization
• Backend Pytorch: Add Apple MPS GPU support
• Backend JAX: FNN supports regularization
• Backend JAX: Fix external variable initialization

New APIs

• Support mixed precision

Thanks to all the contributors to this release!

@g-w1 @lululxvi @Jerry-Jzy @KangyuWeng @vl-dud @bonneted @kyouma

DeepXDE v1.13.2

Areas of improvement

• Backend paddle: Support dde.nn.MfNN
• Backend paddle: Support prim to accelerate running

Thanks to all the contributors to this release!

@lijialin03 @KangyuWeng @kuangdai @bonneted

DeepXDE v1.13.1

This is a bugfix release, fixing the bug of dde.data.PDEOperatorCartesianProd introduced in v1.13.0.

We also support Python 3.12 and require PyTorch>=2.0.0.

Thanks to all the contributors to this release!

@lululxvi @Jerry-Jzy

DeepXDE v1.13.0

Areas of improvement

• Refactor and improve regularizers for backends TensorFlow 1.x/2.x and paddle
• Improve compatibility with NumPy 2
• dde.model.train and dde.model.compile support verbose
• Backend PyTorch: Fix L2 regularizers for external_trainable_variables
• Backend paddle: FNN supports regularization and dropout

New APIs

• Backend PyTorch: Add a new optimizer NNCG

Thanks to all the contributors to this release!

@lululxvi @vl-dud @KangyuWeng @pratikrathore8 @lijialin03 @Jerry-Jzy

DeepXDE v1.12.2

Areas of improvement

• Improve compatibility with NumPy 2
• Bug fix: dde.data.QuadrupleCartesianProd
• Backend TensorFlow 1.x: Improve DeepONet
• Backend PyTorch: FNN supports regularization

Thanks to all the contributors to this release!

@anranjiao @cwoolfo1 @vl-dud @enigne @lululxvi

DeepXDE v1.12.1

Areas of improvement

• Add clear() for forward-mode autodiff to prevent memory leak
• Tensorflow 1.x backend: DeepONet supports layer-by-layer dropout rate setting
• Bug fix: SingleOutputStrategy has unnecessary error checking

New APIs

• dde.geometry.Hypercube supports uniform_boundary_points

Thanks to all the contributors to this release!

@vl-dud @Yiii9 @MinZhu123 @lululxvi @HydrogenSulfate

DeepXDE v1.12.0

Areas of improvement

• EarlyStopping callback supports a new argument start_from_epoch
• Backend TensorFlow v1/v2: Fix many codes to match the new TensorFlow APIs and Keras 3
• Backend Tensorflow v1: DeepONet and DeepONetCartesianProd support dropout
• Backend PyTorch: Fix the L-BFGS code to support PyTorch 2.x
• Backend Paddle: Fix the L-BFGS code
• Backend Paddle: DeepONetCartesianProd supports multiple outputs
• Backend JAX: Support callback VariableValue
• Documentation improvements

New APIs

• dde.data.PDEOperator supports resample_train_points

Thanks to all the contributors to this release!

@bonneted @vnikoofard @vl-dud @tjboise @HydrogenSulfate @agniv-the-marker @lululxvi @lijialin03 @DecoderLiu @anranjiao

DeepXDE v1.11.1

Areas of improvement

• Add 2D interface boundary condition dde.icbc.Interface2DBC
• Backend JAX: Support loss weights
• Backend JAX: Support dde.nn.PFNN
• Backend JAX: Support dde.callbacks.OperatorPredictor
• Backend JAX: Fix input and output transform
• Add new examples in docs

Thanks to all the contributors to this release!

@lululxvi @kuangdai @HydrogenSulfate @bonneted @jdellag @vl-dud @SebastianCobaise

DeepXDE v1.11.0

• DeepXDE stops the support of Python 3.8 from this release.
• Many exciting new functions of automatic differentiation (AD) are added.

Areas of improvement

• dde.grad supports forward-mode AD for backends TensorFlow 1.x and 2.x, PyTorch, JAX. Use dde.config.set_default_autodiff to select.
• dde.grad.jacobian allows both i and j are None
• Backend PyTorch: DeepONet supports multiple outputs

New APIs

• Support new AD method in dde.zcs: Zero Coordinate Shift (ZCS), see https://arxiv.org/abs/2311.00860

DeepXDE v1.10.1

Areas of improvement

• Refactor dde.grad module
• Backend TensorFlow 1.x and 2.x: DeepONet & DeepONetCartesianProd support multiple outputs
• Backend TensorFlow: Add regularization to DeepONet
• Backend PyTorch: Bug fix of MIONet input_transform
• Backend JAX: Support more PINN examples
• Backend JAX: Bug fix of dde.grad