deepxde.utils

deepxde.utils.external module

External utilities.

class deepxde.utils.external.PointSet(points)[source]

Bases: object

A set of points.

Parameters:

points – A NumPy array of shape (N, dx). A list of dx-dim points.

inside(x)[source]

Returns True if x is in this set of points, otherwise, returns False.

Parameters:

x – A NumPy array. A single point, or a list of points.

Returns:

If x is a single point, returns True or False. If x is a list of

points, returns a list of True or False.

values_to_func(values, default_value=0)[source]

Convert the pairs of points and values to a callable function.

Parameters:
  • values – A NumPy array of shape (N, dy). values[i] is the dy-dim function value of the i-th point in this point set.

  • default_value (float) – The function value of the points not in this point set.

Returns:

A callable function. The input of this function should be a NumPy array of

shape (?, dx).

deepxde.utils.external.apply(func, args=None, kwds=None)[source]

Launch a new process to call the function.

This can be used to clear Tensorflow GPU memory after model execution: https://stackoverflow.com/questions/39758094/clearing-tensorflow-gpu-memory-after-model-execution

deepxde.utils.external.dat_to_csv(dat_file_path, csv_file_path, columns)[source]

Converts a dat file to CSV format and saves it.

Parameters:
  • dat_file_path (string) – Path of the dat file.

  • csv_file_path (string) – Desired path of the CSV file.

  • columns (list) – Column names to be added in the CSV file.

deepxde.utils.external.isclose(a, b)[source]

A modified version of np.isclose for DeepXDE.

This function changes the value of atol due to the dtype of a and b. If the dtype is float16, atol is 1e-4. If it is float32, atol is 1e-6. Otherwise (for float64), the default is 1e-8. If you want to manually set atol for some reason, use np.isclose instead.

Parameters:
  • a (array like) – Input arrays to compare.

  • b (array like) – Input arrays to compare.

deepxde.utils.external.plot_best_state(train_state)[source]

Plot the best result of the smallest training loss.

This function only works for 1D and 2D problems. For other problems and to better customize the figure, use save_best_state().

Note

You need to call plt.show() to show the figure.

Parameters:

train_stateTrainState instance. The second variable returned from Model.train().

deepxde.utils.external.plot_loss_history(loss_history, fname=None)[source]

Plot the training and testing loss history.

Note

You need to call plt.show() to show the figure.

Parameters:
  • loss_historyLossHistory instance. The first variable returned from Model.train().

  • fname (string) – If fname is a string (e.g., ‘loss_history.png’), then save the figure to the file of the file name fname.

deepxde.utils.external.save_best_state(train_state, fname_train, fname_test)[source]

Save the best result of the smallest training loss to a file.

deepxde.utils.external.save_loss_history(loss_history, fname)[source]

Save the training and testing loss history to a file.

deepxde.utils.external.saveplot(loss_history, train_state, issave=True, isplot=True, loss_fname='loss.dat', train_fname='train.dat', test_fname='test.dat', output_dir=None)[source]

Save/plot the loss history and best trained result.

This function is used to quickly check your results. To better investigate your result, use save_loss_history() and save_best_state().

Parameters:
  • loss_historyLossHistory instance. The first variable returned from Model.train().

  • train_stateTrainState instance. The second variable returned from Model.train().

  • issave (bool) – Set True (default) to save the loss, training points, and testing points.

  • isplot (bool) – Set True (default) to plot loss, metric, and the predicted solution.

  • loss_fname (string) – Name of the file to save the loss in.

  • train_fname (string) – Name of the file to save the training points in.

  • test_fname (string) – Name of the file to save the testing points in.

  • output_dir (string) – If None, use the current working directory.

deepxde.utils.external.standardize(X_train, X_test)[source]

Standardize features by removing the mean and scaling to unit variance.

The mean and std are computed from the training data X_train using sklearn.preprocessing.StandardScaler, and then applied to the testing data X_test.

Parameters:
  • X_train – A NumPy array of shape (n_samples, n_features). The data used to compute the mean and standard deviation used for later scaling along the features axis.

  • X_test – A NumPy array.

Returns:

Instance of sklearn.preprocessing.StandardScaler. X_train: Transformed training data. X_test: Transformed testing data.

Return type:

scaler

deepxde.utils.external.uniformly_continuous_delta(X, Y, eps)[source]

Compute the supremum of delta in uniformly continuous.

Parameters:

X – N x d, equispaced points.