scvi._settings.ScviConfig#

class scvi._settings.ScviConfig(verbosity=20, progress_bar_style='tqdm', batch_size=128, seed=None, logging_dir='./scvi_log/', dl_num_workers=0, jax_preallocate_gpu_memory=False, warnings_stacklevel=2)[source]#

Config manager for scvi-tools.

Examples

To set the seed

>>> scvi.settings.seed = 1

To set the batch size for functions like SCVI.get_latent_representation

>>> scvi.settings.batch_size = 1024

To set the progress bar style, choose one of “rich”, “tqdm”

>>> scvi.settings.progress_bar_style = "rich"

To set the verbosity

>>> import logging
>>> scvi.settings.verbosity = logging.INFO

To set the number of threads PyTorch will use

>>> scvi.settings.num_threads = 2

To prevent Jax from preallocating GPU memory on start (default)

>>> scvi.settings.jax_preallocate_gpu_memory = False

Attributes table#

batch_size

Minibatch size for loading data into the model.

dl_num_workers

Number of workers for PyTorch data loaders (Default is 0).

jax_preallocate_gpu_memory

Jax GPU memory allocation settings.

logging_dir

Directory for training logs (default './scvi_log/').

num_threads

Number of threads PyTorch will use.

progress_bar_style

Library to use for progress bar.

seed

Random seed for torch and numpy.

verbosity

Verbosity level (default logging.INFO).

warnings_stacklevel

Stacklevel for warnings.

Methods table#

reset_logging_handler()

Resets "scvi" log handler to a basic RichHandler().

Attributes#

ScviConfig.batch_size[source]#

Minibatch size for loading data into the model.

This is only used after a model is trained. Trainers have specific batch_size parameters.

ScviConfig.dl_num_workers[source]#

Number of workers for PyTorch data loaders (Default is 0).

ScviConfig.jax_preallocate_gpu_memory[source]#

Jax GPU memory allocation settings.

If False, Jax will ony preallocate GPU memory it needs. If float in (0, 1), Jax will preallocate GPU memory to that fraction of the GPU memory.

ScviConfig.logging_dir[source]#

Directory for training logs (default ‘./scvi_log/’).

ScviConfig.num_threads[source]#

Number of threads PyTorch will use.

ScviConfig.progress_bar_style[source]#

Library to use for progress bar.

ScviConfig.seed[source]#

Random seed for torch and numpy.

ScviConfig.verbosity[source]#

Verbosity level (default logging.INFO).

ScviConfig.warnings_stacklevel[source]#

Stacklevel for warnings.

Methods#

ScviConfig.reset_logging_handler()[source]#

Resets “scvi” log handler to a basic RichHandler().

This is useful if piping outputs to a file.