Utility

A collection of utility methods.

---

source

free_gpu_memory

 free_gpu_memory (learn:fastai.learner.Learner,
                  dls:fastai.data.core.DataLoaders=None)

Frees GPU memory using gc.collect and torch.cuda.empty_cache

---

source

less_random

 less_random (seed:int=42, deterministic:Optional[bool]=None,
              benchmark:Optional[bool]=None)

Stores and retrieves state of random number generators. Sets random seed for random, torch, and numpy.

Does not set torch.backends.cudnn.benchmark or torch.backends.cudnn.deterministic by default.

	Type	Default	Details
seed	int	42	Seed for random, torch, and numpy
deterministic	bool | None	None	Set torch.backends.cudnn.deterministic if not None
benchmark	bool | None	None	Set torch.backends.cudnn.benchmark if not None

A random state manager which provides some reproducibility without sacrificing potential training speed.

Unlike fastai.torch_core.no_random, less_random does not set torch.backends.cudnn.benchmark or torch.backends.cudnn.deterministic by default.

less_random training runs on the same GPU, PyTorch, & Cuda setup should be close to no_random reproducibility, but different hardware/software setup will have less reproducibility than using no_random.

---

source

scale_time

 scale_time (val:float, spec:str='#0.4G')

Scale fractional second time values and return formatted to spec

---

source

pil_to_numpy

 pil_to_numpy (img:PIL.Image.Image)

Fast conversion of Pillow Image to NumPy NDArray

---

source

convert_to_int

 convert_to_int (s)