Deep Learning Convenience Functions

This notebook contains convenience functions to aid in modeling.

calc_cs

 calc_cs (x)

Calculate nan mean and nan std of an array. Returned as list

	Details
x	numeric array

source

apply_cs

 apply_cs (xs, cs_dict_entry)

	Details
xs
cs_dict_entry	list of length 2 containing mean and s

source

reverse_cs

 reverse_cs (xs, cs_dict_entry)

Boilerplate Functions for Tian et al 2011

source

TianEtAl2011Dataset

 TianEtAl2011Dataset (y1, y2, y3, idx_original, marker_type='markers',
                      transform=None, target_transform=None,
                      use_gpu_num=0, **kwargs)

An abstract class representing a :class:Dataset.

All datasets that represent a map from keys to data samples should subclass it. All subclasses should overwrite :meth:__getitem__, supporting fetching a data sample for a given key. Subclasses could also optionally overwrite :meth:__len__, which is expected to return the size of the dataset by many :class:~torch.utils.data.Sampler implementations and the default options of :class:~torch.utils.data.DataLoader.

.. note:: :class:~torch.utils.data.DataLoader by default constructs a index sampler that yields integral indices. To make it work with a map-style dataset with non-integral indices/keys, a custom sampler must be provided.

	Type	Default	Details
y1
y2
y3			xs,
idx_original
marker_type	str	markers
transform	NoneType	None
target_transform	NoneType	None
use_gpu_num	int	0
kwargs

source

train_loop

 train_loop (dataloader, model, loss_fn, optimizer, silent=False)

source

train_error

 train_error (dataloader, model, loss_fn, silent=False)

source

test_loop

 test_loop (dataloader, model, loss_fn, silent=False)

source

train_nn

 train_nn (nb_name, training_dataloader, testing_dataloader, model,
           learning_rate=0.001, batch_size=64, epochs=500)

source

yhat_loop

 yhat_loop (dataloader, model)