from fastai.basics import *
from fastai.tabular.all import *
from fastai.callback.all import *
from fastai.distributed import *
from fastprogress import fastprogress
from fastai.callback.mixup import *
from fastscript import *

torch.backends.cudnn.benchmark = True
fastprogress.MAX_COLS = 80

get_dls[source]

get_dls(bs=64)

dls = get_dls()

dls.show_batch()

	workclass	education	marital-status	occupation	relationship	race	education-num_na	age	fnlwgt	education-num	salary
0	State-gov	11th	Married-civ-spouse	Adm-clerical	Husband	White	False	49.000000	203039.000250	7.0	<50k
1	Private	Masters	Never-married	Exec-managerial	Not-in-family	White	False	42.000000	210524.999580	14.0	<50k
2	Private	Assoc-acdm	Married-civ-spouse	Prof-specialty	Wife	White	False	48.000000	313924.993803	12.0	>=50k
3	Private	Bachelors	Married-civ-spouse	Protective-serv	Husband	Black	False	33.000000	247205.000913	13.0	<50k
4	Private	1st-4th	Widowed	Handlers-cleaners	Not-in-family	White	False	60.999999	668362.024904	2.0	<50k
5	Private	HS-grad	Married-spouse-absent	Other-service	Unmarried	Black	False	45.000000	234698.998742	9.0	>=50k
6	Private	Prof-school	Married-civ-spouse	Prof-specialty	Husband	Asian-Pac-Islander	False	59.000000	122283.001076	15.0	>=50k
7	Self-emp-not-inc	HS-grad	Married-civ-spouse	Other-service	Husband	White	False	38.000000	184455.999875	9.0	<50k
8	Local-gov	Masters	Never-married	Prof-specialty	Own-child	White	False	25.000000	276249.001345	14.0	<50k
9	Private	HS-grad	Married-civ-spouse	Transport-moving	Husband	White	False	60.000001	85412.997963	9.0	>=50k

train[source]

train(gpu=None, bs=64, epochs=5, fp16=0, dump=0, runs=1)

Training of Tabular data 'ADULT_SAMPLE'.

train_tabular[source]

train_tabular(gpu=None, bs=64, fp16=0, epochs=5, runs=1)