In [ ]:

from fastai.vision import *   # Quick access to computer vision functionality

Vision example¶

Images can be in labeled folders, or a single folder with a CSV.

In [ ]:

path = untar_data(URLs.MNIST_SAMPLE)
path

Out[ ]:

PosixPath('/home/ubuntu/.fastai/data/mnist_sample')

Create a DataBunch, optionally with transforms:

In [ ]:

data = ImageDataBunch.from_folder(path, ds_tfms=(rand_pad(2, 28), []), bs=64)
data.normalize(imagenet_stats)
img,label = data.train_ds[0]
img

Out[ ]:

Create and fit a Learner:

In [ ]:

learn = create_cnn(data, models.resnet18, metrics=accuracy)
learn.fit_one_cycle(1, 0.01)

Total time: 00:05

epoch	train_loss	valid_loss	accuracy
1	0.047818	0.012341	0.997056

In [ ]:

accuracy(*learn.get_preds())

Out[ ]:

tensor(0.9971)

Same as above, using CSV instead of folder name for labels

In [ ]:

data = ImageDataBunch.from_csv(path, ds_tfms=(rand_pad(2, 28), []), bs=64)
data.normalize(imagenet_stats)
img,label = data.train_ds[0]
img

Out[ ]:

In [ ]:

learn = create_cnn(data, models.resnet18, metrics=accuracy)
learn.fit_one_cycle(1, 0.01)

Total time: 00:04

epoch	train_loss	valid_loss	accuracy
1	0.056097	0.014536	0.994802