In [ ]:

import fastai
from fastai import *          # Quick access to most common functionality
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('/data1/jhoward/git/fastai/fastai/../data/mnist_sample')

Image folder version¶

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)

VBox(children=(HBox(children=(IntProgress(value=0, max=1), HTML(value='0.00% [0/1 00:00<00:00]'))), HTML(value…

Total time: 00:04
epoch  train loss  valid loss  accuracy
0      0.053222    0.013478    0.996565  (00:04)

In [ ]:

accuracy(*learn.get_preds())

HBox(children=(IntProgress(value=0, max=16), HTML(value='')))

HBox(children=(IntProgress(value=0, max=16), HTML(value='0.00% [0/16 00:00<00:00]')))

Out[ ]:

tensor(0.9966)

CSV version¶

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)

VBox(children=(HBox(children=(IntProgress(value=0, max=1), HTML(value='0.00% [0/1 00:00<00:00]'))), HTML(value…

Total time: 00:06
epoch  train loss  valid loss  accuracy
0      0.047875    0.014735    0.995466  (00:06)

In [ ]: