Viewing inputs and outputs¶

In [ ]:

from fastai.basics import *
from fastai.gen_doc.nbdoc import *

In this tutorial, we'll see how the same API allows you to get a look at the inputs and outputs of your model, whether in the vision, text or tabular application. We'll go over a lot of different tasks and each time, grab some data in a DataBunch with the data block API, see how to get a look at a few inputs with the show_batch method, train an appropriate Learner then use the show_results method to see what the outputs of our model actually look like.

In [ ]:

jekyll_note("""As usual, this page is generated from a notebook that you can find in the docs_src folder of the
<a href="https://github.com/fastai/fastai">fastai repo</a>. The examples are all designed to run fast, which is why we use
samples of the dataset, a resnet18 as a backbone and don't train for very long. You can change all of those parameters
to run your own experiments!
""")

Note: As usual, this page is generated from a notebook that you can find in the docs_src folder of the fastai repo. The examples are all designed to run fast, which is why we use samples of the dataset, a resnet18 as a backbone and don't train for very long. You can change all of those parameters to run your own experiments!

Vision¶

To quickly get access to all the vision functions inside fastai, we use the usual import statements.

In [ ]:

from fastai.vision import *

A classification problem¶

Let's begin with our sample of the MNIST dataset.

In [ ]:

mnist = untar_data(URLs.MNIST_TINY)
tfms = get_transforms(do_flip=False)

It's set up with an imagenet structure so we use it to load our training and validation datasets, then label, transform, convert them into ImageDataBunch and finally, normalize them.

In [ ]:

data = (ImageList.from_folder(mnist)
        .split_by_folder()          
        .label_from_folder()
        .transform(tfms, size=32)
        .databunch()
        .normalize(imagenet_stats))

Once your data is properly set up in a DataBunch, we can call data.show_batch() to see what a sample of a batch looks like.

In [ ]:

data.show_batch()

Note that the images were automatically de-normalized before being showed with their labels (inferred from the names of the folder). We can specify a number of rows if the default of 5 is too big, and we can also limit the size of the figure.

In [ ]:

data.show_batch(rows=3, figsize=(4,4))

Now let's create a Learner object to train a classifier.

In [ ]:

learn = cnn_learner(data, models.resnet18, metrics=accuracy)
learn.fit_one_cycle(1,1e-2)
learn.save('mini_train')

Total time: 00:02

epoch	train_loss	valid_loss	accuracy	time
0	0.528842	0.331977	0.838340	00:02

Our model has quickly reached around 74% accuracy, now let's see its predictions on a sample of the validation set. For this, we use the show_results method.

In [ ]:

learn.show_results()

Since the validation set is usually sorted, we get only images belonging to the same class. We can then again specify a number of rows, a figure size, but also the dataset on which we want to make predictions.

In [ ]:

learn.show_results(ds_type=DatasetType.Train, rows=4, figsize=(8,10))

A multilabel problem¶

Now let's try these on the planet dataset, which is a little bit different in the sense that each image can have multiple tags (and not just one label).

In [ ]:

planet = untar_data(URLs.PLANET_TINY)
planet_tfms = get_transforms(flip_vert=True, max_lighting=0.1, max_zoom=1.05, max_warp=0.)

Here each images is labelled in a file named 'labels.csv'. We have to add 'train' as a prefix to the filenames, '.jpg' as a suffix and he labels are separated by spaces.

In [ ]:

data = (ImageList.from_csv(planet, 'labels.csv', folder='train', suffix='.jpg')
        .split_by_rand_pct()
        .label_from_df(label_delim=' ')
        .transform(planet_tfms, size=128)
        .databunch()
        .normalize(imagenet_stats))

And we can have look at our data with data.show_batch.

In [ ]:

data.show_batch(rows=2, figsize=(9,7))

Then we can then create a Learner object pretty easily and train it for a little bit.

In [ ]:

learn = cnn_learner(data, models.resnet18)
learn.fit_one_cycle(5,1e-2)
learn.save('mini_train')

Total time: 00:04

epoch	train_loss	valid_loss	time
0	0.839076	0.770665	00:01
1	0.804367	0.775014	00:00
2	0.745942	0.747781	00:00
3	0.699037	0.675334	00:00
4	0.660945	0.624810	00:00

And to see actual predictions, we just have to run learn.show_results().

In [ ]:

learn.show_results(rows=3, figsize=(12,15))

A regression example¶

For the next example, we are going to use the BIWI head pose dataset. On pictures of persons, we have to find the center of their face. For the fastai docs, we have built a small subsample of the dataset (200 images) and prepared a dictionary for the correspondance filename to center.

In [ ]:

biwi = untar_data(URLs.BIWI_SAMPLE)
fn2ctr = pickle.load(open(biwi/'centers.pkl', 'rb'))

To grab our data, we use this dictionary to label our items. We also use the PointsItemList class to have the targets be of type ImagePoints (which will make sure the data augmentation is properly applied to them). When calling transform we make sure to set tfm_y=True.

In [ ]:

data = (PointsItemList.from_folder(biwi)
        .split_by_rand_pct(seed=42)
        .label_from_func(lambda o:fn2ctr[o.name])
        .transform(get_transforms(), tfm_y=True, size=(120,160))
        .databunch()
        .normalize(imagenet_stats))

Then we can have a first look at our data with data.show_batch().

In [ ]:

data.show_batch(rows=3, figsize=(9,6))

We train our model for a little bit before using learn.show_results().

In [ ]:

learn = cnn_learner(data, models.resnet18, lin_ftrs=[100], ps=0.05)
learn.fit_one_cycle(5, 5e-2)
learn.save('mini_train')

Total time: 00:07

epoch	train_loss	valid_loss
1	0.731514	2.588722
2	1.362930	9.761332
3	1.086815	1.290175
4	0.837007	0.607458
5	0.689935	0.342040

In [ ]:

learn.show_results(rows=3)

A segmentation example¶

Now we are going to look at the camvid dataset (at least a small sample of it), where we have to predict the class of each pixel in an image. Each image in the 'images' subfolder as an equivalent in 'labels' that is its segmentations mask.

In [ ]:

camvid = untar_data(URLs.CAMVID_TINY)
path_lbl = camvid/'labels'
path_img = camvid/'images'

We read the classes in 'codes.txt' and the function maps each image filename with its corresponding mask filename.

In [ ]:

codes = np.loadtxt(camvid/'codes.txt', dtype=str)
get_y_fn = lambda x: path_lbl/f'{x.stem}_P{x.suffix}'

The data block API allows us to uickly get everything in a DataBunch and then we can have a look with show_batch.

In [ ]:

data = (SegmentationItemList.from_folder(path_img)
        .split_by_rand_pct()
        .label_from_func(get_y_fn, classes=codes)
        .transform(get_transforms(), tfm_y=True, size=128)
        .databunch(bs=16, path=camvid)
        .normalize(imagenet_stats))

In [ ]:

data.show_batch(rows=2, figsize=(7,5))

Then we train a Unet for a few epochs.

In [ ]:

jekyll_warn("This training is fairly unstable, you should use more epochs and the full dataset to get better results.")

Warning: This training is fairly unstable, you should use more epochs and the full dataset to get better results.

In [ ]:

learn = unet_learner(data, models.resnet18)
learn.fit_one_cycle(3,1e-2)
learn.save('mini_train')

Total time: 00:23

epoch	train_loss	valid_loss
1	8.229017	3.061078
2	5.269776	39.258186
3	5.350030	2.359573

In [ ]:

learn.show_results()

Text¶

Next application is text, so let's start by importing everything we'll need.

In [ ]:

from fastai.text import *

Language modelling¶

First we'll fine-tune a pretrained language model on our subset of imdb.

In [ ]:

imdb = untar_data(URLs.IMDB_SAMPLE)

In [ ]:

data_lm = (TextList.from_csv(imdb, 'texts.csv', cols='text')
                   .split_by_rand_pct()
                   .label_for_lm()
                   .databunch())
data_lm.save()

data.show_batch() will work here as well. For a language model, it shows us the beginning of each sequence of text along the batch dimension (the target being to guess the next word).

In [ ]:

data_lm.show_batch()

idx	text
0	! ! ! xxmaj finally this was directed by the guy who did xxmaj big xxmaj xxunk ? xxmaj must be a replay of xxmaj jonestown - hollywood style . xxmaj xxunk ! xxbos xxmaj this is a extremely well - made film . xxmaj the acting , script and camera - work are all first - rate . xxmaj the music is good , too , though it is
1	that happened to me with " xxmaj the xxmaj young xxmaj xxunk " . xxmaj the cover of the video box , if you can find the video , is extremely xxunk . i 'd xxunk that the two women on the cover are n't even in the film . \n \n xxmaj anyway , i was either born a decade too late to appreciate the xxunk points of
2	about " xxmaj xxunk " . xxmaj on the plus side , the visuals are xxunk and the movie looks great for it 's type . xxmaj for those who like their horror movies gory there are a few nicely executed ( no pun intended ) murder scenes . xxmaj we also get a few good suspense sequences / set - pieces . \n \n xxmaj however , there
3	and xxmaj she xxmaj kills in xxmaj xxunk , but unfortunately his good films are just xxunk amongst xxunk of crap and xxmaj devil xxmaj hunter is very much a part of the crap . i saw this film purely because i want to be able to say i 've seen everything on the xxup dpp 's list ( just two more to go ! ) , and i 'm
4	the movie was more important than the planning . xxmaj because you have a camera does not mean you should make a movie right away ... come . xxmaj everyone can make a movie , but not all will be just as good . xxmaj so a word of advice to xxmaj xxunk xxmaj west are : stop and xxunk what you want . xxmaj use your time to start

Now let's define a language model learner

In [ ]:

learn = language_model_learner(data_lm, AWD_LSTM)
learn.fit_one_cycle(2, 1e-2)
learn.save('mini_train_lm')
learn.save_encoder('mini_train_encoder')

Total time: 00:25

epoch	train_loss	valid_loss	accuracy
1	4.643319	3.866198	0.289663
2	4.367103	3.814913	0.292600

Then we can have a look at the results. It shows a certain amount of words (default 20), then the next 20 target words and the ones that were predicted.

In [ ]:

learn.show_results()

text	target	pred
xxbos xxmaj start of with the good bit : several times xxmaj xxunk talks xxmaj xxunk to his friends or	language is heard among the xxunk . xxmaj that 's a great plus , as normally xxup usa & xxup	of . a . the xxunk . xxmaj the 's why xxunk film . but the , xxunk xxmaj xxup
fact , the characters are never really developed at all . xxmaj the xxunk are xxunk , xxunk xxunk ,	the women merely xxunk beautiful . xxmaj if you go by this movie , you would think that " air	xxunk xxunk are xxunk the xxunk xxmaj the you 're to the , , you 'll n't that the xxmaj
as well ) . xxmaj peter xxunk plays the dying killer daddy and watch for funny man xxmaj xxunk xxmaj	who made me laugh more than anything in the entire film in his brief five xxunk feet ) . xxmaj	. is a laugh . than anyone else the movie film . the xxunk xxunk - . . . xxmaj
a chance . xxmaj she xxunk deserved her xxmaj oscar . \n \n xxmaj this movie is in an	in the most xxunk xxunk . xxmaj all parts xxunk , necessary and perfect . xxmaj xxunk may walk away	xxunk xxunk of of xxmaj it the of . the , interesting . xxmaj the xxmaj be away from you
xxunk ? ) , terrible cinematography , forgettable dialog , nothing funny or humorous , save the fact you just	your life for two hours , soundtrack ? , amateurish performances , uneven , disjointed , and often flat out	a time . the hours . and , xxmaj and xxunk , and acting xxunk acting and xxunk boring ,

Classification¶

Now let's see a classification example. We have to use the same vocabulary as for the language model if we want to be able to use the encoder we saved.

In [ ]:

data_clas = (TextList.from_csv(imdb, 'texts.csv', cols='text', vocab=data_lm.vocab)
                   .split_from_df(col='is_valid')
                   .label_from_df(cols='label')
                   .databunch(bs=42))

Here show_batch shows the beginning of each review with its target.

In [ ]:

data_clas.show_batch()

text	target
xxbos xxmaj raising xxmaj victor xxmaj vargas : a xxmaj review \n \n xxmaj you know , xxmaj raising xxmaj victor xxmaj vargas is like sticking your hands into a big , xxunk bowl of xxunk . xxmaj it 's warm and xxunk , but you 're not sure if it feels right . xxmaj try as i might , no matter how warm and xxunk xxmaj raising xxmaj	negative
xxbos xxup the xxup shop xxup around xxup the xxup corner is one of the xxunk and most feel - good romantic comedies ever made . xxmaj there 's just no getting around that , and it 's hard to actually put one 's feeling for this film into words . xxmaj it 's not one of those films that tries too hard , nor does it come up with	positive
xxbos xxmaj now that xxmaj xxunk ) has finished its relatively short xxmaj australian cinema run ( extremely limited xxunk screen in xxmaj xxunk , after xxunk ) , i can xxunk join both xxunk of " xxmaj at xxmaj the xxmaj movies " in taking xxmaj steven xxmaj xxunk to task . \n \n xxmaj it 's usually satisfying to watch a film director change his style /	negative
xxbos xxmaj this film sat on my xxmaj xxunk for weeks before i watched it . i xxunk a self - indulgent xxunk flick about relationships gone bad . i was wrong ; this was an xxunk xxunk into the xxunk - up xxunk of xxmaj new xxmaj xxunk . \n \n xxmaj the format is the same as xxmaj max xxmaj xxunk ' " xxmaj la xxmaj xxunk	positive
xxbos xxmaj many xxunk that this is n't just a classic due to the fact that it 's the first xxup 3d game , or even the first xxunk - up . xxmaj it 's also one of the first xxunk games , one of the xxunk definitely the first ) truly claustrophobic games , and just a pretty well - xxunk gaming experience in general . xxmaj with graphics	positive

And we can train a classifier that uses our previous encoder.

In [ ]:

learn = text_classifier_learner(data_clas, AWD_LSTM)
learn.load_encoder('mini_train_encoder')
learn.fit_one_cycle(2, slice(1e-3,1e-2))
learn.save('mini_train_clas')

Total time: 00:25

epoch	train_loss	valid_loss	accuracy
1	0.713844	0.674750	0.620000
2	0.695729	0.655419	0.645000

In [ ]:

learn.show_results()

text	target	prediction
xxbos \n \n i 'm sure things did n't exactly go the same way in the real life of xxmaj xxunk xxmaj xxunk as they did in the film adaptation of his book , xxmaj rocket xxmaj boys , but the movie " xxmaj xxunk xxmaj sky " ( an xxunk of the book 's title ) is good enough to stand alone . i have not read xxmaj	positive	positive
xxbos xxmaj to review this movie , i without any doubt would have to quote that memorable scene in xxmaj tarantino 's " xxmaj pulp xxmaj fiction " ( xxunk ) when xxmaj jules and xxmaj vincent are talking about xxmaj mia xxmaj wallace and what she does for a living . xxmaj jules tells xxmaj vincent that the " xxmaj only thing she did worthwhile was pilot " .	negative	negative
xxbos xxmaj how viewers react to this new " adaption " of xxmaj shirley xxmaj jackson 's book , which was promoted as xxup not being a remake of the original 1963 movie ( true enough ) , will be based , i suspect , on the following : those who were big fans of either the book or original movie are not going to think much of this one	negative	negative
xxbos xxmaj the trouble with the book , " xxmaj memoirs of a xxmaj xxunk " is that it had xxmaj japanese xxunk but underneath the xxunk it was all an xxmaj american man 's way of thinking . xxmaj reading the book is like watching a magnificent ballet with great music , sets , and costumes yet performed by xxunk animals dressed in those xxunk far from xxmaj japanese	negative	negative
xxbos xxmaj bonanza had a great cast of wonderful actors . xxmaj xxunk xxmaj xxunk , xxmaj pernell xxmaj whitaker , xxmaj michael xxmaj xxunk , xxmaj dan xxmaj blocker , and even xxmaj guy xxmaj williams ( as the cousin who was brought in for several episodes during 1964 to replace xxmaj adam when he was leaving the series ) . xxmaj the cast had chemistry , and they	positive	negative

Tabular¶

Last application brings us to tabular data. First let's import everything we'll need.

In [ ]:

from fastai.tabular import *

We'll use a sample of the adult dataset here. Once we read the csv file, we'll need to specify the dependant variable, the categorical variables, the continuous variables and the processors we want to use.

In [ ]:

adult = untar_data(URLs.ADULT_SAMPLE)
df = pd.read_csv(adult/'adult.csv')
dep_var = 'salary'
cat_names = ['workclass', 'education', 'marital-status', 'occupation', 'relationship', 'race', 'sex', 'native-country']
cont_names = ['education-num', 'hours-per-week', 'age', 'capital-loss', 'fnlwgt', 'capital-gain']
procs = [FillMissing, Categorify, Normalize]

Then we can use the data block API to grab everything together before using data.show_batch()

In [ ]:

data = (TabularList.from_df(df, path=adult, cat_names=cat_names, cont_names=cont_names, procs=procs)
                           .split_by_idx(valid_idx=range(800,1000))
                           .label_from_df(cols=dep_var)
                           .databunch())

In [ ]:

data.show_batch()

workclass	education	marital-status	occupation	relationship	race	sex	native-country	education-num_na	education-num	hours-per-week	age	capital-loss	fnlwgt	capital-gain	target
Private	Some-college	Never-married	Other-service	Own-child	White	Female	United-States	False	-0.0312	-2.9515	-1.4357	-0.2164	-1.5321	-0.1459	<50k
Private	Some-college	Married-civ-spouse	Transport-moving	Husband	White	Male	United-States	False	-0.0312	-0.0356	0.5434	-0.2164	-1.4779	0.2731	>=50k
Self-emp-not-inc	Bachelors	Married-civ-spouse	Exec-managerial	Husband	White	Male	United-States	False	1.1422	1.5843	0.2502	-0.2164	-0.8355	-0.1459	>=50k
Private	HS-grad	Married-civ-spouse	Craft-repair	Husband	White	Male	United-States	False	-0.4224	-0.0356	0.8365	-0.2164	-1.4989	-0.1459	>=50k
Private	HS-grad	Divorced	Machine-op-inspct	Not-in-family	White	Male	United-States	False	-0.4224	-0.0356	-0.4095	-0.2164	-0.5707	-0.1459	<50k

Here we grab a tabular_learner that we train for a little bit.

In [ ]:

learn = tabular_learner(data, layers=[200,100], metrics=accuracy)
learn.fit(5, 1e-2)
learn.save('mini_train')

Total time: 00:19

epoch	train_loss	valid_loss	accuracy
1	0.336497	0.354954	0.840000
2	0.322417	0.356564	0.815000
3	0.316230	0.340134	0.850000
4	0.313944	0.354506	0.835000
5	0.330136	0.341288	0.850000

And we can use learn.show_results().

In [ ]:

learn.show_results()

workclass	education	marital-status	occupation	relationship	race	sex	native-country	education-num_na	education-num	hours-per-week	age	capital-loss	fnlwgt	capital-gain	target	prediction
Private	Some-college	Divorced	Handlers-cleaners	Unmarried	White	Female	United-States	True	-0.0312	-0.0356	0.4701	-0.2164	-0.8793	-0.1459	<50k	<50k
Self-emp-inc	Prof-school	Married-civ-spouse	Prof-specialty	Husband	White	Male	United-States	True	-0.0312	1.5843	0.5434	-0.2164	0.0290	1.8829	>=50k	>=50k
Private	Assoc-voc	Divorced	#na#	Not-in-family	White	Male	United-States	True	-0.0312	-0.1976	-0.1896	-0.2164	1.7704	-0.1459	<50k	<50k
Federal-gov	Bachelors	Never-married	Tech-support	Not-in-family	White	Male	United-States	True	-0.0312	0.3694	-0.9959	-0.2164	-1.3242	-0.1459	<50k	<50k
Private	Bachelors	Married-civ-spouse	#na#	Husband	White	Male	United-States	True	-0.0312	-0.0356	-0.1163	-0.2164	-0.2389	-0.1459	<50k	<50k