Posit AI Weblog: lime v0.4: The Kitten Image Version


I’m completely satisfied to report a brand new main launch of lime has landed on CRAN. lime is
an R port of the Python library of the identical title by Marco Ribeiro that permits
the person to pry open black field machine studying fashions and clarify their
outcomes on a per-observation foundation. It really works by modelling the end result of the
black field within the native neighborhood across the commentary to clarify and utilizing
this native mannequin to clarify why (not how) the black field did what it did. For
extra details about the idea of lime I’ll direct you to the article
introducing the methodology.

New options

The meat of this launch facilities round two new options which are considerably
linked: Native help for keras fashions and help for explaining picture fashions.

keras and pictures

J.J. Allaire was type sufficient to namedrop lime throughout his keynote introduction
of the tensorflow and keras packages and I felt compelled to help them
natively. As keras is by far the most well-liked technique to interface with tensorflow
it’s first in line for build-in help. The addition of keras implies that
lime now straight helps fashions from the next packages:

In the event you’re engaged on one thing too obscure or innovative to not be capable to use
these packages it’s nonetheless attainable to make your mannequin lime compliant by
offering predict_model() and model_type() strategies for it.

keras fashions are used identical to every other mannequin, by passing it into the lime()
perform together with the coaching knowledge with a purpose to create an explainer object.
As a result of we’re quickly going to speak about picture fashions, we’ll be utilizing one of many
pre-trained ImageNet fashions that’s obtainable from keras itself:

Layer (sort)                              Output Form                         Param #        
input_1 (InputLayer)                      (None, 224, 224, 3)                  0              
block1_conv1 (Conv2D)                     (None, 224, 224, 64)                 1792           
block1_conv2 (Conv2D)                     (None, 224, 224, 64)                 36928          
block1_pool (MaxPooling2D)                (None, 112, 112, 64)                 0              
block2_conv1 (Conv2D)                     (None, 112, 112, 128)                73856          
block2_conv2 (Conv2D)                     (None, 112, 112, 128)                147584         
block2_pool (MaxPooling2D)                (None, 56, 56, 128)                  0              
block3_conv1 (Conv2D)                     (None, 56, 56, 256)                  295168         
block3_conv2 (Conv2D)                     (None, 56, 56, 256)                  590080         
block3_conv3 (Conv2D)                     (None, 56, 56, 256)                  590080         
block3_pool (MaxPooling2D)                (None, 28, 28, 256)                  0              
block4_conv1 (Conv2D)                     (None, 28, 28, 512)                  1180160        
block4_conv2 (Conv2D)                     (None, 28, 28, 512)                  2359808        
block4_conv3 (Conv2D)                     (None, 28, 28, 512)                  2359808        
block4_pool (MaxPooling2D)                (None, 14, 14, 512)                  0              
block5_conv1 (Conv2D)                     (None, 14, 14, 512)                  2359808        
block5_conv2 (Conv2D)                     (None, 14, 14, 512)                  2359808        
block5_conv3 (Conv2D)                     (None, 14, 14, 512)                  2359808        
block5_pool (MaxPooling2D)                (None, 7, 7, 512)                    0              
flatten (Flatten)                         (None, 25088)                        0              
fc1 (Dense)                               (None, 4096)                         102764544      
fc2 (Dense)                               (None, 4096)                         16781312       
predictions (Dense)                       (None, 1000)                         4097000        
Complete params: 138,357,544
Trainable params: 138,357,544
Non-trainable params: 0

The vgg16 mannequin is a picture classification mannequin that has been construct as a part of
the ImageNet competitors the place the objective is to categorise photos into 1000
classes with the very best accuracy. As we are able to see it’s pretty sophisticated.

So as to create an explainer we might want to cross within the coaching knowledge as
properly. For picture knowledge the coaching knowledge is de facto solely used to inform lime that we
are coping with a picture mannequin, so any picture will suffice. The format for the
coaching knowledge is solely the trail to the photographs, and since the web runs on
kitten photos we’ll use considered one of these:

img <- image_read('https://www.data-imaginist.com/belongings/pictures/kitten.jpg')
img_path <- file.path(tempdir(), 'kitten.jpg')
image_write(img, img_path)

As with textual content fashions the explainer might want to know how one can put together the enter
knowledge for the mannequin. For keras fashions this implies formatting the picture knowledge as
tensors. Fortunately keras comes with a variety of instruments for reshaping picture knowledge:

image_prep <- perform(x) {
  arrays <- lapply(x, perform(path) {
    img <- image_load(path, target_size = c(224,224))
    x <- image_to_array(img)
    x <- array_reshape(x, c(1, dim(x)))
    x <- imagenet_preprocess_input(x)
  do.call(abind::abind, c(arrays, list(alongside = 1)))
explainer <- lime(img_path, mannequin, image_prep)

We now have an explainer mannequin for understanding how the vgg16 neural community
makes its predictions. Earlier than we go alongside, lets see what the mannequin consider our

res <- predict(mannequin, image_prep(img_path))
  class_name class_description      rating
1  n02124075      Egyptian_cat 0.48913878
2  n02123045             tabby 0.15177219
3  n02123159         tiger_cat 0.10270492
4  n02127052              lynx 0.02638111
5  n03793489             mouse 0.00852214

So, it’s fairly positive about the entire cat factor. The explanation we have to use
imagenet_decode_predictions() is that the output of a keras mannequin is at all times
only a anonymous tensor:

[1]    1 1000

We’re used to classifiers figuring out the category labels, however this isn’t the case
for keras. Motivated by this, lime now have a technique to outline/overwrite the
class labels of a mannequin, utilizing the as_classifier() perform. Let’s redo our

model_labels <- readRDS(system.file('extdata', 'imagenet_labels.rds', package deal = 'lime'))
explainer <- lime(img_path, as_classifier(mannequin, model_labels), image_prep)

There may be additionally an as_regressor() perform which tells lime, for sure,
that the mannequin is a regression mannequin. Most fashions may be introspected to see
which kind of mannequin they’re, however neural networks doesn’t actually care. lime
guesses the mannequin sort from the activation used within the final layer (linear
activation == regression), but when that heuristic fails then
as_regressor()/as_classifier() can be utilized.

We at the moment are able to poke into the mannequin and discover out what makes it assume our
picture is of an Egyptian cat. However… first I’ll have to speak about yet one more
idea: superpixels (I promise I’ll get to the reason half in a bit).

So as to create significant permutations of our picture (bear in mind, that is the
central concept in lime), now we have to outline how to take action. The permutations wants
to be substantial sufficient to have an effect on the picture, however not a lot that
the mannequin fully fails to recognise the content material in each case – additional,
they need to result in an interpretable outcome. The idea of superpixels lends
itself properly to those constraints. In brief, a superpixel is a patch of an space
with excessive homogeneity, and superpixel segmentation is a clustering of picture
pixels into numerous superpixels. By segmenting the picture to clarify into
superpixels we are able to flip space of contextual similarity on and off throughout the
permutations and discover out if that space is vital. It’s nonetheless essential to
experiment a bit because the optimum variety of superpixels rely upon the content material of
the picture. Keep in mind, we’d like them to be massive sufficient to have an effect however not
so massive that the category chance turns into successfully binary. lime comes
with a perform to evaluate the superpixel segmentation earlier than starting the
clarification and it’s endorsed to play with it a bit — with time you’ll
doubtless get a really feel for the correct values:

# default

# Altering some settings
plot_superpixels(img_path, n_superpixels = 200, weight = 40)

The default is ready to a reasonably low variety of superpixels — if the topic of
curiosity is comparatively small it could be crucial to extend the variety of
superpixels in order that the total topic doesn’t find yourself in a single, or just a few
superpixels. The weight parameter will permit you to make the segments extra
compact by weighting spatial distance larger than color distance. For this
instance we’ll keep on with the defaults.

Bear in mind that explaining picture
fashions is way heavier than tabular or textual content knowledge. In impact it would create 1000
new pictures per clarification (default permutation measurement for pictures) and run these
by means of the mannequin. As picture classification fashions are sometimes fairly heavy, this
will end in computation time measured in minutes. The permutation is batched
(default to 10 permutations per batch), so that you shouldn’t be afraid of working
out of RAM or hard-drive house.

clarification <- clarify(img_path, explainer, n_labels = 2, n_features = 20)

The output of a picture clarification is an information body of the identical format as that
from tabular and textual content knowledge. Every characteristic will probably be a superpixel and the pixel
vary of the superpixel will probably be used as its description. Normally the reason
will solely make sense within the context of the picture itself, so the brand new model of
lime additionally comes with a plot_image_explanation() perform to do exactly that.
Let’s see what our clarification have to inform us:


We will see that the mannequin, for each the foremost predicted courses, focuses on the
cat, which is sweet since they’re each totally different cat breeds. The plot perform
bought just a few totally different features that can assist you tweak the visible, and it filters low
scoring superpixels away by default. An alternate view that places extra focus
on the related superpixels, however removes the context may be seen by utilizing
show = 'block':

plot_image_explanation(clarification, show = 'block', threshold = 0.01)

Whereas not as frequent with picture explanations it is usually attainable to have a look at the
areas of a picture that contradicts the category:

plot_image_explanation(clarification, threshold = 0, show_negative = TRUE, fill_alpha = 0.6)

As every clarification takes longer time to create and must be tweaked on a
per-image foundation, picture explanations will not be one thing that you simply’ll create in
massive batches as you would possibly do with tabular and textual content knowledge. Nonetheless, just a few
explanations would possibly permit you to perceive your mannequin higher and be used for
speaking the workings of your mannequin. Additional, because the time-limiting issue
in picture explanations are the picture classifier and never lime itself, it’s sure
to enhance as picture classifiers turns into extra performant.

Seize again

Aside from keras and picture help, a slew of different options and enhancements
have been added. Right here’s a fast overview:

  • All clarification plots now embody the match of the ridge regression used to make
    the reason. This makes it straightforward to evaluate how good the assumptions about
    native linearity are saved.
  • When explaining tabular knowledge the default distance measure is now 'gower'
    from the gower package deal. gower makes it attainable to measure distances
    between heterogeneous knowledge with out changing all options to numeric and
    experimenting with totally different exponential kernels.
  • When explaining tabular knowledge numerical options will not be sampled from
    a standard distribution throughout permutations, however from a kernel density outlined
    by the coaching knowledge. This could be certain that the permutations are extra
    consultant of the anticipated enter.

Wrapping up

This launch represents an vital milestone for lime in R. With the
addition of picture explanations the lime package deal is now on par or above its
Python relative, feature-wise. Additional improvement will give attention to enhancing the
efficiency of the mannequin, e.g. by including parallelisation or enhancing the native
mannequin definition, in addition to exploring different clarification varieties similar to

Completely happy Explaining!

Leave a Reply

Your email address will not be published. Required fields are marked *