Image transforms¶

fastai provides a complete image transformation library written from scratch in PyTorch. Although the main purpose of the library is for data augmentation when training computer vision models, you can also use it for more general image transformation purposes. Before we get in to the detail of the full API, we'll look at a quick overview of the data augmentation pieces that you'll almost certainly need to use.

Data augmentation¶

Data augmentation is perhaps the most important regularization technique when training a model for Computer Vision: instead of feeding the model with the same pictures every time, we do small random transformations (a bit of rotation, zoom, translation, etc...) that don't change what's inside the image (for the human eye) but change its pixel values. Models trained with data augmentation will then generalize better.

To get a set of transforms with default values that work pretty well in a wide range of tasks, it's often easiest to use get_transforms. Depending on the nature of the images in your data, you may want to adjust a few arguments, the most important being:

• do_flip: if True the image is randomly flipped (default beheavior)
• flip_vert: limit the flips to horizontal flips (when False) or to horizontal and vertical flips as well as 90-degrees rotations (when True)

get_transforms returns a tuple of two list of transforms: one for the training set and one for the validation set (we don't want to modify the pictures in the validation set, so the second list of transforms is limited to resizing the pictures). This can be then passed directly to define a DataBunch object (see below) which is then associated with a model to begin training.

Note that the defaults got get_transforms are generally pretty good for regular photos - although here we'll add a bit of extra rotation so it's easier to see the differences.

We first define here a function to return a new image, since transformation functions modify their inputs. We also define a little helper function plots_f to let us output a grid of transformed images based on a function - the details of this function aren't important here.

If we want to have a look at what this transforms actually do, we need to use the apply_tfms function. It will be in charge of picking the values of the random parameters and doing the transformation to the Image object. This function has multiple arguments you can customize (see its documentation for details), we will highlight here the most useful. The first one we'll need to set, especially if our images are of different shapes, is the target size. It will ensure all the images are cropped or padded to the same size so we can then collate them into batches.

Note that the target size can be a rectangle if you specify a tuple of int (height by width).

The second argument that can be customized is how we treat missing pixels: when applying transforms (like a rotation), some of the pixels inside the square won't have values from the image. We can set missing pixels to one of the following:

• black (padding_mode='zeros')
• the value of the pixel at the nearest border (padding_mode='border')
• the value of the pixel symmetric to the nearest border (padding_mode='reflection')

padding_mode='reflection' is the default. Here is what padding_mode='zeros' looks like:

And here is what padding_mode='border' looks like:

The third argument that might be useful to change is do_crop. Images are often rectangles of different ratios, so to get them to the target size, we can either take a random crop from the result of our transforms (do_crop = True, which is the default behavior), or add padding on the side(s) that needs to get bigger by specifying a value for padding_mode.

Here are the images with do_crop=False.

You can also decide how your images are put to the final size by specifying a resize_method. By default, the library resize the image while keeping its original ratio so that the smaller size corresponds to the given size, then takes a crop (ResizeMethod.CROP). You can choose to resize the image while keeping its original ratio so that the bigger size corresponds to the given size, then take a pad (ResizeeMethod.PAD). Another way is to just squish the image to the given size (ResizeeMethod.SQUISH).

Data augmentation details¶

If you want to quickly get a set of random transforms that have proved to work well in a wide range of tasks, you should use the get_transforms function. The most important parameters to adjust are do_flip and flip_vert, depending on the type of images you have.

This function returns a tuple of two list of transforms, one for the training set and the other for the validation set (which is limited to a center crop by default.

Let's see how get_transforms changes this little kitten now.

Another useful function that gives basic transforms is zoom_crop:

scale should be a given float if do_rand is false, otherwise it can be a range of floats (and the zoom will have a random value inbetween). Again, here is a sense of what this can give us.

This transform is an implementation of the main approach used for nearly all winning Imagenet entries since 2013, based on Andrew Howard's Some Improvements on Deep Convolutional Neural Network Based Image Classification. It determines a new width and height of the image after the random scale and squish to the new ratio are applied. Those are switched with probability 0.5. Then we return the part of the image with the width and height computed, centered in row_pct, col_pct if width and height are both less than the corresponding size of the image. Otherwise we try again with new random parameters.

Randomness¶

The functions that define each transform, such as rotateor flip_lr are deterministic. The fastai library will then randomize them in two different ways:

• each transform can be defined with an argument named p representing the probability for it to be applied
• each argument that is type-annoted with a random function (like uniform or rand_bool) can be replaced by a tuple of arguments accepted by this function, and on each call of the transform, the argument that is passed inside the function will be picked randomly using that random function.

If we look at the function rotate for instance, we see it had an argument degrees that is type-annotated as uniform.

First level of randomness: We can define a transform using rotate with degrees fixed to a value, but by passing an argument p. The rotation will then be executed with a probability of p but always with the same value of degrees.

Second level of randomness: We can define a transform using rotate with degrees defined as a range, without an argument p. The rotation will then always be executed with a random value picked uniformly between the two floats we put in degrees.

All combined: We can define a transform using rotate with degrees defined as a range, and an argument p. The rotation will then always be executed with a probability p and a random value picked uniformly between the two floats we put in degrees.

List of transforms¶

Here is the list of all the deterministic functions on which the transforms are built. As explained before, each of those can have a probability p of being executed, and any time an argument is type-annotated with a random function, it's possible to randomize it via that function.

This transform adjusts the brightness of the image depending on the value in change. A change of 0 will transform the image to black and a change of 1 will transform the image to white. change=0.5 doesn't do adjust the brightness.

scale adjusts the contrast. A scale of 0 will transform the image to grey and a scale over 1 will transform the picture to super-contrast. scale = 1. doesn't adjust the contrast.

This transform takes a crop of the image to return one of the given size. The position is given by (col_pct, row_pct), with col_pct and row_pct being normalized between 0. and 1.

This works like crop but if the target size is bigger than the size of the image (on either dimension), padding is applied according to padding_mode (see pad for an example of all the options) and the position of center is ignored on that dimension.

This transform applies combines a flip (horizontal or vertical) and a rotation of a multiple of 90 degrees.

This is an affine implementation of dihedral that should be used if the target is an ImagePoints or an ImageBBox.

This transform horizontally flips the image. flip_lr mirrors the image.

This is an affine implementation of flip_lr that should be used if the target is an ImagePoints or an ImageBBox.

This transform changes the pixels of the image by randomly replacing them with pixels from the neighborhood (how far the neighborhood extends is controlled by the value of magnitude).

Pads the image by adding padding pixel on each side of the picture accordin to mode:

• mode = zeros - pads with zeros,
• mode = border - repeats the pixels at the border.
• mode = reflection - pads by taking the pixels symmetric to the border.

Perspective warping is a deformation of the image as seen in a different plane of the 3D-plane. The new plane is determined by telling where we want each of the four corners of the image (from -1 to 1, -1 being left/top, 1 being right/bottom).

Apply the four tilts at the same time, each with a strength given in the vector magnitude. See tilt just below for the effect of each individual tilt.

Tilts c in the direction given (0: left, 1: right, 2: top, 3: bottom) with a certain magnitude. A positive number is a tilt forward (toward the person looking at the picture), a negative number a tilt backward.

Convenience functions¶

These functions simplify creating random versions of crop_pad and zoom.

Undocumented Methods - Methods moved below this line will intentionally be hidden¶

New Methods - Please document or move to the undocumented section¶