Basic training functionality¶

basic_train wraps together the data (in a DataBunch object) with a pytorch model to define a Learner object. This is where the basic training loop is defined for the fit function. The Learner object is the entry point of most of the Callback functions that will customize this training loop in different ways (and made available through the train module), notably:

• Learner.lr_find will launch an LR range test that will help you select a good learning rate
• Learner.fit_one_cycle will launch a training using the 1cycle policy, to help you train your model fast.
• Learner.to_fp16 will convert your model in half precision and help you launch a training in mixed precision.

The main purpose of Learner is to train model using Learner.fit. After every epoch, all metrics will be printed, and will also be available to callbacks.

The default weight decay will be wd, which will be handled using the method from Fixing Weight Decay Regularization in Adam if true_wd is set (otherwise it's L2 regularization). If bn_wd is False then weight decay will be removed from batchnorm layers, as recommended in Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour. You can ensure that batchnorm layer learnable params are trained even for frozen layer groups, by enabling train_bn.

To use discriminative layer training pass an nn.Module for each layer group to be optimized with different settings.

Any model files created will be saved in path/model_dir.

You can pass a list of callbacks that you have already created, or (more commonly) simply pass a list of callback functions to callback_fns and each function will be called (passing self) on object initialization, with the results stored as callback objects. For a walk-through, see the training overview page. You may also want to use an application to fit your model, e.g. using the create_cnn method:

Model fitting methods¶

Uses discriminative layer training if multiple learning rates or weight decay values are passed. To control training behaviour, use the callback system or one or more of the pre-defined callbacks.

Uses the OneCycleScheduler callback.

Runs the learning rate finder defined in LRFinder, as discussed in Cyclical Learning Rates for Training Neural Networks.

See results¶

Model summary¶

Test time augmentation¶

Applies Test Time Augmentation to learn on the dataset ds_type. We take the average of our regular predictions (with a weight beta) with the average of predictions obtained thourh augmented versions of the training set (with a weight 1-beta). The transforms decided for the training set are applied with a few changes scale controls the scale for zoom (which isn't random), the cropping isn't random but we make sure to get the four corners of the image. Flipping isn't random but applied once on each of those corner images (so that makes 8 augmented versions total).

Gradient clipping¶

Mixed precision training¶

Uses the MixedPrecision callback to train in mixed precision (i.e. forward and backward passes using fp16, with weight updates using fp32), using all NVIDIA recommendations for ensuring speed and accuracy.

Discriminative layer training¶

When fitting a model you can pass a list of learning rates (and/or weight decay amounts), which will apply a different rate to each layer group (i.e. the parameters of each module in self.layer_groups). See the Universal Language Model Fine-tuning for Text Classification paper for details and experimental results in NLP (we also frequently use them successfully in computer vision, but have not published a paper on this topic yet). When working with a Learner on which you've called split, you can set hyperparameters in four ways:

1. param = [val1, val2 ..., valn] (n = number of layer groups)
2. param = val
3. param = slice(start,end)
4. param = slice(end)

If we chose to set it in way 1, we must specify a number of values exactly equal to the number of layer groups. If we chose to set it in way 2, the chosen value will be repeated for all layer groups. See Learner.lr_range for an explanation of the slice syntax).

Here's an example of how to use discriminative learning rates (note that you don't actually need to manually call Learner.split in this case, since fastai uses this exact function as the default split for resnet18; this is just to show how to customize it):

Rather than manually setting an LR for every group, it's often easier to use Learner.lr_range. This is a convenience method that returns one learning rate for each layer group. If you pass slice(start,end) then the first group's learning rate is start, the last is end, and the remaining are evenly geometrically spaced.

If you pass just slice(end) then the last group's learning rate is end, and all the other groups are end/10. For instance (for our learner that has 3 layer groups):

Sets every layer group to trainable (i.e. requires_grad=True).

Sets every layer group except the last to untrainable (i.e. requires_grad=False).

A convenience method that sets layer_groups based on the result of split_model. If split_on is a function, it calls that function and passes the result to split_model (see above for example).

Saving and loading models¶

Simply call Learner.save and Learner.load to save and load models. Only the parameters are saved, not the actual architecture (so you'll need to create your model in the same way before loading weights back in). Models are saved to the path/model_dir directory.

Segmentation model¶

Build a Learner for segmentation tasks from data, using arch that may be pretrained if that flag is True. split_on will overwrite the default way the layers are split for differential learning rates. The underlying model is a DynamicUnet with blur, blur_final, self_attention, sigmoid and last_cross. norm_type is passed to conv_layer, the kwargs are passed to the Learner constructor.

Other methods¶

Initializes all weights (except batchnorm) using function init, which will often be from PyTorch's nn.init module.

Uses MixUpCallback.

You generally won't need to call this yourself - it's used to create the optim optimizer before fitting the model.

A Learner creates a Recorder object automatically - you do not need to explicitly pass to callback_fns - because other callbacks rely on it being available. It stores the smoothed loss, hyperparameter values, and metrics each batch, and provides plotting methods for each. Note that Learner automatically sets an attribute with the snake-cased name of each callback, so you can access this through Learner.recorder, as shown below.

Plotting methods¶

This is mainly used with the learning rate finder, since it shows a scatterplot of loss vs learning rate.

Note that validation losses are only calculated once per epoch, whereas training losses are calculated after every batch.

Note that metrics are only collected at the end of each epoch, so you'll need to train at least two epochs to have anything to show here.

Callback methods¶

You don't call these yourself - they're called by fastai's Callback system automatically to enable the class's functionality.

Inner functions¶

The following functions are used along the way by the Recorder or can be called by other callbacks.

Module functions¶

Generally you'll want to use a Learner to train your model, since they provide a lot of functionality and make things easier. However, for ultimate flexibility, you can call the same underlying functions that Learner calls behind the scenes:

Note that you have to create the Optimizer yourself if you call this function, whereas Learn.fit creates it for you automatically.

You won't generally need to call this yourself - it's what fit calls for each epoch.

This is what fit calls after each epoch. You can call it if you want to run inference on a DataLoader manually.

You won't generally need to call this yourself - it's what fit and validate call for each batch. It only does a backward pass if you set opt.

Other classes¶