Retrain a Pretrained Model

import poutyne

from deepparse import download_from_url
from deepparse.dataset_container import PickleDatasetContainer
from deepparse.parser import AddressParser

First, let’s download the train and test data from the public repository.

saving_dir = "./data"
file_extension = "p"
training_dataset_name = "sample_incomplete_data"
test_dataset_name = "test_sample_data"
download_from_url(training_dataset_name, saving_dir, file_extension=file_extension)
download_from_url(test_dataset_name, saving_dir, file_extension=file_extension)

Now let’s create a training and test container.

training_container = PickleDatasetContainer(os.path.join(saving_dir,
                                                         training_dataset_name + "." + file_extension))
test_container = PickleDatasetContainer(os.path.join(saving_dir,
                                                     test_dataset_name + "." + file_extension))

We will retrain the fasttext version of our pretrained model.

address_parser = AddressParser(model_type="fasttext", device=0)

Now let’s retrain for 5 epochs using a batch size of 8 since the dataset is really small for the example. Let’s start with the default learning rate of 0.01 and use a learning rate scheduler to lower the learning rate as we progress.

# reduce LR by a factor of 10 each epoch
lr_scheduler = poutyne.StepLR(step_size=1, gamma=0.1)

The checkpoints (ckpt) are saved in the default “./checkpoints” directory

address_parser.retrain(training_container, 0.8, epochs=5, batch_size=8, num_workers=2, callbacks=[lr_scheduler])

Now let’s test our fine tuned model using the best ckeckpoint (default parameter).

address_parser.test(test_container, batch_size=256)