v0.9.84

Testers

• BaseTester
  • Removed size_of_tsne and added visualizer and visualizer_hook to BaseTester. The visualizer needs to implement the fit and transform functions. (In the next version, I'll allow fit_transform as well.) For example:

# UMAP is the dimensionality reducer we will pass in as the visualizer
import umap
import umap.plot
# For plotting the embeddings
def visualizer_hook(umapper, umap_embeddings, labels, split_name, keyname):
    logging.info("UMAP plot for the {} split and label set {}".format(split_name, keyname))
    umap.plot.points(umapper, labels=labels, show_legend=False)
    plt.show()

GlobalEmbeddingSpaceTester(visualizer=umap.UMAP(), visualizer_hook=visualizer_hook)

Utils

• AccuracyCalculator
  • Added include to the init arguments.
  • Renamed exclude_metrics to exclude.
  • Added the requires_knn method.
  • Added check_primary_metrics to AccuracyCalculator, which validates the metrics specified in include and exclude. By @wconnell
• HookContainer
  • Check if primary_metric is in tester.AccuracyCalculator. By @wconnell
• logging_presets
  • Added **kwargs to get_hook_container, so that, for example, you can do get_hook_container(record_keeper, primary_metric="AMI")

Other stuff

• Added an example Google Colab notebook which goes through the entire training/testing workflow.

v0.9.83

Losses

• Added CircleLoss, implemented by @AlenUbuntu
• Changes to ProxyAnchorLoss:
  • Fixed bug that caused it to break when normalize_embeddings=False
  • Made it extend WeightRegularizerMixin
• Fixed/improved application of miner_weights in ProxyAnchorLoss, NCALoss, and FastAPLoss

Utils

• Added AccuracyCalculator
• Changes to loss_and_miner_utils
  • Made convert_to_weights return values between 0 and 1, where 1 represents the most frequently occuring sample. Before, it was scaling the probability by size of batch.

Other stuff

• Added a test for convert_to_weights

v0.9.82

Losses

• Added ProxyAnchorLoss

Trainers

• BaseTrainer
  • Made iterations_per_epoch optional. See the new documentation
  • Changed keys for lr_schedulers to allow for end of iteration, end of epoch, and plateau schedulers to all be used at the same time.
  • Fixed a key verification bug in BaseTrainer.

Utils

• HookContainer

  • Added skip_eval_if_already_done flag to run_tester_separately.
  • Made ignore_epoch a tuple.
  • Added save_custom_figures flag.
  • Made records get saved before models.

• common_functions

  • Removed pass_data_to_model and autograd.Variable usage.

Other stuff

• Fixed bug where __version__ was not accessible.
• Added test for pair and triplet index computation