Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

multilabel support for data_silo.calculate_class_weights #389

Merged
merged 3 commits into from
May 31, 2020
Merged

multilabel support for data_silo.calculate_class_weights #389

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
05819aa
allows data_silo.calculate_class_weights to support multilabel
renaud May 8, 2020
b0084ab
Merge branch 'patch-1' of https://github.com/renaud/FARM into renaud-…
Timoeller May 31, 2020
9629838
Separate class weights computation for multilabel vs multiclass
Timoeller May 31, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
6 changes: 5 additions & 1 deletion farm/data_handler/data_silo.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -478,8 +478,12 @@ def calculate_class_weights(self, task_name, source="train"):
else:
raise Exception("source argument expects one of [\"train\", \"all\"]")
for dataset in datasets:
if dataset is not None:
if "multilabel" in self.processor.tasks[task_name]["task_type"]:
for x in dataset:
observed_labels += [label_list[label_id] for label_id in (x[tensor_idx] == 1).nonzero()]
else:
observed_labels += [label_list[x[tensor_idx].item()] for x in dataset]

#TODO scale e.g. via logarithm to avoid crazy spikes for rare classes
class_weights = list(compute_class_weight("balanced", np.asarray(label_list), observed_labels))
return class_weights
Expand Down