pytorch/examples

mnist example contains bad practices leading to wrongful results

Open

#623 ouverte le 27 août 2019

Voir sur GitHub
 (2 commentaires) (0 réactions) (0 assignés)Python (9 429 forks)batch import
good first issue

Métriques du dépôt

Stars
 (21 634 stars)
Métriques de merge PR
 (Aucune PR mergée en 30 j)

Description

In the mnist example there should be explicit comments about the default nature of the F.nll_loss which is to average the results over the mini-batch. The other thing that can lead to errors is the len(train_loader.dataset) even though that returns the number of samples in the train dataset if someone was to create a split of train data into train/valid using SubsetRandomSampler then calling again len(train_loader.dataset) will still return you the full number of samples in the train set (which is wrong) without reflecting the correct number of samples since the train set now contains X% less samples which have been kept as validation set.

Guide contributeur