Open lopuhin opened 7 years ago
The current training dataset is too big to put in a repo or host on s3 indefinitely. It was created with a crawler that is in the repo, but still it would be nice to have some way to re-train the classifier from scratch. See discussion in #3
The current training dataset is too big to put in a repo or host on s3 indefinitely. It was created with a crawler that is in the repo, but still it would be nice to have some way to re-train the classifier from scratch. See discussion in #3