Closed juice500ml closed 3 years ago
Random max (sampling 100): 0.9402
Orange: Semisupervised (max: 0.9485), Blue: Vanilla (max: 0.9403)
Random max (sampling 128): 0.9401
Our implementation (max: 0.9393, with different hyperparameters, suspecting
inner_epochs
is the culprit)
Nometric: Trained without metric loss Triplet: Trained with triplet loss
Freeze: Only train predictor Nofreeze: Train everything
Triplet loss clearly shows dominance!!!
generated_archs
may contain duplicate seqs