amirdnc

Hi, I have a few follow-up questions: 1. The model in the path above is called "bert_finetune_model_7_1800.bin" is this a spanbert model? 2. what's it's scale? 3. could you add...

I get a similar error when each label has more than 1 embedding. it seems that the discussed line of code: https://github.com/KevinMusgrave/pytorch-metric-learning/blob/58247798ca9bf62ff49874e5cd07c41424e64fe9/src/pytorch_metric_learning/losses/centroid_triplet_loss.py#L124 assumes that the number of labels is a...

Sure. Try this: ``` loss_func = losses.CentroidTripletLoss() l = torch.tensor([228, 228, 228, 228, 228, 228, 228, 228, 228, 228, 83, 83, 83, 83, 83, 83, 83, 83, 83, 83, 200,...