pytorch-metric-learning
pytorch-metric-learning copied to clipboard
KevinMusgrave
The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.
In version 1.2.0, Centroid Triplet Loss is unstable. When the batch size is small, the below error always occurs. If larger batch size, it is relatively be relieved. `File "/root/miniconda3/lib/python3.7/site-packages/pytorch_metric_learning/losses/base_metric_loss_function.py",...
Hi, In `TripletMarginLoss` you have default margin set to **0.05**: ``` class TripletMarginLoss(BaseMetricLossFunction): """ Args: margin: The desired difference between the anchor-positive distance and the anchor-negative distance. swap: Use the...
Hi everyone! What is the purpose of **embeddings_come_from_same_source** argument of [get_accuracy](https://kevinmusgrave.github.io/pytorch-metric-learning/accuracy_calculation/#getting-accuracy) function? Let's consider a case in which query == index and I set this argument to **True**. Will it...
Any plan to include example of this loss function? Thanks
When ```efficient=True```: - All embeddings should be added to each rank's ```CrossBatchMemory.embedding_memory``` - Only the current rank's embeddings should be passed as the first argument to ```CrossBatchMemory.loss.forward()```
This would require changing the order of arguments to ```query, query_labels, reference, reference_labels```
The regularizer mixins are overly complicated: https://github.com/KevinMusgrave/pytorch-metric-learning/blob/master/src/pytorch_metric_learning/losses/mixins.py Also get rid of or simplify [```all_regularization_loss_names```](https://github.com/KevinMusgrave/pytorch-metric-learning/blob/0caae7af403c637732856d6305b4f9111c187fc3/src/pytorch_metric_learning/losses/base_metric_loss_function.py#L55-L64)
This seemed like a good idea when used with record-keeper, but it complicates things if you're not using record-keeper
It can be useful to compute the average loss over the training set or validation set, and use that (rather than some accuracy metric) to select the best checkpoint. See...
As mentioned in this pull request: https://github.com/KevinMusgrave/pytorch-metric-learning/pull/424#issuecomment-1042868787
Metadata
Owner
Metadata
The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.