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.
- I have a dataset consisting 1000 identities, each with a varying number of face images (minimum 3). - I also have a trained face recognition model, say ArcFace to...
Hi, Thanks for this amazing library. I wanted to know if it is currently feasible to mine quadruplets which qualify certain conditions like in SEMIHARD mode for triplet mining. I...
Hi, I find that it's nice to have a few benchmark datasets integrated into libraries for easier research. My feature request boils down to the implementation of a few image...
Hi, this PR implements the loss presented in the paper [Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval](https://arxiv.org/abs/2007.12163). The default hyperparameters are chosen using the values that resemble a heavyside...
Hi, this PR implements the loss presented in the paper [Threshold-Consistent Margin Loss for Open-World Deep Metric Learning](https://arxiv.org/abs/2307.04047). The loss is combined with a base loss provided by the user....
As always, thanks again for the library and apologies for asking another question! I was wondering if the MatchFinder or InferenceModel can return all of the distances for all classes...
[This line](https://github.com/KevinMusgrave/pytorch-metric-learning/blob/28d5acce05f61b0d0c15acbe423a7ba387efcb4d/src/pytorch_metric_learning/utils/common_functions.py#L302) is generating a `RuntimeError`: ``` RuntimeError: Error(s) in loading state_dict for DataParallel: Missing key(s) in state_dict: "module.conv1.weight", "module.bn1.weight", ... ``` This happened after running [this example](https://github.com/KevinMusgrave/pytorch-metric-learning/blob/master/examples/notebooks/MetricLossOnly.ipynb), replacing `trainer.train(num_epochs=num_epochs)`...
Metadata
Owner
Metadata
The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.