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.
@KevinMusgrave I have a question about using pytorch-metric-learning with a labeled triplet dataset. I have around one million (query, positive, negative) triplet for training. Now, looking at the example code...
Add compatibility of distributedwrapper for two stream input, so wrapped miner and loss can also use forward as `self.miner(query_embed, labels, doc_embed, labels.clone())` and `self.loss(query_embed, labels, doc_embed, labels.clone())`
Hi, how does the DistributedWrapper support two stream input? I see the original implementation DistributedWrapper class only has three input with `def forward(self, embeddings, labels)` , but I want something...
It's normal to try: ```python labels = torch.arange(32) x = lmu.get_all_pairs_indices(labels, ref_labels=labels) ``` This will result in 0 positive pairs because of the `labels is ref_labels` check. This isn't documented...
pytorch_metric_learning.utils.inference in function try_gpu(line258), weather gpu_index or cpu_index, both call function add_to_index_and_search, but this function only use cpu for faiss search ----------------------------------------------------------------------------------------- def add_to_index_and_search(index, query, reference, k): if reference is...
Hello, I am working on Dynamic Arcface: https://arxiv.org/pdf/2010.05350.pdf. I implemented a unit test. However, I have some implementation concerns. Particularly, Dynamic Arcface seems to more of a wrapper than a...
Hello, I have a question about `CrossBatchMemory`. According to the paper (Wang et al, 2020), > As the feature drift is relatively large at the early epochs, we warm up...
Hello sir, your git does really ease my burden, I really appreciate it . Thanks! But when I change my code to a DDP manner, something goes wrong. Here is...
Metadata
Owner
Metadata
The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.