embedding-propagation

embedding-propagation copied to clipboard

1. Reproduced results far worse than reported in paper Specifically, on mini-ImageNet with ResNet12 backbone, I get 52.38 for 1-shot SSL, and 67.02 for 5-shot SSL, compared to Table 4...

shwangtangjun

Question about label propagation during finetuning

1

In https://github.com/ServiceNow/embedding-propagation/blob/master/src/models/finetuning.py#L103 , why is the query matrix multiplied by `nclasses` . Shouldn't it start from zeros matrix since no labels are available for queries .. and labels are propagated...

Saurabh7

Can not reproduce the results

4

Hello, I cannot reproduce the results of the paper on the miniImagenet dataset. Is there any solution?（thanks very much） I used the pretrained and finetuned model data（backbone-wrn） you provided in...

sjiajia

finetune problems

1

when I finetune the pretrain model，there is an error. AssertionError File"trainval.py",line112, in trainval savedir_base=savedir_base /src/models/finetuning.py,line 66 in __init__assert(best_accuracy >0.1) can you help me ?

successhaha

some question about code

3

When I tried to reproduce the code, I encountered the following problems. I hope I can get your help. 1. When I used the pre-training model you uploaded on GitHub,...

Cccoooder

The code is different with paper in Embedding propagation

1

in paper[2.1-Embedding Propagation] said need to use σ2=var(dij2) to compute adjacency, but in the code[embedding-propagation.py--get_similarity_matrix()], which use function-torch.std() to compute adjacency, but var is Variance, std is Standard Deviation

Bulingbuling-ozgaga