LocalAggregation-Pytorch
LocalAggregation-Pytorch copied to clipboard
In the ‘train_one_epoch‘ function,I notice that when 'loss.backward()' is carried out for the first time,the Ci is not clustered by k-means method. Clustering does not work until the second data...
Hi, chengxuz, I have a question. In LA part, the loss backpropogates before k-mean updation. Does this mean that the first data batch did not define Ci as mentioned in...
Hello, I'm curious about the function __get_relative_prob in Class: LocalAggregationLossModule. Specifically, why you set 'keepdim = True' in function torch.sum conducted on back_nei_probs, while, 'keepdim = False' (default setting) in...
When I run command `CUDA_VISIBLE_DEVICES=0 python scripts/localagg.py ./config/imagenet_la.json` to do LA training, I get the following error : > > LocalAggregation-Pytorch/src/objectives/localagg.py(240)run_kmeans() > -> losses = faiss.vector_to_array(clus.obj) > (Pdb) n >...
I cannot understand the formulation in function "def _softmax". What is the value of 2876934.2 ?
It has taken me several hours while one epoch of training has not finished yet.