Installed from: Installed from ananconda (conda 4.10.3)
Faiss compilation options:
Running on:
[ ] CPU
[x] GPU
Interface:
[ ] C++
[x] Python
Reproduction instructions
Hey Everyone,
I tried the first command for clustering before the training part:
python3 main.py --mode=cluster --arch=vgg16 --pooling=netvlad --num_clusters=64
And then it throws me the following error while computing the 'main.py' file from the repository:
Namespace(arch='vgg16', batchSize=4, cacheBatchSize=24, cachePath='/tmp/', cacheRefreshRate=1000, ckpt='latest', dataPath='/home/kau4hi/slam_ws/src/pytorch-NetVlad/netvlad_v100_datasets/data/', dataset='pittsburgh', evalEvery=1, fromscratch=False, lr=0.0001, lrGamma=0.5, lrStep=5, margin=0.1, mode='cluster', momentum=0.9, nEpochs=30, nGPU=1, nocuda=False, num_clusters=64, optim='SGD', patience=10, pooling='netvlad', resume='', runsPath='/home/kau4hi/slam_ws/src/pytorch-NetVlad/netvlad_v100_datasets/runs/', savePath='checkpoints', seed=123, split='val', start_epoch=0, threads=8, vladv2=False, weightDecay=0.001)
===> Loading dataset(s)
===> Building model
===> Calculating descriptors and clusters
====> Extracting Descriptors
====> Clustering..
Traceback (most recent call last):
File "main.py", line 498, in
get_clusters(whole_train_set)
File "main.py", line 281, in get_clusters
kmeans.train(dbFeat[...])
File "/home/kau4hi/gpu_anaconda3/lib/python3.6/site-packages/faiss/__init__.py", line 734, in train
clus.train(x, self.index, weights)
File "/home/kau4hi/gpu_anaconda3/lib/python3.6/site-packages/faiss/__init__.py", line 85, in replacement_train
self.train_c(n, swig_ptr(x), index)
File "/home/kau4hi/gpu_anaconda3/lib/python3.6/site-packages/faiss/swigfaiss_avx2.py", line 1477, in train
return _swigfaiss_avx2.Clustering_train(self, n, x, index, x_weights)
****NotImplementedError: Wrong number or type of arguments for overloaded function 'Clustering_train'.
Possible C/C++ prototypes are:
faiss::Clustering::train(faiss::Clustering::idx_t,float const *,faiss::Index &,float const *)
faiss::Clustering::train(faiss::Clustering::idx_t,float const *,faiss::Index &**)**
Summary
Platform
OS: Ubuntu 18.04 LTS
Faiss version: faiss-gpu 1.6.3
Installed from: Installed from ananconda (conda 4.10.3)
Faiss compilation options:
Running on:
Interface:
Reproduction instructions
Hey Everyone, I tried the first command for clustering before the training part: python3 main.py --mode=cluster --arch=vgg16 --pooling=netvlad --num_clusters=64 And then it throws me the following error while computing the 'main.py' file from the repository: Namespace(arch='vgg16', batchSize=4, cacheBatchSize=24, cachePath='/tmp/', cacheRefreshRate=1000, ckpt='latest', dataPath='/home/kau4hi/slam_ws/src/pytorch-NetVlad/netvlad_v100_datasets/data/', dataset='pittsburgh', evalEvery=1, fromscratch=False, lr=0.0001, lrGamma=0.5, lrStep=5, margin=0.1, mode='cluster', momentum=0.9, nEpochs=30, nGPU=1, nocuda=False, num_clusters=64, optim='SGD', patience=10, pooling='netvlad', resume='', runsPath='/home/kau4hi/slam_ws/src/pytorch-NetVlad/netvlad_v100_datasets/runs/', savePath='checkpoints', seed=123, split='val', start_epoch=0, threads=8, vladv2=False, weightDecay=0.001) ===> Loading dataset(s) ===> Building model ===> Calculating descriptors and clusters ====> Extracting Descriptors ====> Clustering.. Traceback (most recent call last): File "main.py", line 498, in