pytorch-NetVlad

pytorch-NetVlad copied to clipboard

Hi, I am stuck on an issue to use '.mat' trained model files inside PyTorch module. I want to use these as baseline models for a new dataset and somehow...

SharangKaul123

tokyo 24/7 performance

18

thanks for the remarkable work. have u done the experiment on the tokyo dataset? it seems that the performance is too much lower than the results in the paper.

bashar-tom

There is no further progress in the code

1

python main.py --mode=train --arch=vgg16 --pooling=netvlad --num_clusters=64 I tried above codes but theis no answer and just keep loading below .. (delg_env) C:\Users\User>python main.py --mode=train --arch=vgg16 --pooling=netvlad --num_clusters=64 --nGPU 1 Namespace(arch='vgg16',...

HyeokJaeKiM

Is it possible to convert to ONNX format?

1

Is it possible to convert to ONNX format? We want to work with TensorRT environment for runtime purpose.

fettahyildizz

np.square(knn.kneighbors(clsts, 2)[1]) Should be changed?

2

https://github.com/Nanne/pytorch-NetVlad/blob/8f7c37ba7a79a499dd0430ce3d3d5df40ea80581/netvlad.py#L51 Should this code be changed to this? "： `dsSq = np.square(knn.kneighbors(clsts, 2)[0])` knn.kneighbors(clsts, 2) returns two ndarrays, the first ndarray is the distance value, the second is the index...

wpumain