About Normalize in get_transformer_train and get_transformer_test

[sihan-fu-98]

Thanks for your work!
I saw you are using
T.Normalize(mean=[0.48501960784313836, 0.4579568627450961, 0.4076039215686255],
std=[0.00392156862745098, 0.00392156862745098, 0.00392156862745098]) in get_transformer_train and get_transformer_test, different from the usually used:
T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]), which is also used in https://github.com/Nanne/pytorch-NetVlad.
(1) Is it due to that you are using the pretrained model vgg16_pitts_64_desc_cen.hdf5 which is matched to the former standard deviation while the pretrained VGG model in torchvision is using the later standard deviation?
And respectively, the learing rate you are using is 0.001, while Nanne/pytorch-NetVlad is using 0.0001, is it due to this?
(2) I'm trying to reproduce the SARE-joint result under the framework of Nanne/pytorch-NetVlad. I added the loss function written on my own and I'm using pretrained model vgg16_pitts_64_desc_cen.hdf5. The learning rate is still 0.0001 as Nanne/pytorch-NetVlad did. The standard deviation fallows Nanne/pytorch-NetVlad.
But I cannot achieve 89% Recall1 result on Pitts250k-test. I only have 3 GPUs to use so I have to set batch size to (3) I didn't add T.ColorJitter(0.7, 0.7, 0.7, 0.5) in get_transformer_train as Nanne/pytorch-NetVlad did.
Is it due to the batch size or T.ColorJitter or I should just use the pretrained VGG model in torchvision with T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])? Or would you give me some other suggestions?
Really thanks for your help!

[yxgeee]

(1) Yes, the mean and std are used to match the pre-trained VGG model. The official codes of NetVLAD and SARE both used 0.001 as the learning rate, please check.
(2) I did not reproduce the results by using Nanne/pytorch-NetVlad, so I cannot localize the problem exactly. Why not trying to use this repo?