HashNet

HashNet copied to clipboard

pairwise loss in pytorch code

10

Hi, I have difficult in understanding the pairwise loss in your pytorch code. Particularly, 1. I can not relate it to the Equation (4) in the paper. What is the...

bfan

AlexNet backbone result (COCO)

3

I run PyTorch HashNet with the below parameters, I just change the backbone network to AlexNet for comparing this code result with the original paper. dataset: coco net: AlexNet lr:...

fegler

HashNet on CUB200

1

Hi, I've tried to use HashNet to Fine-grained recognition, so I adopted the PyTorch code to CUB200 dataset with finetuned ResNet50, but I can't make the loss converge. I've tried...

zhouxiaohang

number of training images for imagenet

1

Hi, first really appreciate for sharing codes. I have a question about the experimental settings. in your paper, experimental settings for imagenet is > We randomly select 100 categories, use...

xulj-cs

False sampling of data

1

hi, I just found out, that all images in the query list are also in the database list, which is not allowed for fair validation. thanks

hbellafkir

Hi! I'm looking to do inference only, and not retrain. Would anybody be willing to share their model parameters that was trained on ImageNet or similar full size images? (Preferably...

exnx

Pytorch with Resnet50

6

I change the network to resnet50 in the pytorch version HashNet, and i can not produce acceptable map on CUB dataset. I have tried some fine tuning, and the best...

rayLemond

Hi authors, in the paper, you mention that nuswide "use the subset of 195,834 images that are associated with the 21 most frequent concepts", but i saw vector with size...

kamwoh

nuswide dataset

1

I can't download this dataset. May I have a copy, please

ximi2018

@bfan @caozhangjie

1

@bfan @caozhangjie I add the weight in pytorch version(without c). ``` def pairwise_loss(outputs1,outputs2,label1,label2): similarity = Variable(torch.mm(label1.data.float(), label2.data.float().t()) > 0).float() dot_product = torch.mm(outputs1, outputs2.t()) #exp_product = torch.exp(dot_product) mask_positive = similarity.data >...

LiShuiYu