Phoebe-star

Results 35 comments of Phoebe-star

TypeError: get_updates() missing 1 required positional argument: 'constraints'

I use keras 2.0.0 , it can work, but use keras 2.0.8 can not work

how do you choose your cuhk03 dataset ?

the code can convert to tensorflow ? and when training , your triplet loss is always small ? like : Step: 67, Learning rate: 0.009951, Train loss: 0.031987 Step: 3300,...

how do you choose your cuhk03 dataset ?

how do you do resize images? you directly resize 224x224 ? not do crop? or others? and how about your Data Augmentation

how do you choose your cuhk03 dataset ?

how about your troubles?

how do you choose your cuhk03 dataset ?

yes, you are right , mk(x,y) is a 1*1 local convolutional layer which not shared weight have you been used hard example? if you used, the training will be hard.

how do you choose your cuhk03 dataset ?

Do you have use the googlenet pretrain from imagenet? how about your loss?

how do you choose your cuhk03 dataset ?

I think your vgg have some problem? like the whights don't change . why don't you use the googlenet? if use original triplet loss ,the loss will be easy to...

how do you choose your cuhk03 dataset ?

I also use someone github , but can I point it here? after all, here is zlmzju 's github

data

thanks ~ could you introduce any network pretrain for imagenet (on the github for tensorflow) , like , resnet50 ,googlenet,...... I want to retrain and fine tune the pretrain weight...

error split() takes at least 3 arguments (2 given)

thanks , I solved but how to do input two images and get the result whether if they are the same or not?