deepJDOT

deepJDOT copied to clipboard

Currently I am using my ground truth labels of the target dataset for searching the optimal loss weights. In your code they are called `sloss, tloss, jdot_alpha`. Are there other...

msseibel

Not important, I am just curious about your code style in the Deepjdot class. Why do you assign functions to the class with the following structure: class Deepjdot(object): .... def...

msseibel

Hello, https://github.com/bbdamodaran/deepJDOT/blob/b8814679d0e4b6f7c3e5aacf3964b767d1d2c22d/Deepjdot.py#L200 Why didn't you use log (softmax output) when you get C1 in Deepjdot.py ?

jeeyung

Recently, I read your ECCV2018 paper. It's an awesome paper. However, when I read this repository, I had some questions about the loss. When you fixed gamma to optimize the...

lw0517

Hi! Thank you for the procedure, I recently applied your program to solve some practical problems. But I encountered some difficulties. In your jdot_align model, you use self.model.train_on_batch([data], [np.vstack((ys, l_dummy)),...

xiangruyimoxiaoyangyang

Also reduce learning rate for demo file. See #10

offchan42

How to achieve high target accuracy given DeepJDOT limitations

2

I want to improve accuracy or loss of target dataset. So I would want to ask a few questions that might affect the accuracy. 1. If I want to increase...

offchan42