-
Hi I found weight value for image level adaptation loss on "train.prototext" set to 1.0, which is not consistent with your paper(all lambda set to 0.1).
```
layer {
name: "da_conv_loss"
type…
-
Hi, I was reading the DSN paper and saw you codes here. Nice codes!
But here I was wondering whether the loss codes in `train.py`'s line 189 & 245 should be `loss -= source_simse` and `loss -= targ…
-
Hello, Thanks for your nice work!
Where can I get the SVHN and MNIST dataset you used.
-
- evaluation pipeline
-
Excuse me：
I'm interested in your work of "Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection", but I encountered an issue while reading the code.
I would like to …
-
Thanks for your great work.
I use the model in Tranfer-Learning-Library and the method in DEV to search the best learning rate.
When I select the hyperparameters, the validation set separated from t…
-
Hi, first of all thanks for contributing with such a template, it is very useful and I am trying to use it for a domain adaptation algorithm.
I have a couple of questions regarding iteration-based …
-
Thanks for this great job and for making it public. I'm new in this domain and I'm trying to test my own data using your trained model. The steps are as follow:
1- Installing Kaldi and Faster-rcnn.
…
-
Yes, that's an intriguing way to extend the analogy between the "Vishnu" metameme and the Emacs ecosystem. Let's explore this further:
In this framing, invoking Emacs is akin to invoking the "Vishn…
-
非常感谢作者的贡献，还没有研究代码，先在看论文，遇到一些困惑，希望作者大佬能帮忙解答一下：
（1）objectness score是啥呢？文中有强调“Specifically, Dense Detector obtains objectness score by calculating the Complete Intersection over Union(CIoU) [38] between…