-
Thanks for your great work!
Just one quick question, how many GPUs were used to obtain the results in the paper? I didn't seem to find the specification on this.
Best
-
hello,
when I run the program, the error is reported, I thought it was a file permission issue, but I couldn't find that file.
how to solve it?
Traceback (most recent call last):
File "F:\80…
-
Hi,
Sorry to bother you again. I tried to reproduce the results reported in your paper on CIFAR100-LT. Here is my running: python train.py --dataset cifar100 --num-max 50 --num-max-u 400 --a…
-
Hello. Thanks for the great work.
Besides, I was wondering if you can share your baseline implementation e.g., fixmatch.
Thank you.
-
Hi, I want to ask you why you set the mode of the teacher network to evaluation when generating pseudo labels.
https://github.com/azhuantou/HSSDA/blob/30822d0cd8992a3b460f9f190abe076bed11f338/pcdet…
-
最近在追您的工作，想做一些实验，目前遇到了几个问题，麻烦您帮忙看一下：
1.由于我的环境是单卡的集群，在按照readme里配置后，使用这个指令运行，出现下面的问题，请问您是否遇见过，有没有什么建议？
sh scripts/train.sh 1 20023
2.还有个思路上的问题，我看到您的代码中，包括特征级的扰动，和图像级的强扰动，都是采用同样的参数来实施的，那么您是否考虑过对于…
-
Sorry to bother you, but when reproducing your code, I can't get the same results mentioned in your paper. Even when removing the adaptive weighting, just run Fixmatch, I got the mean acc 55.06, which…
-
代码勘误：根据论文3.2和3.3节的描述（公式（3）、公式（9）），弱数据增强的预测概率q^i_c（即pseudo_label）中不低于p_cutoff的部分s^i_c为1，但代码中用的是强数据增强的预测概率（即softmax_pred）。以下是我从flexmatch_util.py中摘取的例子：
`mask_k_npl = F.where((mask_k==1)&(softmax_pred>p…
-
Pascal: [JPEGImages](http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar) | [SegmentationClass](https://drive.google.com/file/d/1ikrDlsai5QSf2GiSUR3f8PZUzyTubcuF/view?usp=sharin…
-
Hi
Thanks for the great work and package. I have recently started using skorch :)
I would like to implement FixMatch in skorch: https://arxiv.org/abs/2001.07685
so the main idea is that in eac…