-
你好，因为你的数据是允许bag最多有4个标签的，那么在main_mil.py里面，因为要选择在标签列上最大的那一行作为这个bag的表示，多标签的bag的话要选择哪个标签呢？（即select_instance函数，我看了下，你好像是直接选择第一个标签的？）谢谢！
-
Is it working only with LibSVMdata?
-
**Describe the bug**
I'm trying to use deepspeed to finetune a bert based classification model, but when trying to launch multi-node training all nodes include localhost get errno: 110 - Connection t…
-
What's the meaning of the folders 'data' and 'edge'? How did you get the files such as 0.label2,0.stroke_feature???? Can you upload the raw dataset ?
-
@ywangeq
Hi, Thank you for sharing your results. And can you give me some advice to get the following network structure diagram in your paper？ I want to draw a similar structure, but I don't know ho…
-
Good evening. I would like to use a U-Net with a pre-trained ResNet encoder as a multi-task learning neural network with a multi-task weighted loss function. Could you please guide me through this pro…
-
```
Thanks for all the good work you shared
Enhancement advice is needed on the best way to implement this in order to
detect two/three (or more) languages from the same document. Any guidelines are…
-
Hi @Innixma
When 'n_train_subsmaple' is set to 5000, and the number of train_data is larger than 5000, say, 40000, the following error is reported.
### **Error messages**
File "C:\miniconda…
-
https://arxiv.org/abs/1902.10640
-
## Issue will be closed if:
> 1) You mention more than one algorithm. You can create a separate issue for each algorithm once the current one is completed.
> 2) You propose an algorithm that is …