ZENG, wenqi comments

Results 5 comments of


                                            ZENG, wenqi

why do we manually loop through each batch ?

Hi @linminhtoo , I have same question as you. The scripts make batchsize=64 while actually batchsize is hardcoded as 1. I noticed the line (https://github.com/FreyrS/dMaSIF/blob/master/data_iteration.py#L353) also ensures the batchsize=1 when...

你缝合了这么多东西，好歹写个引用出处啊

所以目测自己写的只有文件夹里/qbot/

subprocess.CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1.

I also encounter similar issues. don't how to fix

subprocess.CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1.

I found the solution discussed in previous issue: https://github.com/DeepGraphLearning/AStarNet/issues/3 the problem is caused by TorchDrug, the missing header file in different versions, e.g., "ATen/SparseTensorUtils.h" should be change to "ATen/native/SparseTensorUtils.h".

Mask only support padding mask

Thanks for the reply! I am new to sequence tagging and accidentally want to mask less important tokens. Somehow I want the model to focus on other important labels. That's...