wmf1997
wmf1997
hello, I think of how to solve it? ## 0. My Environment OS: Ubuntu 16.04 Python: Python 3.7.3 PyTorch: 1.2.0 ## 1. Why This Occur I think this is the...
> change the image into rgb doesn't solve this problem @xun6000 Indeed, changing the ```omniglot``` dataset's image to RGB (1 channel -> 3 channel) does not solve it. emm... if...
hello @divelab : I use the PPI dataset in PyTorch-Geometric, with the download url: https://s3.us-east-2.amazonaws.com/dgl.ai/dataset/ppi.zip I want to ask if it is the PPI you are doing experiment in the...
hello @EmptyCity1995 : I am also a user of ```torchstat```. i really like this tool. sorry, i am a little poor in english.... if you want to input a batch-like...
oh... i forgot one thing about tstat_version in file 2. you should write a line before the class defination. ```python from torchstat import __version__ as tstat_version ``` P.P.S. torchstat can...
dear @EmptyCity1995 : first, I must say sorry to you... :sob: actually, only Total MemR+W doubled... and other summaries do not change at all... I think I can change the...
Hello @willyd : I installed caffe and caffe-cpu via your conda packages successfully. And I want to ask a little question. If I use a new **C++ layer**(NOT PYTHON LAYER)...
Thank you very much~ @willyd
P.S. I use PyTorch 1.1.0, PyTorch Geometric is 1.3.0 (newest), PyTorch Unique is the newest.