-
I failed to cancel my job with `sky cancel`. I had to manually ssh in and kill it.
@Michaelvll have you met this issue before?
```
(sky) weichiang@blaze:~/repos/bert-sign/sky-experiments/prototype/…
-
Hello, sorry to bother you, now I have finished the data_processing step with my own decoys, and got the iinterface and linterface files. How to divide it into training set, test set and import it int…
-
Dear Author, really thanks you all for opening this open source.
I'm a novice and do not have much techniques in dealing with and running all kinds of framework, so today, I've been suffered from …
-
## 🚀 Feature
Empirical and theoretical research suggests that (semi-)orthonormal initialization results in better performance for MLPs, CNNs, RNNs, etc. For example:
1. [*Exact solutions to th…
-
## 🐛 Bug
Recently, we have been reported that program hangs at very beginning when distributed train. I found it's more likely if many trainers are booted and `cython` enabled DGL(it's enabled in…
-
## ❓ Questions and Help
Hello Everyone, So past few days I have been trying to run GNN using ONNX runtime (Python and eventually on C++). However I get the following error after I successfully export…
-
### 🐛 Describe the bug
I am trying to implement various RL algorithms using GNNs and Eligibility Traces of the network parameters. I found a couple of examples online, but for some reason I cannot …
-
## 🐛 Bug
## To Reproduce
Steps to reproduce the behavior:
1. python main.py
1.
1.
Test loss 0.4159 | Test Micro f1 0.8748 | Test Macro f1 0.8741
## Expected behavior
Te…
-
## 🐛 Bug
Hi, I'm struggling with a CUDA error 😥
Following arises the error ```CUDA error: an illegal memory access was encountered```.
```python
model = Model(**input_args)
trainer = tra…
-
Dear Authors,
I use the LBA model and try to use "model = model.to(device)", but it got the error
"device, dtype, non_blocking = torch._C._nn._parse_to(*args, **kwargs)
ValueError: too many va…