Shy
Shy
I have tried `opset_version == 16` in my problem and it works.
Anyone encountering a situation where the GPU memory is insufficient can reduce memory usage significantly by using the command model = torch.compile(model). In my experimental setup, this approach reduced GPU...
> > Anyone encountering a situation where the GPU memory is insufficient can reduce memory usage significantly by using the command model = torch.compile(model). In my experimental setup, this approach...
> Thank you,Doctor Zhou.I also want to ask what is FHE and AHE? I guess they are final heading error and average heading error.
``` $ pip list | grep torch pytorch-lightning 2.1.2 pytorch-triton 2.1.0+e6216047b8 torch 2.1.0+cu118 torch-geometric 2.3.1 torch-scatter 2.1.2 torch2trt 0.4.0 torchaudio 2.1.0+cu118 torchmetrics 1.2.0 torchvision 0.16.0+cu118**** ``` This is my complete...
> > Anyone encountering a situation where the GPU memory is insufficient can reduce memory usage significantly by using the command model = torch.compile(model). In my experimental setup, this approach...
> I also added this line of code where you mentioned it, but it still reported an error：raise TypeError(f"Trainer.fit() requires a LightningModule, got: {model.class.qualname}") TypeError: Trainer.fit() requires a LightningModule, got:...
> You can suppress this exception and fall back to eager by setting: import torch._dynamo torch._dynamo.config.suppress_errors = True""" You can try to follow https://github.com/pytorch/pytorch/issues/95791#issuecomment-1595237235, or write your custom radius function,...
> @SunHaoOne Could you provide some Code for your custom radius function? Did you replace the whole radius_graph function from torch-cluster or did you integrate your radius function into torch-cluster?...
Hi, @kennethweitzel > What do you use for k in this case? Since we aim to deploy the model, using radius can cause `dynamic` dimensions due to `non-zero` elements, which...