Philip Cho
Philip Cho
sorry, one more question. I am trying to export a test model and integrate it to my deepstream pipeline for testing, and I am facing unusual error here. ``` tao...
Ah I see, I think I found another possible bug that should be fixed. The export command runs, and there is another error coming from the config file that I...
Got it. thanks.
Has this issue been fixed? seems like the error remains
@junpeiz Thank you very much for your help! ``` def type_inference(self): # Don't compare the shape directly if there is symbolic shape. if any_symbolic(self.real_data.shape) or any_symbolic(self.imag_data.shape): # Checking the non-symbolic...
Thank you, I look forward to hearing updates on this!
I did kind of find a way to bypass the problem. You can create a padding network ``` class PadLayer(torch.nn.Module): def __init__(self): super().__init__() def forward(self, x): x, _ = autopad(x,...
thank you, your latest commit fixes all those issues. cheers.
sorry, one more question. This may be a related issue to your previous commit i think, as similar issue happens during validation. If you look at evaluation/coco.py starting line 283,...
I think you are right, because the validation loop crashes on the final batch (17th batch). Up to 16th, the validation proceeds perfectly. I checked the train.py (let me know...