jaymefosa
jaymefosa
 torch 1.5.0
I'd like to grab model weights from the same directory as the .yaml file, using nuctl's deploy --path argument. Is this possible? I've tried a bunch of dockerfile copy variations...
Swapping out the clock files for a kitchenware set of images (10 images) generated by the Kaolin datagenerator in Omniverse, following the Kaolin video tutorial, results in mesh generation that...
Is this a case where we don't want the grid to match the input resolution?
 CPU: i7-9750H GPU: 2070 Default run settings. img-size 256. Checked it on another system with a 2080ti and had similarly long times. Is there an issue somewhere?
Running the sample bash scan118: TypeError: forward() got an unexpected keyword argument 'save_vis'
After the end of a successful finetune while it's trying to save the validation: TypeError: forward() got an unexpected keyword argument 'save_vis' seems the finetune trainer doesn't have this arg