djay29

Results 5 comments of djay29

about resuming training from a specific weight in colab

@therockwin1 do you have the method to resume the training from saved weights? If yes, then please share the method.

RuntimeError: don't know how to restore data location of torch.storage.UntypedStorage (tagged with privateuseone:0)

This happens after generating one frame of txt2vid on AMD graphics card using DML

An exception occurred while trying to process the frame: tensor.device().type() == at::DeviceType::PrivateUse1 INTERNAL ASSERT FAILED at "D:\\a\\_work\\1\\s\\pytorch-directml-plugin\\torch_directml\\csrc\\dml\\DMLTensor.cpp":31, please report a bug to PyTorch. unbox expects Dml at::Tensor as inputs

This is with vid2vid on AMD graphics card using DML

An exception occurred while trying to process the frame: tensor.device().type() == at::DeviceType::PrivateUse1 INTERNAL ASSERT FAILED at "D:\\a\\_work\\1\\s\\pytorch-directml-plugin\\torch_directml\\csrc\\dml\\DMLTensor.cpp":31, please report a bug to PyTorch. unbox expects Dml at::Tensor as inputs

@system3600 It is not working on AMD gpus. It was able generate only one frame in txt2vid after that there is another error which is also reported by me in...

could not convert string to float: ' '

While txt2video it is giving this error.