okaits#7534

icon indicating a website link https://www.okaits7534.net/index.en.html icon indicating an email [email protected]

icon company Junior highschool student icon location Aichi pref., Japan icon location A Japanese junior highschool student. / Languages: Japanese, English, Python3, etc

Results 6 comments of okaits#7534

RuntimeError: expected scalar type Half but found Float

Adding `--no-half` option to main.py worked for me.

RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn

Same error on Anaconda3. (Ubuntu 23.04, NVIDIA GeForce GTX 1660 SUPER, Python 3.9, CUDA 11.6, PyTorch 20.0.0+cu118, conda 22.9.0) Show all output ``` [18:08:56] INFO [18:08:56] NumExpr defaulting to 6...

RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn

I tried it with my Windows 11 (CUDA 12.1) and failed with the same error. So I think this error can be caused by something with my hardware or CUDA...

RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn

Train started without any errors by disabling GPU in docker. But now it's too slow...

RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn

Oh, it worked!

RuntimeError: expected scalar type Half but found Float

Oh, sorry, it's webui.py, not main.py.