Jiaao Zhang comments

Results 8 comments of


                                            Jiaao Zhang

Is it possible to use smaller GPU for inference?

> > My gpu is V100, 16G, when I run > > python demo.py --trained_model weights/WIDERFace_DSFD_RES152.pth --img_root data/worlds-largest-selfie.jpg > > It gets error: RuntimeError: CUDA out of memory > >...

No file named 'correlation.so'

> Install CUDA. > Build the custom OPs. > Run Flownet2. Thanks, I had already solved the problem. But I got another question, have you ever tested the model on...

No file named 'correlation.so'

Some code is written by C++, so you need to build them. You can find the C++ code in the catalogue named "src/ops". The C++ code is supported by CUDA....

Result on Kitti 2012 cannot be recognised by the kitti benchmark system

could you please tell me how to use the official code "evaluate_scene_flow.cpp"? I studied it for a long time, but it didn't work.

Could not find resulting .flo file!

> I solved the problem by using flowNet2. > Thanks. ;) I have the same problem. But I just want to use the flownet1.0, what can I do? Thanks!

merge_sort: failed to synchronize: cudaErrorIllegalAddress with TensorField during training on some ScanNet scans

I fixed this error by using torch1.10.0+cuda11.3

import errors

hi bro, I got the same error!!!!!! have you solved this issue yet ?

import errors

thank you bro @sagadre by the way， how did you get tf-nightly==2.12？ I check the （https://pypi.python.org/pypi/tf-nightly），the oldest version is 2.13