lynshwoo2022
lynshwoo2022
hi @bathal1 , I encountered some problems : https://github.com/mitsuba-renderer/mitsuba3/issues/467, is this caused by the issue you mentioned?
hi @jatentaki , did you solve this problem? when I use : ``` "integrator": { "type": "path", 'max_depth': 8, 'hide_emitters':True }, ``` the error same as u occured, and if...
> @lynshwoo2022 that's good to know. I wasn't able to reduce the repro case nor get a core dump (since I'm running in a container and that messes with debugging)...
just changed integrator type to `prb_reparam`(integrating mitsuba in pytorch). and yes, some times it happens after 100 iterations, sometimes just happens in the beginning....
> @Speierers recently fixed a number of sources of undefined behavior on the `master` branch. If you are able to compile from Git, I suspect that this will likely fix...
> hi there, I compiled mitsuba from git. assertion errors solved, but [NAN problems](https://github.com/mitsuba-renderer/mitsuba3/issues/468) remained.
problem solved by: 1. change: `stage_configuration = load_model_config(args['stage'], args['mode'])` to `stage_configuration = load_model_config(args['stage'], args['model'])` 2. change 3 `freeze` config to `True` in config/stage yaml you use. 3. change `all_gen_img_idx =...
have you solved this problem?
持续follow进展
> @mdswyz However, when I downsample my acquired image (LR 214x259) to 22x27 and used `CelebA_X8.pt`, it works as good as the image you provide (LR 22x27). So I doubt...