deeepwin

In addition to above comments, in your error log, you have a mismatch between pre-compiled jaxlib cuDNN version and the cuDNN version you have installed (8.1.0 versus 8.6.0). See [here](https://github.com/deeepwin/nerf-multinerf)...

I had the same issue. Reduced batch_size to match available GPU memory helped in my case. See similar ticket [here](https://github.com/google-research/multinerf/issues/77). Also check README `OOM Error` section.

Same here with search() method, with get_news() it works.

> The estimated camera pose during the colmap stage for things with no surface features is inaccurate, so the generated image is very poor But the poses look actually quite...

@mli0603 I have also added my example to be able to reproduce: - Checkpoint - Config - Data - Mesh https://1drv.ms/u/s!AtwBlzVMECHC4m1cGAxKqqd_mTKB?e=zVayUR

I have retried and it seems to work now (with commit b772282d26f62064401b1f4f0d53eefe908afdb3). I do not know why, but I did the following things: 1. I generated config file with: `python3...

@iam-machine Yes, sure, here my example, textured and without:  

@Choco83 there are several ways. With the mouse-2 example I used Kiri, see NerfStudio description [here](https://docs.nerf.studio/en/latest/quickstart/custom_dataset.html). In one instance of data, I already had the poses in COLMAP format (images.txt)...

Same here. I guess, as enable_op_determinism() documentation states: ``` Certain ops will raise an `UnimplementedError` because they do not yet have a deterministic implementation. Additionally, due to bugs, some ops...

Seems when disabling XLA, error disappers for MaxPooling2D: ``` @TF.function(jit_compile=False) def _train() ```