Mohammad Shafiei

Actually I resolved the seg fault in the last commit. It runs on Windows now. Didn't check it on linux yet

Sure. It's the [der hass](http://download.hrz.tu-darmstadt.de/media/FB20/GCC/mve_datasets/der_hass-20140923.tar.gz) dataset. But you should no longer face the seg fault if you check out the latest commit

For me, seg fault does not happen anymore in debug mode. But it is strange that in release mode it crashes.

The seg fault that I mentioned in last post was due to the existing destructors. I added @tmako123 's functions and the issues are now resolved. I added few files...

The transform function crashes for ORB feature type but works for SURF and AKAZE. On the other hand, the score function returns score 1.0 for SURF and AKAZE feature types...

So the problem is with the io functions. I resolved the io between step0 and step1. Where the _features_ vector is stored in a binary file. Instead I write it...

But the images with high scores should have similar view points. Isn't that correct? This is not the case when I run the code on _Der Hass_ dataset. Moreover, the...

I'm using CUDA 11.5. I installed jaxlib and jax from source (1.75.0 and 0.2.28). I am getting CUDA_ERROR_MISALIGNED_ADDRESS randomly while optimizing a neural net. I tried reducing the size of...

I get error with the following command, ``` >>> rng, init_rng = jax.random.split(jax.random.PRNGKey(1)) 2022-02-02 17:44:08.505863: E external/org_tensorflow/tensorflow/compiler/xla/pjrt/pjrt_stream_executor_client.cc:2089] Execution of replica 0 failed: INTERNAL: CustomCall failed: jaxlib/cuda_prng_kernels.cc:30: operation cudaGetLastError() failed: no...

@hawkinsp sure, ``` +-----------------------------------------------------------------------------+ | NVIDIA-SMI 495.29.05 Driver Version: 495.29.05 CUDA Version: 11.5 | |-------------------------------+----------------------+----------------------+ | GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf...