Jin-Hwa Kim

Results 13 issues of Jin-Hwa Kim

instapaper's articles can be organized with Folders. may it equals to readability's Tag feather, so can it be mapping between two of them?

Using `coco2` branch, I expand to another dataset, Visual QA. w.r.t multithreading, I didn't gain speed up with this status. - iowait: 9% - read/s: 20 mb/s - batch size:...

Could I get a checkpoint of ~~VGG9~~ ResNet32 pre-trained on TinyImageNet in https://github.com/alinlab/L2T-ww/blob/master/train_l2t_ww.py#L177 used in the paper?

I assume that the 3rd matching task needs `*DualEncoder` for two inputs; however, [lra_benchmarks.utils.train_utils:get_model()](https://github.com/google-research/long-range-arena/blob/main/lra_benchmarks/utils/train_utils.py#L34) doesn't have that functionality. Am I missing something?

Since Hessian is indefinite for CNNs, CG cannot guarantee the monotonic decrease of errors. So, have you ever tried to use the best step's results instead of the last? In...

luarocks build error ``` /usr/bin/ld: cannot find -lcufft collect2: error: ld returned 1 exit status make[2]: *** [libspectralnet.so] Error 1 make[1]: *** [CMakeFiles/spectralnet.dir/all] Error 2 make: *** [all] Error 2...

This pull request addresses two issues that were identified in the RayMarcher and Volume Rendering code: 1. Random Order Aggregation in RayMarcher: Previously, the samples were aggregated in random order...

Could you specify what kind of license do you permit to use the code and the dataset?

Please refer to [this issue](https://github.com/jnhwkim/MulLowBiVQA/issues/9) in our recent work on VQA. Notice that the preprocessing for question model is the same. Thanks!

I follow your instruction on README, appearance.color doesn't change the color of indicator. Would you check your code or may I miss something else?