Alexander Chebykin

Hello. Are you planning on releasing your trained models? That would be very helpful

Is it actually reasonable to use single-class accuracy?

1

Hi, I'd like to ask a question regarding your paper. I'm interested in Fig 2.C and Fig S4.a,b. If I understand correctly, there you remove 256 neurons least relevant to...

CompressedSparseRow bug

1

While looking through sources in file https://github.com/YaccConstructor/QuickGraph/blob/master/src/QuickGraph/CompressedSparseRowGraph.cs I've noticed that the method ```FromGraph``` seems likely not to work due to the fact that ```start``` variable isn't updated after initialization. I've...

Wrapper classes for https://github.com/gunrock/gunrock Methods to test performance of corresponding Gunrock and Quickgraph solutions Linux only! (due to the fact that Gunrcok is Linux-only, which may change)

Pre-trained supernet weights release

3

Hi, Your approach is very impressive; I was wondering if you're planning to release the weights of the supernets you trained? (I'm specifically interested in the HyTra supernet)

Ways to free memory?

45

Hello. I'm using JavaParser and JavaSymbolSolver when creating a dataset by processing thousands of git repos. My problem is that the RAM consumption increases the longer my dataset-creating-program runs until...

Hi, Finding unique labels is not necessary when order == 0. In DownsampleSegForDSTransform2 in nnunet, this function is called multiple times, and it all adds up, especially in the limited...

As described in https://github.com/google/brax/issues/477, currently there is no friction-like force in the ``pusher`` environment with the ``spring`` backend. This means that even a slight touch of the object by the...