Kamer Ali Yuksel

Question on Shared Model & Multiprocesses

1

Dear Didier, You have been super helpful last time. Hence, if you would allow me, I would like to ask one more question. In the following code, I am trying...

Hello! Thanks a lot. Do you also plan to maybe include an AutoShuffle version of the ShuffleNetV2? https://arxiv.org/abs/1901.08624

Would you also be interested implementing Global Second Order Pooling? it claims to be better than CBAM: https://arxiv.org/abs/1811.12006

Comparison to Mish activation

7

Mish is the current most popular activation function. Thus, it would be good if you can also compare with it.

Hello again, I hope that you're doing well. I am creating some multi-agent RL environments, as mentioned in the title, and got interesting results for the crowd and predator-prey simulations...

GNN-based Meta-Learning for Sparse Portfolio Optimization

5

Hello, Let me start by saying that I am a fan of your work here. I have recently open-sourced by GNN-based meta-learning method for optimization. I have applied it to...

1D version of Fast-MPN-Cov

5

Can you please also release a 1D version that we can use for time series rather than images?

Changing The Face in a Real Image with an Artificial Face

1

Hello, would that be possible for you to do that?

Generative Meta-Learning for Large-Scale Non-Convex Optimization (RL)

8

Hello! You can find it here: https://github.com/kayuksel/generative-opt Just change the following lines for combinatorial optimization. I also implemented Fast CMA-ES and Tabu Search in PyTorch. Here is Fast CMA-ES: https://github.com/kayuksel/torch-tsp-es/...

Hello! Thanks a lot. Do you also plan to maybe include an AutoShuffle version of the ShuffleNetV2? https://arxiv.org/abs/1901.08624