-
With NNFW-Runtime, multiple models may share a single session.
We need an interface to allow multiple NNFW instances in a pipeline to share a session if the user wants to do so.
If you take this…
-
**System information**.
Ubuntu 20.04.2 LTS (GNU/Linux 5.4.0-74-generic x86_64)
TensorFlow 2.0.0 installed by anaconda
gcc (Ubuntu 9.3.0-17ubuntu1~20.04) 9.3.0
NVIDIA-SMI 460.80 Driver Version: 460…
-
Hello, I saw a new effort on the "Vulkan state of the Union GDC Mar19" about that the Vulkan ecosystem is working on exposing machine learning computing capabilities on modern GPU.
At the moment, ou…
nihui updated
3 years ago
-
Please follow this Issue template to provide relevant information, such as source code repository, website URL and screenshots, which will help us investigate.
请按照此 Issue 模版提供相关信息,例如源码仓库、网站链接和屏幕截图,这将…
-
According to the `test/numerical/TestConv.cpp`, we need to copy weight each time we call the convolution function. Is there any method to set weight once, and avoid copying each time when computing?
-
Hi, I put a GPU-based nerual network in this project and I noticed that run.py has set the cuda invisible.
https://github.com/google-research/motion_imitation/blob/bbc04b1c3b083215f14858ce3435e3f0cb3…
-
I plan to use 3D convolution nerual network with PPO for my project recently, I don't know if it can works. haha~
However, it seems that ML-Agents only support adding one-dimensional array observatio…
-
please if i can send me an email or somthing soo i can contact with you
-
### What is the problem?
*Ray version and other system information (Python version, TensorFlow version, OS):*
ray: master
A timeslice's burn_in time steps will have samples from other episo…
-
你好,如果使用paired数据是否可以不用encoder-decoder结构,原作中是对隐空间进行了约束,既然我们对隐空间的分布没什么要求,应该可以使用更简单的网络,比如全连接来处理,不知我的理解是否有误?