-
In the line mentioned below, which is a part of documentation, it is mentioned that you are using conditional batch norm. However, in the code, you are using residual blocks without any batch norm. It…
-
**Submitting author:** @somefunagba (Oluwasegun Somefun)
**Repository:** https://github.com/somefunAgba/NLSIG-COVID19Lab
**Version:** v1.1.0
**Editor:** @majensen
**Reviewers:** @agahkarakuzu, @kakear…
-
Hi,
I don't really believe the results using these scripts, so I decided to prove me wrong.
my environment
```
- Ubuntu 18.04
- Supports Vulkan 1.2
- TensorRT 7.1.3
- cuDNN 8.0
- CUDA 10.2…
-
if I use it, how to call it. hidden is not defined.
-
Hi,
Thanks for the great work. I have several questions.
First, do the numbers in Table 7 include the training techniques mentioned in Appendix B.2?
Second, I'm wondering why are the improvemen…
-
Hey, thanks for the repository.
In footnote 3 of the paper Karras mentions a doubling of signal variance. Then, in the official TF code there are the lines
https://github.com/NVlabs/stylegan2/blob…
-
First, congratulation on your Mish paper accepted.
I've been thinking about activation functions, and how they can be improved, what properties are most important for a long time, and also inspired…
-
Hi all,
as already posted [here](https://community.rstudio.com/t/build-parsnip-model-from-nnetar-function-in-forecast-package/77208):
"I would like to build a parsnip model for a simple neural net…
-
Hi @hurjunhwa those configs seem not be used in main.py
```
--training_dataset_root=$KITTI_RAW_HOME \
--training_dataset_flip_augmentations=True \
--training_dataset_preprocessing_crop=True \
--t…
-
I am trying to benchmark ResNet on CPU, GPU and using Torch.
Therefore, I adapted the usage example as follows:
```julia
using Revise
using BenchmarkTools
using Flux
using Metalhead
using Tor…