-
Architecture selection is major and challenging task when constructing DNNs.
Research how the architecture selection affects the results for the MNIST dataset.
Find the best architecture from all arch…
-
I'm a pytorch and mxnet user and `Flux` looks promising to me. I have 8 GPUs on the server and I want to train my model faster. Unfortunately, I see no document about parallel training on multiple GP…
-
Hi!
I got this notification while running this line in cifar_single_model.ipynb:
fastshap.train(
fastshap_train,
fastshap_val,
batch_size=128,
num_samples=2,
max_epochs=…
-
I am the co-author of [Foolbox](https://github.com/bethgelab/foolbox) and coordinator of the [Robust Vision Benchmark](https://robust.vision/benchmark/leaderboard/). The results you report are amazing…
-
MPC-based Realtime Power System Control with DNN-based Prediction/Sensitivity-Estimation. (arXiv:2106.02794v1 [eess.SY])
https://ift.tt/2T57uXK
This paper presents a model predictive control (MPC)-bas…
-
I came across your article on arXiv today and the timing is incredible. I've been working on capturing a large dataset for analyzing human activity based on estimated skeleton position in video frames…
-
Dear All,
There are many existing projects based on the existing version, Caffe.
After Facebook open sourced Caffe2 (Apr 18, 2017) as a next version of Caffe, It seems that
Caffe2 include lots…
-
[Understanding Neural Networks Through Deep Visualization](https://arxiv.org/abs/1506.06579)
Recent years have produced great advances in training large, deep neural networks (DNNs), including notabl…
-
Currently, the COMPUTE() loop is a pure time-wasting loop, designed to be insensitive to the DVFS/frequency settings of the underlying CPU, as well as to the underlying CPU architecture/type. This avo…
-
hello：
when i test the ImageDemo.py, i find that a picture of 600*640 pixes need 17s on cpu, and 10s on gpu; However, this is not the case in the paper. Is the processing time normal? Time is mainly …