-
我尝试使用latencyencoder来encode input,但是在神经元的选择上,sj里并没有现成的适用于ttfs的neuron类型,我尝试了issue里面的方法来进行实现并没有成功。能否问一下如何实现ttfs的神经元
-
二值脉冲本应用bool类型表示,能够极大的节省显存。但由于PyTorch的bool类型不支持携带梯度,需要设法重写梯度的机制。
-
微博内容精选
-
请问sops的计算是否漏掉了某些步骤?为什么本地运行的结果与表格相差近1000倍?已经明确不是单位的问题。
-
您好,我最近在尝试复现GitHub上一个SNN backbone+ANN head目标检测的代码。最初按照作者的描述安装了pytorch1.11、spikingjelly0.0.0.0.4等,但出现了AttributeError: module 'spikingjelly.clock_driven.neuron' has no attribute 'MultiStepParametricLIFNo…
xxyll updated
6 months ago
-
As discussed in many-a PR, cell positions and orientations need to be formalised.
A related and more pressing matter is that the in-plane distances between pyramidal cells (10 x 10 grid with 1 um s…
cjayb updated
3 years ago
-
[https://github.com/ggsonic/tacotron/blob/master/10.mp3](https://github.com/ggsonic/tacotron/blob/master/10.mp3)
based on your code, i can get clear voices,like the one above.
text is : The seven a…
-
**This is Part 6, I am splitting issues to reduce loading times and avoid github collapsing messages.**
**Browse all threads and find latest one to post to using the [gallery](https://github.com/oc…
-
您好,DVS128 Gesture的一条数据平均时间是6s,但论文中的 dt*T = 15 * 60 = 900ms,是不是可以认为您只使用了一条数据的前0.9s的信息,这样做不会丢失掉信息吗?
-
# Problem
The current implementation of the `apply_spikes` method presumes the charge value being supplied is relative to the threshold specified in the network JSON and the scale of `max_weight`. Pe…