Open xiaoluomi opened 2 years ago
The first layer is used to convert the images to spike. To be specific, we use the IF neurons with the images as the input to generate spike.
Thank you for your reply. I find it .According to my understanding ,If I change the input into spike time series, the model should also be able to output the corresponding results.
Hi, Here are some questions about SpikeTensor. As you said SpikeTensor is a time series of 0 or 1. But after I convert imgs tensor to SpikeTensor by SpikeTensor(), I can't find the time series. I'd like to ask you about the method of converting the images to spike, is it Poisson flow? Can you tell me how to find the time series corresponding to each pixel of each picture? May it is a tensor like [1,0,1,1,1,0,1,0 ], the len(tensor)=timesteps ? or T=1 spike_img=[ [1,0,1], [0,1,0]... [0,1,1] ] T=2 spike_img=[ [1,1,1], [1,1,0]...[0,1,0] ] ....I tried for a long time and still couldn't figure it out. I really look forward to your reply.