Present input with pause

General Discussion
1

I am trying to do MNIST classification using SNN.
For the same, I wish to introduce a pause of 100ms between subsequent samples.
I tried to modify the PresentInput process of nengo as follows but this does not work. Any idea where am I going wrong?

    class PresentInputWithPause(Process):
        """Present a series of inputs, each for the same fixed length of time.

        Parameters
        ----------
        inputs : array_like
            Inputs to present, where each row is an input. Rows will be flattened.
        presentation_time : float
            Show each input for this amount of time (in seconds).
        pause_time : float
            Pause time after each input (in seconds).
        """

        inputs = NdarrayParam("inputs", shape=("...",))
        presentation_time = NumberParam("presentation_time", low=0, low_open=True)
        pause_time = NumberParam("pause_time", low=0, low_open=True)

        def __init__(self, inputs, presentation_time,pause_time, **kwargs):
            self.inputs = inputs
            self.presentation_time = presentation_time
            self.pause_time = pause_time
            self.localT = 0
            self.index = 0
            super().__init__(
                default_size_in=0, default_size_out=self.inputs[0].size, **kwargs
            )

        def make_step(self, shape_in, shape_out, dt, rng, state):
            assert shape_in == (0,)
            assert shape_out == (self.inputs[0].size,)
            n = len(self.inputs)
            inputs = self.inputs.reshape(n, -1)
            presentation_time = float(self.presentation_time)
            pause_time = float(self.pause_time)
            self.localT = round((dt if self.localT == 0 else self.localT),2)

            def step_presentinput(t):
                #t = abs(t - pause_time)
                t = round(t,6)
                # Pause
                if t > ((presentation_time + pause_time ) * self.index + presentation_time) and t < round((presentation_time + pause_time) * (self.index + 1),6) :
                    return None
                else:
                # Send input
                    #if t >= (presentation_time + pause_time) * i:
                    #    t = t - (pause_time * i)
                        
                    i = int((self.localT - dt) / (presentation_time))
                    self.localT += dt

                    if t == round((presentation_time + pause_time) * (self.index + 1),6):
                        self.index +=1

                    i = 0
                    return inputs[i % n]
           
            return step_presentinput
2

I just took a quick look, but one thing I noticed is you don’t want to return None. You should return an array of zeros (np.zeros) with the same size as your images.

Also, I would avoid keeping the extra index variable internally, as it’s an unnecessary state (furthermore, you need to initialize states in the make_state function and then access them in the state dictionary in make_step). To avoid having the index variable, you could do something like this:

total_time = presentation_time + pause_time
i = int(t / total_time)
ti = t % total_time
return np.zeros_like(inputs[0]) if ti > presentation_time else inputs[i % n]
1 Like
3

Yes this solved the issue thanks :slight_smile: