5c3de2518362675e14b15f87044742a94b816ef2,snntoolbox/simulation/target_simulators/loihi_target_sim.py,,normalize_loihi_network,#Any#Any#,394

Before Change

        // threshold to tune. So we only need to update the input to the next
        // layer, and propagate the scale. The input layer (i == 0) counts as
        // spiking.
        if i > 0 and not is_spiking(layer, config):
            x = y
            scales[layer.name] = scales[model_copy.layers[i - 1].name]
            continue

        // The highest EPSP determines whether to raise threshold.
        y_max = get_scale_fac(y[np.nonzero(y)], 100)
        print("Maximum increase in compartment voltage per timestep: {}."
              "".format(int(y_max)))

After Change

            // Loihi AveragePooling layers get weights of ones. To reproduce
            // this in our Keras model, we need to apply the same
            // transformations as for a regular layer that has weights.
            elif "AveragePooling" in get_type(layer):
                a = np.prod(layer.pool_size) * (2 ** num_weight_bits - 1)
                y = y * _weight_gain * 2 ** (weight_exponent + prev_scale) * a

Instances