Flip your axes. The C1 elements are your bins and the current x-axis is your frequency. For further explanation of the color variations see response to a similar question here: Understanding Histogram Summary Plot in Tensorboard. Thanks. read more
Flip your axes. The C1 elements are your bins and the current x-axis is your frequency. For further explanation of the color variations see response to a similar question here: Understanding Histogram Summary Plot in Tensorboard. read more
These histograms are probably not that interesting for shallow models, you could imagine that with deep networks, weights in high layers might take a while to grow because of the logistic function being saturated. read more