Good to hear that the 2:1 rule of thumb is right.
We will add a second blog post in which we discuss how accurate this rule is under different conditions. It looks like it depends on many factors such as batch size, type of parameters, depth, etc.
Following up on this—the aforementioned second blog post is now up!
Good to hear that the 2:1 rule of thumb is right.
We will add a second blog post in which we discuss how accurate this rule is under different conditions. It looks like it depends on many factors such as batch size, type of parameters, depth, etc.
Following up on this—the aforementioned second blog post is now up!