Optimization Single Step Preview

class Value:

    def __init__(self, data, _children=(), _op='', label=''):
        self.data = data
        self.grad = 0.0
        self._prev = set(_children)
        self._op = _op
        self.label = label


    def __repr__(self):   # This basically allows us to print nicer looking expressions for the final output
        return f"Value(data={self.data})"

    def __add__(self, other):
        out = Value(self.data + other.data, (self, other), '+')
        return out

    def __mul__(self, other):
        out = Value(self.data * other.data, (self, other), '*')
        return out

a = Value(2.0, label='a')
b = Value(-3.0, label='b')
c = Value(10.0, label='c')
e = a*b; e.label='e'
d= e + c; d.label='d'
f = Value(-2.0, label='f')
L = d*f; L.label='L'
L

Value(data=-8.0)

from graphviz import Digraph

def trace(root):
    #Builds a set of all nodes and edges in a graph
    nodes, edges = set(), set()
    def build(v):
        if v not in nodes:
            nodes.add(v)
            for child in v._prev:
                edges.add((child, v))
                build(child)
    build(root)
    return nodes, edges

def draw_dot(root):
    dot = Digraph(format='svg', graph_attr={'rankdir': 'LR'}) #LR == Left to Right

    nodes, edges = trace(root)
    for n in nodes:
        uid = str(id(n))
        #For any value in the graph, create a rectangular ('record') node for it
        dot.node(name = uid, label = "{ %s | data %.4f | grad %.4f }" % ( n.label, n.data, n.grad), shape='record')
        if n._op:
            #If this value is a result of some operation, then create an op node for it
            dot.node(name = uid + n._op, label=n._op)
            #and connect this node to it
            dot.edge(uid + n._op, uid)

    for n1, n2 in edges:
        #Connect n1 to the node of n2
        dot.edge(str(id(n1)), str(id(n2)) + n2._op)

    return dot

L.grad = 1.0
f.grad = 4.0
d.grad = -2.0
c.grad = -2.0
e.grad = -2.0
a.grad = 6.0
b.grad = -4.0

draw_dot(L)

a.data += 0.01 * a.grad
b.data += 0.01 * b.grad
c.data += 0.01 * c.grad
f.data += 0.01 * f.grad

e = a*b;
d= e + c;
L = d*f;
L

print(L.data)

-6.723584000000001