1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
| import math
import random
from sklearn.tree import export_graphviz
from graphviz import Digraph
def trace(root):
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'})
nodes, edges = trace(root)
for n in nodes:
uid = str(id(n))
dot.node(name = uid, label = "{ %s | %.4f | grad %.4f }" % (n.label, n.data, n.grad), shape='record')
if n._op:
dot.node(name = uid + n._op, label = n._op)
dot.edge(uid + n._op, uid)
for n1, n2 in edges:
dot.edge(str(id(n1)), str(id(n2)) + n2._op)
dot.save('output.dot')
return dot
class Value:
def __init__(self, data, _children=(), _op='', label=''):
self.data = data
self.grad = 0.0
self._backward = lambda: None
self._prev = set(_children)
self._op = _op
self.label = label
def __repr__(self):
return f"Value(data={self.data})"
def __add__(self, other):
other = other if isinstance(other, Value) else Value(other)
out = Value(self.data + other.data, (self, other), '+')
def _backward():
self.grad += 1.0 * out.grad
other.grad += 1.0 * out.grad
out._backward = _backward
return out
def __mul__(self, other):
other = other if isinstance(other, Value) else Value(other)
out = Value(self.data * other.data, (self, other), '*')
def _backward():
self.grad += other.data * out.grad
other.grad += self.data * out.grad
out._backward = _backward
return out
def __pow__(self, other):
assert isinstance(other, (int, float)), "only supporting int/float powers for now"
out = Value(self.data**other, (self,), f'**{other}')
def _backward():
self.grad += other * (self.data ** (other - 1)) * out.grad
out._backward = _backward
return out
def __rmul__(self, other):
return self * other
def __truediv__(self, other):
return self * other**-1
def __neg__(self):
return self * -1
def __sub__(self, other):
return self + (-other)
def __radd__(self, other):
return self + other
def tanh(self):
x = self.data
t = (math.exp(2*x) - 1)/(math.exp(2*x) + 1)
out = Value(t, (self, ), 'tanh')
def _backward():
self.grad += (1 - t**2) * out.grad
out._backward = _backward
return out
def exp(self):
x = self.data
out = Value(math.exp(x), (self, ), 'exp')
def _backward():
self.grad += out.data * out.grad
out._backward = _backward
return out
def backward(self):
topo = []
visited = set()
def build_topo(v):
if v not in visited:
visited.add(v)
for child in v._prev:
build_topo(child)
topo.append(v)
build_topo(self)
self.grad = 1.0
for node in reversed(topo):
node._backward()
class Neuron:
def __init__(self, nin):
self.w = [Value(random.uniform(-1,1)) for _ in range(nin)]
self.b = Value(random.uniform(-1,1))
def __call__(self, x):
act = sum((wi*xi for wi,xi in zip(self.w,x)), self.b)
out = act.tanh()
return out
def parameters(self):
return self.w + [self.b]
class Layer:
def __init__(self, nin, nout):
self.neurons = [Neuron(nin) for _ in range(nout)]
def __call__(self, x):
outs = [n(x) for n in self.neurons]
return outs[0] if len(outs) == 1 else outs
def parameters(self):
return [p for neuron in self.neurons for p in neuron.parameters()]
class MLP:
def __init__(self, nin, nouts):
sz = [nin] + nouts
self.layers = [Layer(sz[i],sz[i+1]) for i in range(len(nouts))]
def __call__(self, x):
for layer in self.layers:
x = layer(x)
return x
def parameters(self):
return [p for layer in self.layers for p in layer.parameters()]
def main():
n = MLP(3, [4, 4, 1])
xs = [
[2.0, 3.0, -1.0],
[3.0, -1.0, 0.5],
[0.5, 1.0, 1.0],
[1.0, 1.0, -1.0],
]
ys = [1.0, -1.0, -1.0, 1.0]
for k in range(20):
ypred = [n(x) for x in xs]
loss = sum((yout - ygt)**2 for ygt, yout in zip(ys, ypred))
for p in n.parameters():
p.grad = 0.0
loss.backward()
for p in n.parameters():
p.data += -0.1 * p.grad
print(k, loss.data)
print(ypred)
main()
|
