Spaces:
Sleeping
Sleeping
File size: 4,650 Bytes
9cecb44 |
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 |
import random
import math
import json
INPUTS = [[0,0],[0,1],[1,0],[1,1]]
OUTPUTS = [[0],[1],[1],[0]]
EPOCHS = 1000000
ALPHAS = 20
WEPOCHS = EPOCHS // 100
VARIANCE_W = 0.5
VARIANCE_B = 0
w11 = random.uniform(-VARIANCE_W,VARIANCE_W)
w21 = random.uniform(-VARIANCE_W,VARIANCE_W)
b1 = VARIANCE_B
w12 = random.uniform(-VARIANCE_W,VARIANCE_W)
w22 = random.uniform(-VARIANCE_W,VARIANCE_W)
b2 = VARIANCE_B
w13 = random.uniform(-VARIANCE_W,VARIANCE_W)
w23 = random.uniform(-VARIANCE_W,VARIANCE_W)
b3 = VARIANCE_B
o1 = random.uniform(-VARIANCE_W,VARIANCE_W)
o2 = random.uniform(-VARIANCE_W,VARIANCE_W)
o3 = random.uniform(-VARIANCE_W,VARIANCE_W)
ob = VARIANCE_B
## Tudo a 0.5
# VARIANCE_W = 0.5
# VARIANCE_B = 1
# w11 = VARIANCE_W
# w21 = VARIANCE_W
# b1 = VARIANCE_B
# w12 = VARIANCE_W
# w22 = VARIANCE_W
# b2 = VARIANCE_B
# w13 = VARIANCE_W
# w23 = VARIANCE_W
# b3 = VARIANCE_B
# o1 = VARIANCE_W
# o2 = VARIANCE_W
# o3 = VARIANCE_W
# ob = VARIANCE_B
def sigmoid(x):
return 1.0 / (1.0 + math.exp(-x))
def sigmoid_prime(x): # x already sigmoided
return x * (1 - x)
def relu(x):
return max(0,x)
def relu_prime(x):
return 1 if x>0 else 0
def tanh(x):
return math.tanh(x)
def tanh_prime(x):
return 1 - x**2
def softmax(x):
return math.exp(x) / (math.exp(x) + 1)
def softmax_prime(x):
return x * (1 - x)
def predict(i1, i2, activation=sigmoid):
s1 = w11 * i1 + w21 * i2 + b1
# s1 = sigmoid(s1)
s1 = activation(s1)
s2 = w12 * i1 + w22 * i2 + b2
# s2 = sigmoid(s2)
s2 = activation(s2)
s3 = w13 * i1 + w23 * i2 + b3
# s3 = sigmoid(s3)
s3 = activation(s3)
output = s1 * o1 + s2 * o2 + s3 * o3 + ob
# output = sigmoid(output)
output = activation(output)
return output
def learn(i1,i2,target, activation, activation_prime, alpha=0.2):
global w11,w21,b1,w12,w22,b2,w13,w23,b3
global o1,o2,o3,ob
s1 = w11 * i1 + w21 * i2 + b1
# s1 = sigmoid(s1)
s1 = activation(s1)
s2 = w12 * i1 + w22 * i2 + b2
# s2 = sigmoid(s2)
s2 = activation(s2)
s3 = w13 * i1 + w23 * i2 + b3
# s3 = sigmoid(s3)
s3 = activation(s3)
output = s1 * o1 + s2 * o2 + s3 * o3 + ob
# output = sigmoid(output)
output = activation(output)
error = target - output
# derror = error * sigmoid_prime(output)
derror = error * activation_prime(output)
# ds1 = derror * o1 * sigmoid_prime(s1)
ds1 = derror * o1 * activation_prime(s1)
# ds2 = derror * o2 * sigmoid_prime(s2)
ds2 = derror * o2 * activation_prime(s2)
# ds3 = derror * o3 * sigmoid_prime(s3)
ds3 = derror * o3 * activation_prime(s3)
o1 += alpha * s1 * derror
o2 += alpha * s2 * derror
o3 += alpha * s3 * derror
ob += alpha * derror
w11 += alpha * i1 * ds1
w21 += alpha * i2 * ds1
b1 += alpha * ds1
w12 += alpha * i1 * ds2
w22 += alpha * i2 * ds2
b2 += alpha * ds2
w13 += alpha * i1 * ds3
w23 += alpha * i2 * ds3
b3 += alpha * ds3
def train(epochs=EPOCHS, alpha=ALPHAS):
modelo = None
for epoch in range(1,epochs+1):
indexes = [0,1,2,3]
random.shuffle(indexes)
for j in indexes:
learn(INPUTS[j][0],INPUTS[j][1],OUTPUTS[j][0], activation=sigmoid, activation_prime=sigmoid_prime, alpha=alpha)
if epoch%WEPOCHS == 0:
cost = 0
for j in range(4):
o = predict(INPUTS[j][0],INPUTS[j][1], activation=sigmoid)
cost += (OUTPUTS[j][0] - o) ** 2
cost /= 4
print("epoch", epoch, "mean squared error:", cost)
modelo = {
"w11": w11,
"w21": w21,
"b1": b1,
"w12": w12,
"w22": w22,
"b2": b2,
"w13": w13,
"w23": w23,
"b3": b3,
"o1": o1,
"o2": o2,
"o3": o3,
"ob": ob
}
return modelo
def save_model(modelo, filename):
with open(filename, 'w') as json_file:
json.dump(modelo, json_file)
## Main
def main():
# Train model
modelo = train()
print(modelo)
# Save model to file
save_model(modelo, "modelo.json")
for i in range(4):
result = predict(INPUTS[i][0],INPUTS[i][1], activation=sigmoid)
print("for input", INPUTS[i], "expected", OUTPUTS[i][0], "predicted", f"{result:4.4}", "which is", "correct" if round(result)==OUTPUTS[i][0] else "incorrect")
# print("for input", INPUTS[i], "expected", OUTPUTS[i][0], "predicted", result, "which is", "correct" if round(result)==OUTPUTS[i][0] else "incorrect")
if __name__ == "__main__":
main() |