FizzBuzz是一个简单的小游戏。游戏规则如下:从1开始往上数数,当遇到3的倍数的时候,说fizz,当遇到5的倍数,说buzz,当遇到15的倍数,就说fizzbuzz,其他情况下则正常数数。
我们可以写一个简单的小程序来决定要返回正常数值还是fizz, buzz 或者 fizzbuzz。
代码:
# One-hot encode the desired outputs: [number, "fizz", "buzz", "fizzbuzz"]
def fizz_buzz_encode(i):
if i % 15 == 0: return 3
elif i % 5 == 0: return 2
elif i % 3 == 0: return 1
else: return 0
def fizz_buzz_decode(i, prediction):
return [str(i), "fizz", "buzz", "fizzbuzz"][prediction]
print(fizz_buzz_decode(1, fizz_buzz_encode(1)))
print(fizz_buzz_decode(2, fizz_buzz_encode(2)))
print(fizz_buzz_decode(5, fizz_buzz_encode(5)))
print(fizz_buzz_decode(12, fizz_buzz_encode(12)))
print(fizz_buzz_decode(15, fizz_buzz_encode(15)))
结果:
1
2
buzz
fizz
fizzbuzz
我们首先定义模型的输入与输出(训练数据)
代码:
import numpy as np
import torch
NUM_DIGITS = 10
# Represent each input by an array of its binary digits.
def binary_encode(i, num_digits):
return np.array([i >> d & 1 for d in range(num_digits)])
trX = torch.Tensor([binary_encode(i, NUM_DIGITS) for i in range(101, 2 ** NUM_DIGITS)])
trY = torch.LongTensor([fizz_buzz_encode(i) for i in range(101, 2 ** NUM_DIGITS)])
然后我们用PyTorch定义模型
代码:
# Define the model
NUM_HIDDEN = 100
model = torch.nn.Sequential(
torch.nn.Linear(NUM_DIGITS, NUM_HIDDEN),
torch.nn.ReLU(),
torch.nn.Linear(NUM_HIDDEN, 4)
)
代码:
loss_fn = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr = 0.05)
以下是模型的训练代码
代码:
# Start training it
BATCH_SIZE = 128
for epoch in range(10000):
for start in range(0, len(trX), BATCH_SIZE):
end = start + BATCH_SIZE
batchX = trX[start:end]
batchY = trY[start:end]
y_pred = model(batchX)
loss = loss_fn(y_pred, batchY)
optimizer.zero_grad()
loss.backward()
optimizer.step()
# Find loss on training data
loss = loss_fn(model(trX), trY).item()
print(‘Epoch:‘, epoch, ‘Loss:‘, loss)
最后我们用训练好的模型尝试在1到100这些数字上玩FizzBuzz游戏
代码:
# Output now
testX = torch.Tensor([binary_encode(i, NUM_DIGITS) for i in range(1, 101)])
with torch.no_grad():
testY = model(testX)
predictions = zip(range(1, 101), list(testY.max(1)[1].data.tolist()))
print([fizz_buzz_decode(i, x) for (i, x) in predictions])
结果:
[‘1‘, ‘2‘, ‘fizz‘, ‘fizz‘, ‘buzz‘, ‘fizz‘, ‘7‘, ‘8‘, ‘fizz‘, ‘buzz‘, ‘11‘, ‘12‘, ‘13‘, ‘14‘, ‘fizzbuzz‘, ‘16‘, ‘17‘, ‘fizz‘, ‘19‘, ‘buzz‘, ‘fizz‘, ‘fizz‘, ‘fizz‘, ‘fizz‘, ‘buzz‘, ‘26‘, ‘fizz‘, ‘28‘, ‘29‘, ‘30‘, ‘31‘, ‘32‘, ‘fizz‘, ‘34‘, ‘buzz‘, ‘fizz‘, ‘37‘, ‘38‘, ‘fizz‘, ‘buzz‘, ‘41‘, ‘fizz‘, ‘43‘, ‘44‘, ‘fizzbuzz‘, ‘46‘, ‘47‘, ‘fizz‘, ‘fizz‘, ‘buzz‘, ‘fizz‘, ‘52‘, ‘53‘, ‘fizz‘, ‘buzz‘, ‘fizz‘, ‘fizz‘, ‘58‘, ‘59‘, ‘fizzbuzz‘, ‘61‘, ‘62‘, ‘fizz‘, ‘64‘, ‘buzz‘, ‘fizz‘, ‘67‘, ‘fizz‘, ‘fizz‘, ‘buzz‘, ‘71‘, ‘72‘, ‘73‘, ‘74‘, ‘fizzbuzz‘, ‘76‘, ‘fizz‘, ‘fizz‘, ‘fizz‘, ‘buzz‘, ‘fizz‘, ‘82‘, ‘83‘, ‘fizz‘, ‘buzz‘, ‘86‘, ‘fizz‘, ‘88‘, ‘89‘, ‘90‘, ‘91‘, ‘92‘, ‘fizz‘, ‘94‘, ‘buzz‘, ‘fizz‘, ‘97‘, ‘98‘, ‘fizz‘, ‘buzz‘]
代码:
print(np.sum(testY.max(1)[1].numpy() == np.array([fizz_buzz_encode(i) for i in range(1,101)])))
testY.max(1)[1].numpy() == np.array([fizz_buzz_encode(i) for i in range(1,101)])
结果:
88
array([ True, True, True, False, True, True, True, True, True,
True, True, False, True, True, True, True, True, True,
True, True, True, False, False, True, True, True, True,
True, True, False, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, False, True, True, True, True, True,
True, False, True, True, True, True, True, True, True,
True, True, True, True, False, True, True, True, False,
True, True, True, True, False, True, False, True, True,
True, True, True, True, True, True, True, True, False,
True, True, True, True, True, True, True, True, True,
True])
原文:https://www.cnblogs.com/luedong/p/14588280.html