pyTorch 用深度学习玩FizzBuzz游戏 —— 动手学深度学习03

游戏规则

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。

# 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):
    
    #[str(i), "fizz", "buzz", "fizzbuzz"]为一个列表，里面有4个元素，对应为四类，可用索引来访问
    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)))

定义输入输出数据

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)])

pytorch 定义模型

# 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)
)

定义损失函数和优化器

loss_fn = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr = 0.05)

模型训练代码

# 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)

玩玩FizzBuzz 游戏看看效果

# 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])