使用PyTorch进行深度学习

# Author: Robert Guthrie

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim

torch.manual_seed(1)

lin = nn.Linear(5, 3)  # maps from R^5 to R^3, parameters A, b
# data is 2x5.  A maps from 5 to 3... can we map "data" under A?
data = torch.randn(2, 5)
print(lin(data))  # yes

tensor([[ 0.1755, -0.3268, -0.5069],
        [-0.6602,  0.2260,  0.1089]], grad_fn=)

# In pytorch, most non-linearities are in torch.functional (we have it imported as F)
# Note that non-linearites typically don't have parameters like affine maps do.
# That is, they don't have weights that are updated during training.
data = torch.randn(2, 2)
print(data)
print(F.relu(data))

tensor([[-0.5404, -2.2102],
        [ 2.1130, -0.0040]])
tensor([[0.0000, 0.0000],
        [2.1130, 0.0000]])

# Softmax is also in torch.nn.functional
data = torch.randn(5)
print(data)
print(F.softmax(data, dim=0))
print(F.softmax(data, dim=0).sum())  # Sums to 1 because it is a distribution!
print(F.log_softmax(data, dim=0))  # theres also log_softmax

tensor([ 1.3800, -1.3505,  0.3455,  0.5046,  1.8213])
tensor([0.2948, 0.0192, 0.1048, 0.1228, 0.4584])
tensor(1.)
tensor([-1.2214, -3.9519, -2.2560, -2.0969, -0.7801])

[4,0]

[2,2]

[Count(hello),Count(world)]

data = [("me gusta comer en la cafeteria".split(), "SPANISH"),
        ("Give it to me".split(), "ENGLISH"),
        ("No creo que sea una buena idea".split(), "SPANISH"),
        ("No it is not a good idea to get lost at sea".split(), "ENGLISH")]

test_data = [("Yo creo que si".split(), "SPANISH"),
             ("it is lost on me".split(), "ENGLISH")]

# word_to_ix maps each word in the vocab to a unique integer, which will be its
# index into the Bag of words vector
word_to_ix = {}
for sent, _ in data + test_data:
    for word in sent:
        if word not in word_to_ix:
            word_to_ix[word] = len(word_to_ix)
print(word_to_ix)

VOCAB_SIZE = len(word_to_ix)
NUM_LABELS = 2

class BoWClassifier(nn.Module):  # inheriting from nn.Module!

    def __init__(self, num_labels, vocab_size):
        # calls the init function of nn.Module.  Dont get confused by syntax,
        # just always do it in an nn.Module
        super(BoWClassifier, self).__init__()

        # Define the parameters that you will need.  In this case, we need A and b,
        # the parameters of the affine mapping.
        # Torch defines nn.Linear(), which provides the affine map.
        # Make sure you understand why the input dimension is vocab_size
        # and the output is num_labels!
        self.linear = nn.Linear(vocab_size, num_labels)

        # NOTE! The non-linearity log softmax does not have parameters! So we don't need
        # to worry about that here

    def forward(self, bow_vec):
        # Pass the input through the linear layer,
        # then pass that through log_softmax.
        # Many non-linearities and other functions are in torch.nn.functional
        return F.log_softmax(self.linear(bow_vec), dim=1)

def make_bow_vector(sentence, word_to_ix):
    vec = torch.zeros(len(word_to_ix))
    for word in sentence:
        vec[word_to_ix[word]] += 1
    return vec.view(1, -1)

def make_target(label, label_to_ix):
    return torch.LongTensor([label_to_ix[label]])

model = BoWClassifier(NUM_LABELS, VOCAB_SIZE)

# the model knows its parameters.  The first output below is A, the second is b.
# Whenever you assign a component to a class variable in the __init__ function
# of a module, which was done with the line
# self.linear = nn.Linear(...)
# Then through some Python magic from the PyTorch devs, your module
# (in this case, BoWClassifier) will store knowledge of the nn.Linear's parameters
for param in model.parameters():
    print(param)

# To run the model, pass in a BoW vector
# Here we don't need to train, so the code is wrapped in torch.no_grad()
with torch.no_grad():
    sample = data[0]
    bow_vector = make_bow_vector(sample[0], word_to_ix)
    log_probs = model(bow_vector)
    print(log_probs)

{'me': 0, 'gusta': 1, 'comer': 2, 'en': 3, 'la': 4, 'cafeteria': 5, 'Give': 6, 'it': 7, 'to': 8, 'No': 9, 'creo': 10, 'que': 11, 'sea': 12, 'una': 13, 'buena': 14, 'idea': 15, 'is': 16, 'not': 17, 'a': 18, 'good': 19, 'get': 20, 'lost': 21, 'at': 22, 'Yo': 23, 'si': 24, 'on': 25}
Parameter containing:
tensor([[ 0.1194,  0.0609, -0.1268,  0.1274,  0.1191,  0.1739, -0.1099, -0.0323,
         -0.0038,  0.0286, -0.1488, -0.1392,  0.1067, -0.0460,  0.0958,  0.0112,
          0.0644,  0.0431,  0.0713,  0.0972, -0.1816,  0.0987, -0.1379, -0.1480,
          0.0119, -0.0334],
        [ 0.1152, -0.1136, -0.1743,  0.1427, -0.0291,  0.1103,  0.0630, -0.1471,
          0.0394,  0.0471, -0.1313, -0.0931,  0.0669,  0.0351, -0.0834, -0.0594,
          0.1796, -0.0363,  0.1106,  0.0849, -0.1268, -0.1668,  0.1882,  0.0102,
          0.1344,  0.0406]], requires_grad=True)
Parameter containing:
tensor([0.0631, 0.1465], requires_grad=True)
tensor([[-0.5378, -0.8771]])

label_to_ix = {"SPANISH": 0, "ENGLISH": 1}

# Run on test data before we train, just to see a before-and-after
with torch.no_grad():
    for instance, label in test_data:
        bow_vec = make_bow_vector(instance, word_to_ix)
        log_probs = model(bow_vec)
        print(log_probs)

# Print the matrix column corresponding to "creo"
print(next(model.parameters())[:, word_to_ix["creo"]])

loss_function = nn.NLLLoss()
optimizer = optim.SGD(model.parameters(), lr=0.1)

# Usually you want to pass over the training data several times.
# 100 is much bigger than on a real data set, but real datasets have more than
# two instances.  Usually, somewhere between 5 and 30 epochs is reasonable.
for epoch in range(100):
    for instance, label in data:
        # Step 1\. Remember that PyTorch accumulates gradients.
        # We need to clear them out before each instance
        model.zero_grad()

        # Step 2\. Make our BOW vector and also we must wrap the target in a
        # Tensor as an integer. For example, if the target is SPANISH, then
        # we wrap the integer 0\. The loss function then knows that the 0th
        # element of the log probabilities is the log probability
        # corresponding to SPANISH
        bow_vec = make_bow_vector(instance, word_to_ix)
        target = make_target(label, label_to_ix)

        # Step 3\. Run our forward pass.
        log_probs = model(bow_vec)

        # Step 4\. Compute the loss, gradients, and update the parameters by
        # calling optimizer.step()
        loss = loss_function(log_probs, target)
        loss.backward()
        optimizer.step()

with torch.no_grad():
    for instance, label in test_data:
        bow_vec = make_bow_vector(instance, word_to_ix)
        log_probs = model(bow_vec)
        print(log_probs)

# Index corresponding to Spanish goes up, English goes down!
print(next(model.parameters())[:, word_to_ix["creo"]])

tensor([[-0.9297, -0.5020]])
tensor([[-0.6388, -0.7506]])
tensor([-0.1488, -0.1313], grad_fn=)
tensor([[-0.2093, -1.6669]])
tensor([[-2.5330, -0.0828]])
tensor([ 0.2803, -0.5605], grad_fn=)