Pytorch 相当于 tensorflow keras StringLookup?
Pytorch equivalent of tensorflow keras StringLookup?
我现在正在使用 pytorch,我缺少一个层:tf.keras.layers.StringLookup
帮助处理 id。有什么解决方法可以用 pytorch 做类似的事情吗?
我正在寻找的功能示例:
vocab = ["a", "b", "c", "d"]
data = tf.constant([["a", "c", "d"], ["d", "a", "b"]])
layer = tf.keras.layers.StringLookup(vocabulary=vocab)
layer(data)
Outputs:
<tf.Tensor: shape=(2, 3), dtype=int64, numpy=
array([[1, 3, 4],
[4, 1, 2]])>
你可以使用库 torchtext,
只需使用 python3 -m pip install torchtext
安装它
你可以这样:
from torchtext.vocab import vocab
from collections import OrderedDict
tokens = ['a', 'b', 'c', 'd']
v1 = vocab(OrderedDict([(token, 1) for token in tokens]))
v1.lookup_indices(["a","b","c"])
这是结果:
([0, 1, 2],)
软件包 tornlp,
pip install pytorch-nlp
from torchnlp.encoders import LabelEncoder
data = ["a", "c", "d", "e", "d"]
encoder = LabelEncoder(data, reserved_labels=['unknown'], unknown_index=0)
enl = encoder.batch_encode(data)
print(enl)
tensor([1, 2, 3, 4, 3])
您可以将 Collections.Counter
与 torchtext
的 vocab
对象一起使用,从您的词汇表中构造一个查找函数。然后,您可以轻松地将序列传递给它并将它们的编码作为张量获取:
from torchtext.vocab import vocab
from collections import Counter
tokens = ["a", "b", "c", "d"]
samples = [["a", "c", "d"], ["d", "a", "b"]]
# Build string lookup
lookup = vocab(Counter(tokens))
>>> torch.tensor([lookup(s) for s in samples])
tensor([[0, 2, 3],
[3, 0, 1]])
我现在正在使用 pytorch,我缺少一个层:tf.keras.layers.StringLookup
帮助处理 id。有什么解决方法可以用 pytorch 做类似的事情吗?
我正在寻找的功能示例:
vocab = ["a", "b", "c", "d"]
data = tf.constant([["a", "c", "d"], ["d", "a", "b"]])
layer = tf.keras.layers.StringLookup(vocabulary=vocab)
layer(data)
Outputs:
<tf.Tensor: shape=(2, 3), dtype=int64, numpy=
array([[1, 3, 4],
[4, 1, 2]])>
你可以使用库 torchtext, 只需使用 python3 -m pip install torchtext
安装它你可以这样:
from torchtext.vocab import vocab
from collections import OrderedDict
tokens = ['a', 'b', 'c', 'd']
v1 = vocab(OrderedDict([(token, 1) for token in tokens]))
v1.lookup_indices(["a","b","c"])
这是结果:
([0, 1, 2],)
软件包 tornlp,
pip install pytorch-nlp
from torchnlp.encoders import LabelEncoder
data = ["a", "c", "d", "e", "d"]
encoder = LabelEncoder(data, reserved_labels=['unknown'], unknown_index=0)
enl = encoder.batch_encode(data)
print(enl)
tensor([1, 2, 3, 4, 3])
您可以将 Collections.Counter
与 torchtext
的 vocab
对象一起使用,从您的词汇表中构造一个查找函数。然后,您可以轻松地将序列传递给它并将它们的编码作为张量获取:
from torchtext.vocab import vocab
from collections import Counter
tokens = ["a", "b", "c", "d"]
samples = [["a", "c", "d"], ["d", "a", "b"]]
# Build string lookup
lookup = vocab(Counter(tokens))
>>> torch.tensor([lookup(s) for s in samples])
tensor([[0, 2, 3],
[3, 0, 1]])