pytorch embedding层报错index out of range in self

使用pytorch时，数据过embedding层时报错：

Traceback (most recent call last):
  File "C:/Users/gaosiqi/PycharmProjects/DeepFM/main.py", line 68, in 
    out = model(train_data)
  File "C:\Anaconda3\envs\tensorflow\lib\site-packages\torch\nn\modules\module.py", line 722, in _call_impl
    result = self.forward(*input, **kwargs)
  File "C:/Users/gaosiqi/PycharmProjects/DeepFM/main.py", line 26, in forward
    embedding = self.word_embedding(x)
  File "C:\Anaconda3\envs\tensorflow\lib\site-packages\torch\nn\modules\module.py", line 722, in _call_impl
    result = self.forward(*input, **kwargs)
  File "C:\Anaconda3\envs\tensorflow\lib\site-packages\torch\nn\modules\sparse.py", line 126, in forward
    self.norm_type, self.scale_grad_by_freq, self.sparse)
  File "C:\Anaconda3\envs\tensorflow\lib\site-packages\torch\nn\functional.py", line 1814, in embedding
    return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
IndexError: index out of range in self

原因是输入进embedding层的数据并不是经过词典映射的，而是原始数据，因此张量内部有超出embedding层合法范围的数。

embedding层需检查张量内部具体值的大小，并确保它们的值在有效范围内[0, num_embeddings-1]。例如此次出错就是张量内最大值是30000+，最小是-2，因此这两种过大和过小的值就引起问题。

再例如：

train_data = [[1,-1,1,1,2,2,2,3,4,23,2,3,1,2,2,2],
			[4,3,2,5,3,2,8,9,3,66,7,7,4,3,2,3]]

用

print(train_data.max())  #（已转变为张量后）
print(train_data.min())

来检查张量内部的最大最小值

此时会报错：

如果我们将大于num_embeddings和小于0的值都改掉看看：

train_data = [[1,1,1,1,2,2,2,3,4,2,2,3,1,2,2,2],
              [4,3,2,5,3,2,8,9,3,6,7,7,4,3,2,3]]

此时就顺利经过了embedding层，并且得到了嵌入层的结果：

正确使用embedding层示例：

from collections import Counter
import torch.nn as nn

# Let's say you have 2 sentences(lowercased, punctuations removed) :
sentences = "i am new to PyTorch i am having fun"
words = sentences.split(' ')

vocab = Counter(words)  # create a dictionary
vocab = sorted(vocab, key=vocab.get, reverse=True)
vocab_size = len(vocab)

# map words to unique indices
word2idx = {word: ind for ind, word in enumerate(vocab)}

# word2idx = {'i': 0, 'am': 1, 'new': 2, 'to': 3, 'pytorch': 4, 'having': 5, 'fun': 6}

encoded_sentences = [word2idx[word] for word in words]

# encoded_sentences = [0, 1, 2, 3, 4, 0, 1, 5, 6]
print(encoded_sentences)
# let's say you want embedding dimension to be 3
emb_dim = 3