我正在尝试将 facebooks 的快速文本模型转换为 tensorflow-hub 格式。为此，我附上了两个主要文件。
def _compute_ngrams(word, min_n=1, max_n=3):
BOW, EOW = ('<', '>') # Used by FastText to attach to all words as prefix and suffix
ngrams = [] # batch_size, n_words, maxlen
shape = word.shape # batch_size, n_sentenes, n_words
maxlen = 0
for b in range(shape[0]): # batch
ngram_b = []
for w in word[b]:
ngram = []
extended_word = BOW + "".join( chr(x) for x in bytearray(w)) + EOW
if w.decode("utf-8") not in global_vocab:
for ngram_length in range(min_n, min(len(extended_word), max_n) + 1):
for i in range(0, len(extended_word) - ngram_length + 1):
ngram.append(extended_word[i:i + ngram_length])
else:
ngram.append(w.decode("utf-8") )
ngram_b.append(ngram)
maxlen = max(maxlen, len(ngram))
ngrams.append(ngram_b)
for batches in ngrams:
for words in batches:
temp = maxlen
r = []
while temp > len(words):
r.append("UNK")
temp = temp - 1
words.extend(r)
return ngrams
def make_module_spec(vocabulary_file, vocab_size, embeddings_dim=300,
num_oov_buckets=1):
def module_fn():
"""Spec function for a token embedding module."""
words = tf.placeholder(shape=[None, None], dtype=tf.string, name="tokens")
tokens = tf.py_func(_compute_ngrams, [words], tf.string)
embeddings_var = tf.get_variable(
initializer=tf.zeros([vocab_size + num_oov_buckets, embeddings_dim]),
name=EMBEDDINGS_VAR_NAME,
dtype=tf.float32
)
lookup_table = tf.contrib.lookup.index_table_from_file(
vocabulary_file=vocabulary_file,
num_oov_buckets=num_oov_buckets,
)
ids = lookup_table.lookup(tokens)
#combined_embedding = tf.reduce_mean(tf.nn.embedding_lookup(params=embeddings_var, ids=ids), axis=2)
combined_embedding = tf.nn.embedding_lookup(params=embeddings_var, ids=ids)
hub.add_signature("default", {"tokens": words},
{"default": combined_embedding})
return hub.create_module_spec(module_fn)
该模型是按预期使用 tf-hub 格式创建的。
但是当我尝试使用上面创建的模型时，我得到了这个错误。
下面附上使用上面创建的 tf-hub 模型的示例测试代码。
with tf.Graph().as_default():
module_url = "/home/sahil_wadhwa/tf-hub/tf_sent"
embed = hub.Module(module_url)
embeddings = embed([["Indian", "American"], ["Hello", "World"]])
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
sess.run(tf.tables_initializer())
result = sess.run(embeddings)
print(result)
print(result.shape)
我得到的错误在这里。
Traceback (most recent call last):
File "/home/sahil_wadhwa/.local/lib/python3.6/site-packages/tensorflow/python/ops/script_ops.py", line 195, in __call__
raise ValueError("callback %s is not found" % token)
ValueError: callback pyfunc_0 is not found
[[{{node module_apply_default/PyFunc}} = PyFunc[Tin=[DT_STRING], Tout=[DT_STRING], token="pyfunc_0", _device="/job:localhost/replica:0/task:0/device:CPU:0"](Const)]]
被这个问题困扰了很长时间，这里的任何帮助都会很有用。
提前致谢。