Python 无法使用tensorflow 1.15保存universal lite的tensorflow hub模型

使用universal lite 2（）的集线器模型训练数据后，我无法保存模型

我已将模型保存到本地

path ="C:/Users/771556/Downloads/ModelLiteUSE"  #url ="https://tfhub.dev/google/universal-sentence-encoder-lite/2"  liteModule = hub.Module(path)

input_placeholder = tf.sparse_placeholder(tf.int64, shape=[None, None])  encodings = liteModule(  inputs=dict(  values=input_placeholder.values,  indices=input_placeholder.indices,  dense_shape=input_placeholder.dense_shape))

with tf.Session() as sess:  spm_path = sess.run(liteModule(signature="spm_path"))

sp = spm.SentencePieceProcessor()  sp.Load(spm_path)  print("SentencePiece model loaded at {}.".format(spm_path))

def process_to_IDs_in_sparse_format(sp, sentences):    ids = [sp.EncodeAsIds(x) for x in sentences]  max_len = max(len(x) for x in ids)  dense_shape=(len(ids), max_len)  values=[item for sublist in ids for item in sublist]  indices=[[row,col] for row in range(len(ids)) for col in range(len(ids[row]))]  return (values, indices, dense_shape)

def embed(input):  values, indices, dense_shape = process_to_IDs_in_sparse_format(sp, input)  # Reduce logging output.  logging.set_verbosity(logging.ERROR)  with tf.Session() as session:  session.run([tf.global_variables_initializer(), tf.tables_initializer()])  message_embeddings = session.run(  encodings,  feed_dict={input_placeholder.values: values,  input_placeholder.indices: indices,  input_placeholder.dense_shape: dense_shape})  return message_embeddings  

tf.saved_model.save(TrainModel,'D:/liteTrainmodel')

训练数据

TrainModel= embed(file_data.text)

保存模式

path ="C:/Users/771556/Downloads/ModelLiteUSE"  #url ="https://tfhub.dev/google/universal-sentence-encoder-lite/2"  liteModule = hub.Module(path)

input_placeholder = tf.sparse_placeholder(tf.int64, shape=[None, None])  encodings = liteModule(  inputs=dict(  values=input_placeholder.values,  indices=input_placeholder.indices,  dense_shape=input_placeholder.dense_shape))

with tf.Session() as sess:  spm_path = sess.run(liteModule(signature="spm_path"))

sp = spm.SentencePieceProcessor()  sp.Load(spm_path)  print("SentencePiece model loaded at {}.".format(spm_path))

def process_to_IDs_in_sparse_format(sp, sentences):    ids = [sp.EncodeAsIds(x) for x in sentences]  max_len = max(len(x) for x in ids)  dense_shape=(len(ids), max_len)  values=[item for sublist in ids for item in sublist]  indices=[[row,col] for row in range(len(ids)) for col in range(len(ids[row]))]  return (values, indices, dense_shape)

def embed(input):  values, indices, dense_shape = process_to_IDs_in_sparse_format(sp, input)  # Reduce logging output.  logging.set_verbosity(logging.ERROR)  with tf.Session() as session:  session.run([tf.global_variables_initializer(), tf.tables_initializer()])  message_embeddings = session.run(  encodings,  feed_dict={input_placeholder.values: values,  input_placeholder.indices: indices,  input_placeholder.dense_shape: dense_shape})  return message_embeddings  

tf.saved_model.save(TrainModel,'D:/liteTrainmodel')

错误

---

请正确设置您的格式。如何设置，如果您知道，请共享代码。请查找Colab url:@ZayedRais，我已经查看了您的Colab，发现没有这样的模型。您可以定义一个模型，然后尝试保存它。如果不想定义模型。你能解释一下你到底想达到什么目的吗？这样我们就可以帮助你了？谢谢