Yang Qinjuan comments

Repositories
Issues
Comments

Results 3 comments of


                                            Yang Qinjuan

ValueError: shapes must be equal rank, but are 0 and 3 for 'onnx_tf_prefix_Where_1751' (op: 'Select') with input:[32,1,120], [], [32,3072,120]

I got the similar problem when converting torch to tf through onnx with error: `ValueError: Shapes must be equal rank, but are 0 and 3 for 'onnx_tf_prefix_Where_118' (op: 'Select') with...

same problem. I add an embedding layer before the AttentionSeq2seq layer. Here is my code: `model = Sequential() model.add(Embedding(max_features, embedding_vector_dim, input_length=max_doc_length)) model.add(AttentionSeq2Seq(input_length=max_doc_length, input_dim=embedding_vector_dim, hidden_dim=hidden_dim, output_length=max_doc_length, output_dim=embedding_vector_dim)) model.compile(loss='mse', optimizer='adam')`

Yang Qinjuan

如何使用用户词典？

ValueError: shapes must be equal rank, but are 0 and 3 for 'onnx_tf_prefix_Where_1751' (op: 'Select') with input:[32,1,120], [], [32,3072,120]

AttentionSeq2Seq error