0
我使用TensorFlow來實現本文所述的卷積遞歸神經網絡:Arxiv。FailedPreconditionError:sequence_length(0)<= X
我所有的代碼可以在這裏找到:crnn
所以我加載各種長度的訓練樣本的X號。加載訓練集時,我將其大小調整爲32x2000。當把他們送進了神經網絡,TensorFlow引發此錯誤:
tensorflow.python.framework.errors_impl.FailedPreconditionError: sequence_length(0) <= 124
[[Node: CTCBeamSearchDecoder = CTCBeamSearchDecoder[beam_width=100, merge_repeated=true, top_paths=1, _device="/job:localhost/replica:0/task:0/cpu:0"](transpose/_3, _recv_seq_len_0)]]
[[Node: CTCLoss/_5 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/gpu:0", send_device="/job:localhost/replica:0/task:0/cpu:0", send_device_incarnation=1, tensor_name="edge_758_CTCLoss", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
奇怪的是,我沒有得到很多在谷歌搜索結果的,所以我認爲這是值得詢問。
值得注意的是,我的代碼或數據中沒有124位,所以我很困惑。