Open unshaven opened 5 years ago
thank for your good work~ when I train the model on MLT dataset,I got the error. can you tell me how can i handle it? thanks
InvalidArgumentError (see above for traceback): Labels length is zero in batch 26 [[Node: model_2/CTCLoss = CTCLoss[ctc_merge_repeated=true, ignore_longer_outputs_than_inputs=true, preprocess_collapse_repeated=false, _device="/job:localhost/replica:0/task:0/device:CPU:0"](model_2/lstmLayers/fc/BiasAdd/_19615, _arg_model_2/input_btags/indices_0_32, _arg_model_2/input_btags/values_0_34, model_2/Cast/_19617)]] [[Node: model_2/CTCLoss/_19621 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device_incarnation=1, tensor_name="edge_49165_model_2/CTCLoss", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:GPU:0"]()]]
thank for your good work~ when I train the model on MLT dataset,I got the error. can you tell me how can i handle it? thanks
InvalidArgumentError (see above for traceback): Labels length is zero in batch 26 [[Node: model_2/CTCLoss = CTCLoss[ctc_merge_repeated=true, ignore_longer_outputs_than_inputs=true, preprocess_collapse_repeated=false, _device="/job:localhost/replica:0/task:0/device:CPU:0"](model_2/lstmLayers/fc/BiasAdd/_19615, _arg_model_2/input_btags/indices_0_32, _arg_model_2/input_btags/values_0_34, model_2/Cast/_19617)]] [[Node: model_2/CTCLoss/_19621 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device_incarnation=1, tensor_name="edge_49165_model_2/CTCLoss", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:GPU:0"]()]]