Using En-VI checkpoint to evaluate, not found in checkpoint

[posenhuang]

Hi, when I used the provided checkpoints to evaluate EN-VI tasks, I encounter the following error. NotFoundError (see above for traceback): Key dynamic_seq2seq/decoder/multi_rnn_cell/cell_0/basic_lstm_cell/bias not found in checkpoint [[Node: save/RestoreV2_1 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_arg_save/Const_0_0, save/RestoreV2_1/tensor_names, save/RestoreV2_1/shape_and_slices)]] [[Node: save/Assign/_24 = _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_59_save/Assign", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/gpu:0"]()]] Here is the script I used to run it: python -m nmt.nmt \ --src=en --tgt=vi \ --ckpt=deen_model_1/translate.ckpt \ --hparams_path=nmt/standard_hparams/iwslt15.json.json \ --out_dir=out/deen_model_1 \ --vocab_prefix=data/vocab \ --inference_input_file=data/tst2013.en \ --inference_output_file=out/tst2013_infer \ --inference_ref_file=data/tst2013.vi

I am using tensorflow 1.2.1, code in tf-1.2 branch, and python 2.7. I wonder what version should I use to use the checkpoints. Thanks!

[inspurasc]

Can you resolve this problem. I also met the same error. I am using tensorflow 1.8.0, and python27.