Report error for batched prediction about e2e-coref

[roger1993]

BTW, I've created a file where each line is in the exactly same json format with the sample in the readme and I also have changed the eval_path to the test file address which belongs to the final area in the experiments.conf

[roger1993]

This issue has been solved by downloading a new document to replace the old one which is empty

[dungtn]

Hi @roger1993, I've got the same error

InvalidArgumentError (see above for traceback): Restoring from checkpoint failed. This is most likely due to a mismatch between the current graph and the graph from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error:
Assign requires shapes of both tensors to match. lhs shape= [1,8] rhs shape= [115,8]
[[node save_2/Assign_2 (defined at .../e2e-coref/coref_model.py:90) = Assign[T=DT_FLOAT, _class=["loc:@char_embeddings"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/device:GPU:0"](char_embeddings, save_2/RestoreV2/_9)]]

What document did you replace to resolve this?

All the best!