Closed ravikrn closed 5 years ago
This is an indexing error where there vocabulary file is longer then the pretrained softmax matrix. Make sure the vocabulary file, vocabulary size in the options file, and checkpoint are all consistent between pretraining and fine tuning.
InvalidArgumentError (see above for traceback): indices[0] = 1043672 is not in [0, 793471)
I am using new dataset as per the instructions and I am getting this error. Could you please help me.
Traceback (most recent call last): File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 1334, in _do_call return fn(*args) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 1319, in _run_fn options, feed_dict, fetch_list, target_list, run_metadata) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 1407, in _call_tf_sessionrun run_metadata) tensorflow.python.framework.errors_impl.InvalidArgumentError: indices[0] = 1043672 is not in [0, 793471) [[{{node lm/sampled_softmax_loss_1/embedding_lookup_1}}]] [[{{node clip_by_global_norm/clip_by_global_norm/_8}}]]
During handling of the above exception, another exception occurred:
Traceback (most recent call last): File "bin/restart.py", line 57, in
main(args)
File "bin/restart.py", line 42, in main
restart_ckpt_file=ckpt_file)
File "/usr/local/lib/python3.6/dist-packages/bilm-0.1.post5-py3.6.egg/bilm/training.py", line 861, in train
feed_dict=feed_dict
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 929, in run
run_metadata_ptr)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 1152, in _run
feed_dict_tensor, options, run_metadata)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 1328, in _do_run
run_metadata)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 1348, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: indices[0] = 1043672 is not in [0, 793471)
[[node lm/sampled_softmax_loss_1/embedding_lookup_1 (defined at /usr/local/lib/python3.6/dist-packages/bilm-0.1.post5-py3.6.egg/bilm/training.py:506) ]]
[[node clip_by_global_norm/clip_by_global_norm/_8 (defined at /usr/local/lib/python3.6/dist-packages/bilm-0.1.post5-py3.6.egg/bilm/training.py:913) ]]
Caused by op 'lm/sampled_softmax_loss_1/embedding_lookup_1', defined at: File "bin/restart.py", line 57, in
main(args)
File "bin/restart.py", line 42, in main
restart_ckpt_file=ckpt_file)
File "/usr/local/lib/python3.6/dist-packages/bilm-0.1.post5-py3.6.egg/bilm/training.py", line 705, in train
model = LanguageModel(options, True)
File "/usr/local/lib/python3.6/dist-packages/bilm-0.1.post5-py3.6.egg/bilm/training.py", line 72, in init
self._build()
File "/usr/local/lib/python3.6/dist-packages/bilm-0.1.post5-py3.6.egg/bilm/training.py", line 430, in _build
self._build_loss(lstm_outputs)
File "/usr/local/lib/python3.6/dist-packages/bilm-0.1.post5-py3.6.egg/bilm/training.py", line 506, in _build_loss
num_true=1)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/nn_impl.py", line 1864, in sampled_softmax_loss
seed=seed)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/nn_impl.py", line 1399, in _compute_sampled_logits
biases, all_ids, partition_strategy=partition_strategy)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/embedding_ops.py", line 316, in embedding_lookup
transform_fn=None)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/embedding_ops.py", line 133, in _embedding_lookup_and_transform
result = _clip(array_ops.gather(params[0], ids, name=name),
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/util/dispatch.py", line 180, in wrapper
return target(*args, *kwargs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/array_ops.py", line 3273, in gather
return gen_array_ops.gather_v2(params, indices, axis, name=name)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/gen_array_ops.py", line 3748, in gather_v2
"GatherV2", params=params, indices=indices, axis=axis, name=name)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/op_def_library.py", line 788, in _apply_op_helper
op_def=op_def)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/util/deprecation.py", line 507, in new_func
return func(args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py", line 3300, in create_op
op_def=op_def)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py", line 1801, in init
self._traceback = tf_stack.extract_stack()
InvalidArgumentError (see above for traceback): indices[0] = 1043672 is not in [0, 793471) [[node lm/sampled_softmax_loss_1/embedding_lookup_1 (defined at /usr/local/lib/python3.6/dist-packages/bilm-0.1.post5-py3.6.egg/bilm/training.py:506) ]] [[node clip_by_global_norm/clip_by_global_norm/_8 (defined at /usr/local/lib/python3.6/dist-packages/bilm-0.1.post5-py3.6.egg/bilm/training.py:913) ]]