luka0612 / asr_transformer Goto Github PK

Is it need update mean and var in batchnorm at training and testing period? In fact, some application only one wave to recognize.

It's little wired because your comment is "Linear projections", but with RELU it will be a nolinear function.

大佬，可以提供下 数据集么，http://openslr.org/resources.php 下载 中文语音数据好慢，可以提供下数据么，还有如何 跑通你的代码，可以提供下么，非常感谢！！！

Traceback (most recent call last):
File "/home/uvideo/anaconda3/envs/nlp/lib/python3.6/site-packages/tensorflow/python/ops/array_ops.py", line 2667, in gather
return params.sparse_read(indices, name=name)
AttributeError: 'Tensor' object has no attribute 'sparse_read'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "train.py", line 51, in
tmodel.build_test_model(get_wer=True)
File "/home/uvideo/huatianxiang/asr_transformer/transformer.py", line 268, in build_test_model
self.test_preds = self.get_beam_search_preds(reuse=reuse, is_training=is_training, get_wer=get_wer)
File "/home/uvideo/huatianxiang/asr_transformer/transformer.py", line 247, in get_beam_search_preds
return self.make_parallel_beam_search(reuse=reuse, is_training=is_training, get_wer=get_wer)
File "/home/uvideo/huatianxiang/asr_transformer/transformer.py", line 614, in make_parallel_beam_search
prediction = self.model_beam_search_preds(X, reuse, is_training, scope="transformer")
File "/home/uvideo/huatianxiang/asr_transformer/transformer.py", line 264, in model_beam_search_preds
test_preds = self.beam_search(enc_output, reuse)
File "/home/uvideo/huatianxiang/asr_transformer/transformer.py", line 428, in beam_search
back_prop=False)
File "/home/uvideo/anaconda3/envs/nlp/lib/python3.6/site-packages/tensorflow/python/ops/control_flow_ops.py", line 3274, in while_loop
return_same_structure)
File "/home/uvideo/anaconda3/envs/nlp/lib/python3.6/site-packages/tensorflow/python/ops/control_flow_ops.py", line 2994, in BuildLoop
pred, body, original_loop_vars, loop_vars, shape_invariants)
File "/home/uvideo/anaconda3/envs/nlp/lib/python3.6/site-packages/tensorflow/python/ops/control_flow_ops.py", line 2929, in _BuildLoop
body_result = body(*packed_vars_for_body)
File "/home/uvideo/huatianxiang/asr_transformer/transformer.py", line 401, in step
preds = tf.gather(preds, indices=tf.cast(k_indices, tf.int64) / beam_size)
File "/home/uvideo/anaconda3/envs/nlp/lib/python3.6/site-packages/tensorflow/python/ops/array_ops.py", line 2669, in gather
return gen_array_ops.gather_v2(params, indices, axis, name=name)
File "/home/uvideo/anaconda3/envs/nlp/lib/python3.6/site-packages/tensorflow/python/ops/gen_array_ops.py", line 3232, in gather_v2
"GatherV2", params=params, indices=indices, axis=axis, name=name)
File "/home/uvideo/anaconda3/envs/nlp/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 609, in _apply_op_helper
param_name=input_name)
File "/home/uvideo/anaconda3/envs/nlp/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 60, in _SatisfiesTypeConstraint
", ".join(dtypes.as_dtype(x).name for x in allowed_list)))
TypeError: Value passed to parameter 'indices' has DataType float64 not in list of allowed values: int32, int64 你好，我运行的代码出现上面的错误是什么原因啊，环境python3.6 和tf1.11.0