**Batch Prediction Error**

[iqram1337]

i try to run batch prediction with command:
"python deepdenoiser/predict.py --format=mseed --model_dir=model/190614-104802 --data_dir=test_data/ --data_list=test_data/testing.csv --sampling_rate=100 --plot_figure --save_signal --save_noise"

but getting an error:

Traceback (most recent call last):
  File "D:\QuakeFlow\DeepDenoiser\deepdenoiser\predict.py", line 136, in <module>
    main(args)
  File "D:\QuakeFlow\DeepDenoiser\deepdenoiser\predict.py", line 129, in main
    pred_fn(args, data_reader, log_dir=args.output_dir)
  File "D:\QuakeFlow\DeepDenoiser\deepdenoiser\predict.py", line 81, in pred_fn
    X_batch, fname_batch, t0_batch = sess.run(data_batch)
  File "D:\miniconda3\lib\site-packages\tensorflow\python\client\session.py", line 968, in run
    result = self._run(None, fetches, feed_dict, options_ptr,
  File "D:\miniconda3\lib\site-packages\tensorflow\python\client\session.py", line 1191, in _run
    results = self._do_run(handle, final_targets, final_fetches,
  File "D:\miniconda3\lib\site-packages\tensorflow\python\client\session.py", line 1371, in _do_run
    return self._do_call(_run_fn, feeds, fetches, targets, options,
  File "D:\miniconda3\lib\site-packages\tensorflow\python\client\session.py", line 1397, in _do_call
    raise type(e)(node_def, op, message)  # pylint: disable=no-value-for-parameter
tensorflow.python.framework.errors_impl.InvalidArgumentError: Graph execution error:

Detected at node 'Input_Batch/IteratorGetNext' defined at (most recent call last):
    File "D:\QuakeFlow\DeepDenoiser\deepdenoiser\predict.py", line 136, in <module>
      main(args)
    File "D:\QuakeFlow\DeepDenoiser\deepdenoiser\predict.py", line 129, in main
      pred_fn(args, data_reader, log_dir=args.output_dir)
    File "D:\QuakeFlow\DeepDenoiser\deepdenoiser\predict.py", line 56, in pred_fn
      data_batch = data_reader.dataset(args.batch_size)
    File "D:\QuakeFlow\DeepDenoiser\deepdenoiser\data_reader.py", line 801, in dataset
      dataset = tf.compat.v1.data.make_one_shot_iterator(
Node: 'Input_Batch/IteratorGetNext'
Incompatible shapes at component 0: expected [?,3,1,31,1202,2] but got [1,3,1,31,1201,2].
         [[{{node Input_Batch/IteratorGetNext}}]]

Original stack trace for 'Input_Batch/IteratorGetNext':
  File "D:\QuakeFlow\DeepDenoiser\deepdenoiser\predict.py", line 136, in <module>
    main(args)
  File "D:\QuakeFlow\DeepDenoiser\deepdenoiser\predict.py", line 129, in main
    pred_fn(args, data_reader, log_dir=args.output_dir)
  File "D:\QuakeFlow\DeepDenoiser\deepdenoiser\predict.py", line 56, in pred_fn
    data_batch = data_reader.dataset(args.batch_size)
  File "D:\QuakeFlow\DeepDenoiser\deepdenoiser\data_reader.py", line 801, in dataset
    dataset = tf.compat.v1.data.make_one_shot_iterator(
  File "D:\miniconda3\lib\site-packages\tensorflow\python\data\ops\iterator_ops.py", line 440, in get_next
    flat_ret = gen_dataset_ops.iterator_get_next(
  File "D:\miniconda3\lib\site-packages\tensorflow\python\ops\gen_dataset_ops.py", line 3036, in iterator_get_next
    _, _, _op, _outputs = _op_def_library._apply_op_helper(
  File "D:\miniconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 797, in _apply_op_helper
    op = g._create_op_internal(op_type_name, inputs, dtypes=None,
  File "D:\miniconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 3800, in _create_op_internal
    ret = Operation(

this is my input data:

[xioddd]

The reason might be found in these two lines of code: if np.mod(data.shape[-1], 3000) == 1: # 3001=>3000 and data = data[..., :-1] （←in data_reader.py）. Commenting them out should allow the program to run successfully.Please forgive my poor English QAQ

[ljh116]

The reason might be found in these two lines of code: if np.mod(data.shape[-1], 3000) == 1: # 3001=>3000 and data = data[..., :-1] （←in data_reader.py）. Commenting them out should allow the program to run successfully.Please forgive my poor English QAQ

Hello，I tried the methods you suggested, but the issue still persists.Are there any other solutions?

[cookicelan]

hello

…

________________________________ 发件人: ljh116 ***@***.***> 发送时间: 2024年12月9日 20:48 收件人: AI4EPS/DeepDenoiser ***@***.***> 抄送: Subscribed ***@***.***> 主题: Re: [AI4EPS/DeepDenoiser] **Batch Prediction Error** (Issue #26) The reason might be found in these two lines of code: if np.mod(data.shape[-1], 3000) == 1: # 3001=>3000 and data = data[..., :-1] （←in data_reader.py）. Commenting them out should allow the program to run successfully.Please forgive my poor English QAQ Hello，I tried the methods you suggested, but the issue still persists.Are there any other solutions? ― Reply to this email directly, view it on GitHub<#26 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/BBRMXJTBIXLP4HV2YQJSKWL2EWGTBAVCNFSM6AAAAABTIYITECVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDKMRXHAZTMOBXGI>. You are receiving this because you are subscribed to this thread.