Loading flac files about deepxi HOT 10 CLOSED

Hi,

My first hunch as to what is causing this is the saved pickle file for the inference list. Try deleting the 'test_x_list.p' from data and then run it again. I will have to devise a better system if this is the case.

If this doesn't fix the problem, please let me know.

Thanks!

from deepxi.

Thank you for answering Aaron.

As I previously changed the code, I ran it again out of the box to be sure and the error persists: "operands could not be broadcast together with shapes (1,956,257) (0,257)"
I was guessing that it is due to data type differences (int16, float).

Before facing the issue I made the code create pickle file every time, as it was being unable to see when new files are added.

from deepxi.

Hi,

Would you be able to send all of the output to terminal?

from deepxi.

Sure.
"
/home/stefan/work/DeepXi/p3speech/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:516: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint8 = np.dtype([("qint8", np.int8, 1)])
/home/stefan/work/DeepXi/p3speech/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:517: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint8 = np.dtype([("quint8", np.uint8, 1)])
/home/stefan/work/DeepXi/p3speech/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:518: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint16 = np.dtype([("qint16", np.int16, 1)])
/home/stefan/work/DeepXi/p3speech/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:519: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint16 = np.dtype([("quint16", np.uint16, 1)])
/home/stefan/work/DeepXi/p3speech/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:520: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint32 = np.dtype([("qint32", np.int32, 1)])
/home/stefan/work/DeepXi/p3speech/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
np_resource = np.dtype([("resource", np.ubyte, 1)])
/home/stefan/work/DeepXi/p3speech/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:541: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint8 = np.dtype([("qint8", np.int8, 1)])
/home/stefan/work/DeepXi/p3speech/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:542: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint8 = np.dtype([("quint8", np.uint8, 1)])
/home/stefan/work/DeepXi/p3speech/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:543: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint16 = np.dtype([("qint16", np.int16, 1)])
/home/stefan/work/DeepXi/p3speech/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:544: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint16 = np.dtype([("quint16", np.uint16, 1)])
/home/stefan/work/DeepXi/p3speech/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:545: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint32 = np.dtype([("qint32", np.int32, 1)])
/home/stefan/work/DeepXi/p3speech/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:550: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
np_resource = np.dtype([("resource", np.ubyte, 1)])
Creating test_x list, as no pickle file exists...
The test_x list has a total of 48 entries.
Loading sample statistics from pickle file...
Preparing graph...
Inference...
2%|██▋ | 1/48 [00:05<04:18, 5.50s/it]Traceback (most recent call last):
File "deepxi.py", line 44, in
if args.infer: infer(sess, net, args)
File "lib/dev/infer.py", line 45, in infer
y_MAG = np.multiply(input_feat[0], gain.gfunc(xi_hat, xi_hat+1, gtype=args.gain))
ValueError: operands could not be broadcast together with shapes (1,956,257) (0,257)
"

from deepxi.

This is weird. I just ran with a .flac file from Librispeech with no errors. Could you try with a .wav file? I believe you will get the same error with a .wav file. It seems to be successfully making the input features (noisy speech magnitude spectra --- input_feat[0] (1,956,257)), but the output of the network seems to not be correct (0,257).

May I ask if you changed something to do with the network?

Thanks!

from deepxi.

Ohh, that is weird. Wavs do not have any issue.
Could it be that there are different file formats inside the test folder? One wav and other flac.
Ill try and let you know.

I tested it out of github to share you the results before, without any changes applied.

from deepxi.

I just tried with .wav and .flac and it worked. I will place the .flac file in set/test_noisy_speech. Will you be able to try it?

from deepxi.

it is a clean speech file, but that doesn't matter. See if you can run with those two files. I am able to for some reason.

from deepxi.

It is showing the same error and breaking on flac file. I cloned it clean and just ran the command shown on github with "python3 deepxi.py --infer 1 --out_type y --gain mmse-lsa --ver '3f' --epoch 175 --gpu 5"

Maybe due to system configuration, but waves are running fine.

Thank you very much eather way, your response its highly appreciated.

from deepxi.

That's a shame. I will have another look at it. Please let me know if you find a fix.

Thank you!

from deepxi.