Comments (10)
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.
Related Issues (20)
- Multi gpu trainin HOT 4
- Understanding the loss implementation HOT 9
- can i train this model without gpu? HOT 1
- How to run version resnet-1.0n? HOT 1
- Errors during training HOT 2
- What is the major consideration when choosing Hamming window with no periodic? HOT 11
- Clarity on file format reqruired in '/set' folder HOT 1
- no deepxi.network.attention.py file thus no MHANet class HOT 2
- Running Inference/Testing on Multiple GPUs HOT 7
- Training on other noise dataset gives resuts worse than unprocessed noisy HOT 5
- Denoise Live Microphone Feed HOT 1
- I can't find the implementation of addnoise function from deep_xi_test_set.m HOT 4
- Some questions about the data and the training process HOT 5
- Error loading pretrain model during inference HOT 3
- i can not find the freesound packs. does it mean Sound Ids HOT 2
- Some questions HOT 2
- Additional questions HOT 7
- mhanet loss results
- Can the MHANet run in real time HOT 4
- ValueError: No sample.npz file exists. (Inference)
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from deepxi.