search

rlleshi / phar

deep learning sex position classifier
Apache License 2.0
217 stars 25 forks source link

Issue with audio in inference-recognizer #4

Closed Arialphe closed 1 year ago

Arialphe commented 1 year ago

Hello, I tried to test the app, but i got the same problem as the issue here: https://github.com/rlleshi/phar/issues/1

Stack Trace: File "src/demo/multimodial_demo.py", line 601, in main() File "src/demo/multimodial_demo.py", line 562, in main audio_inference(clip, args.coefficients) File "src/demo/multimodial_demo.py", line 385, in audio_inference results = inference_recognizer(AUDIO_MODEL, out_feature) File "/workspace/phar/mmaction2/mmaction/apis/inference.py", line 99, in inference_recognizer raise RuntimeError('The type of argument video is not supported: ' RuntimeError: The type of argument video is not supported: <class 'str'>

I checked that the code is up to date, and it's the case: line 381..:
subprocess.run( ['python', AUDIO_FEATURE_SCRIPT, TEMP, TEMP, '--ext', 'wav'], capture_output=True)

Any ideas on what I'm doing wrong ?

rlleshi commented 1 year ago

Can you try to replace the glob search in mmaction2/tools/data/build_audio_features.py file with this line:

files = glob.glob(args.audio_home_path + '/*' * args.level + '.' + args.ext)

Arialphe commented 1 year ago

Thank you for your help, that did the job ! Have a great day