How to test with a different test list?

[Dimuthu Anuraj]

hi @dvisockas @joonson, if we want to test with a new test list from a different dataset, Can we do it by changing only the test list?

[joonson]

Yes, test list and test path.

[Dimuthu Anuraj]

@dvisockas @joonson. I tried that but I am getting this error.

Python Version: 3.8.10 (default, Jun 4 2021, 15:09:15)
[GCC 7.5.0]
PyTorch Version: 1.9.0+cu102
Number of GPUs: 1
Save path: exps/test
Embedding size is 512, encoder SAP.
Initialised AngleProto
Initialised Adam optimizer
Initialised step LR scheduler
Model baseline_lite_ap.model loaded!
Total parameters: 1437078
Test list /mnt/ricproject4/anuraj_works/data_collection/YoutubeVideos/Results_Videos/finallist_s00.txt
Traceback (most recent call last):
File "./trainSpeakerNet.py", line 316, in
main()
File "./trainSpeakerNet.py", line 312, in main
main_worker(0, None, args)
File "./trainSpeakerNet.py", line 199, in main_worker
sc, lab, _ = trainer.evaluateFromList(**vars(args))
File "/mnt/ricproject4/commercial_product/speaker_verification/anuraj/voxceleb_trainer_4/voxceleb_trainer/SpeakerNet.py", line 178, in evaluateFromList
for idx, data in enumerate(test_loader):
File "/home/anuraj/anaconda3/envs/vox_trainer/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 521, in next
data = self._next_data()
File "/home/anuraj/anaconda3/envs/vox_trainer/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1203, in _next_data
return self._process_data(data)
File "/home/anuraj/anaconda3/envs/vox_trainer/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1229, in _process_data
data.reraise()
File "/home/anuraj/anaconda3/envs/vox_trainer/lib/python3.8/site-packages/torch/_utils.py", line 425, in reraise
raise self.exc_type(msg)
TypeError: init() missing 1 required positional argument: 'dtype'``

[Dimuthu Anuraj]

@joonson Problem solved. My data set had stereo wave files. To process the data we need to only mono wave files. Thank you.