v-iashin / voxceleb

An attempt to replicate the results of [1706.08612] VoxCeleb: a large-scale speaker identification dataset

VoxCeleb

An attempt to replicate the results of [1706.08612] VoxCeleb: a large-scale speaker identification dataset. Only identification results are provided.

Identification

Top-5 accuracy: 90 % (92 % reported)

Top-1 accuracy: 76 % (81 % reported)

voxceleb's Issues

VGG Vox Network

In the original implementation, the number of filters in conv3 is 384 while you are using 256, any particular reason?

Verification part

Hi,

did you finish the verification part, if yes, what is the performance?

about the iden_split.txt

Hi~
your code is really helpful. could you please tell me more about the iden_split.txt?
is it a text file that contains file paths, one row one path?

error: module multiprocessing.util' has no attribute '_flush_std_streams

hey~~~
I run your code but error shows up.....
it seems like cannot enumerate trainloader. once do enumerate(trainloader), error appears: "module multiprocessing.util' has no attribute '_flush_std_streams"
However, change the NUM_WORKERS to 1, it disappeared..., but that's not what I want...

`AttributeError Traceback (most recent call last)
in
21 plt.title('Batch from dataloader')
22
---> 23 for i_batch, sample_batched in enumerate(dataloader):
24 print(i_batch, sample_batched['image'].size(),
25 sample_batched['landmarks'].size())

~/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/utils/data/dataloader.py in iter(self)
499
500 def iter(self):
--> 501 return _DataLoaderIter(self)
502
503 def len(self):

~/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/utils/data/dataloader.py in init(self, loader)
287 for w in self.workers:
288 w.daemon = True # ensure that the worker exits on process exit
--> 289 w.start()
290
291 _update_worker_pids(id(self), tuple(w.pid for w in self.workers))

~/anaconda3/envs/pytorch/lib/python3.6/multiprocessing/process.py in start(self)
103 'daemonic processes are not allowed to have children'
104 _cleanup()
--> 105 self._popen = self._Popen(self)
106 self._sentinel = self._popen.sentinel
107 # Avoid a refcycle if the target function holds an indirect

~/anaconda3/envs/pytorch/lib/python3.6/multiprocessing/context.py in _Popen(process_obj)
221 @staticmethod
222 def _Popen(process_obj):
--> 223 return _default_context.get_context().Process._Popen(process_obj)
224
225 class DefaultContext(BaseContext):

~/anaconda3/envs/pytorch/lib/python3.6/multiprocessing/context.py in _Popen(process_obj)
275 def _Popen(process_obj):
276 from .popen_fork import Popen
--> 277 return Popen(process_obj)
278
279 class SpawnProcess(process.BaseProcess):

~/anaconda3/envs/pytorch/lib/python3.6/multiprocessing/popen_fork.py in init(self, process_obj)
15
16 def init(self, process_obj):
---> 17 util._flush_std_streams()
18 self.returncode = None
19 self._launch(process_obj)

AttributeError: module 'multiprocessing.util' has no attribute '_flush_std_streams'`

I dont know how to solve it