A request for updating your code

[StudyingLover]

Hellp,can you provide ypu teacher model /home/fboutros/arcface_torch/output/emore_random_resnet

More inportantly, recently I run your code in ubuntu 18.04,cuda 11.0,I meet many mistakes . For example, I got this mistake when I run my own dataset

Traceback (most recent call last):
  File "/root/Masked-Face-Recognition-KD/train_kd.py", line 226, in <module>
    main(args_)
  File "/root/Masked-Face-Recognition-KD/train_kd.py", line 185, in main
    features_teacher = F.normalize(backbone_teacher(img))
  File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/parallel/distributed.py", line 619, in forward
    output = self.module(*inputs[0], **kwargs[0])
  File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/root/Masked-Face-Recognition-KD/backbones/iresnet.py", line 175, in forward
    x = self.fc(x.float() if self.fp16 else x)
  File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/linear.py", line 93, in forward
    return F.linear(input, self.weight, self.bias)
  File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/functional.py", line 1690, in linear
    ret = torch.addmm(bias, input, weight.t())
RuntimeError: mat1 dim 1 must match mat2 dim 0

Besides, when I run faces_emore dataset,I neet this mistake

Exception in thread Thread-1:
Traceback (most recent call last):
  File "/root/miniconda3/lib/python3.8/threading.py", line 932, in _bootstrap_inner
    self.run()
  File "/root/miniconda3/lib/python3.8/threading.py", line 870, in run
    self._target(*self._args, **self._kwargs)
  File "/root/miniconda3/lib/python3.8/site-packages/torch/utils/data/_utils/pin_memory.py", line 25, in _pin_memory_loop
    r = in_queue.get(timeout=MP_STATUS_CHECK_INTERVAL)
  File "/root/miniconda3/lib/python3.8/multiprocessing/queues.py", line 116, in get
    return _ForkingPickler.loads(res)
  File "/root/miniconda3/lib/python3.8/site-packages/torch/multiprocessing/reductions.py", line 282, in rebuild_storage_fd
    fd = df.detach()
  File "/root/miniconda3/lib/python3.8/multiprocessing/resource_sharer.py", line 57, in detach
    with _resource_sharer.get_connection(self._id) as conn:
  File "/root/miniconda3/lib/python3.8/multiprocessing/resource_sharer.py", line 87, in get_connection
    c = Client(address, authkey=process.current_process().authkey)
  File "/root/miniconda3/lib/python3.8/multiprocessing/connection.py", line 508, in Client
    answer_challenge(c, authkey)
  File "/root/miniconda3/lib/python3.8/multiprocessing/connection.py", line 752, in answer_challenge
    message = connection.recv_bytes(256)         # reject large message
  File "/root/miniconda3/lib/python3.8/multiprocessing/connection.py", line 216, in recv_bytes
    buf = self._recv_bytes(maxlength)
  File "/root/miniconda3/lib/python3.8/multiprocessing/connection.py", line 414, in _recv_bytes
    buf = self._recv(4)
  File "/root/miniconda3/lib/python3.8/multiprocessing/connection.py", line 379, in _recv
    chunk = read(handle, remaining)
ConnectionResetError: [Errno 104] Connection reset by peer