Tested model:
=============
------- notif_encoder:
NotifEncoderSimple(
  (model): Linear(in_features=29, out_features=32, bias=True)
)

------- evnt_encoder:
EvntEncoderSimple(
  (model): Linear(in_features=11, out_features=32, bias=True)
)

------- info_encoder:
InfoEncoder(
  (model): Sequential(
    (0): Linear(in_features=28, out_features=64, bias=True)
    (1): PReLU(num_parameters=1)
    (2): Linear(in_features=64, out_features=32, bias=True)
    (3): Dropout(p=0.2, inplace=False)
  )
)

------- embedder:
ConvEmbedderSimple(
  (adapter): Linear(in_features=32, out_features=32, bias=True)
  (representer): ConvRepresenter(
    (convs): ParameterList(
        (0): Object of type: ConvRepresenterBlock
        (1): Object of type: ConvRepresenterBlock
      (0): ConvRepresenterBlock(
        (model): Sequential(
          (0): Conv1d(32, 64, kernel_size=(3,), stride=(1,), padding=(1,))
          (1): PReLU(num_parameters=1)
          (2): Conv1d(64, 32, kernel_size=(3,), stride=(1,), padding=(1,))
          (3): PReLU(num_parameters=1)
        )
      )
      (1): ConvRepresenterBlock(
        (model): Sequential(
          (0): Conv1d(32, 64, kernel_size=(3,), stride=(1,), padding=(1,))
          (1): PReLU(num_parameters=1)
          (2): Conv1d(64, 32, kernel_size=(3,), stride=(1,), padding=(1,))
          (3): PReLU(num_parameters=1)
        )
      )
    )
  )
  (final): Conv1d(32, 32, kernel_size=(22,), stride=(1,))
)

(Training dataset class occurences: {3: 176, 4: 45, 1: 46, 2: 1}.)
svm finished: True; SV cnt 93;
Trained SVM with LINEAR kernel with loss 887950.0087727046 and 93 outliers.
svm finished: True; SV cnt 86;
Trained SVM with POLYNOMIAL (deg 2) kernel with loss 843941.6123241688 and 86 outliers.
svm finished: True; SV cnt 91;
Trained SVM with GAUSSIAN (sigma 1) kernel with loss 843941.6123241688 and 86 outliers.
Results of classification of specially annotated notifications:
  IDs of clssified notificaions: [9961382, 9962202, 9971171, 10168557, 10213020, 10275769, 11168292, 11169523, 11173814]
  SVM with LINEAR kernel: tensor([ 1.,  1.,  1.,  1.,  1.,  1.,  1., -1.,  1.], dtype=torch.float64)
  SVM with POLYNOMIAL kernel: tensor([ 1.,  1.,  1.,  1.,  1.,  1.,  1., -1.,  1.], dtype=torch.float64)
  SVM with GAUSSIAN kernel: tensor([ 1.,  1.,  1.,  1.,  1.,  1.,  1., -1.,  1.], dtype=torch.float64)
  logistic regression: tensor([[1.0000e+00, 8.2416e-28],
        [1.0000e+00, 3.0385e-35],
        [1.0000e+00, 4.9033e-14],
        [1.0000e+00, 0.0000e+00],
        [1.7237e-23, 1.0000e+00],
        [3.4791e-19, 1.0000e+00],
        [1.0000e+00, 0.0000e+00],
        [0.0000e+00, 1.0000e+00],
        [1.0000e+00, 0.0000e+00]], grad_fn=<SoftmaxBackward0>)
  MLP classifier: tensor([[1.0000e+00, 0.0000e+00],
        [1.0000e+00, 0.0000e+00],
        [1.0000e+00, 0.0000e+00],
        [1.0000e+00, 0.0000e+00],
        [3.1970e-11, 1.0000e+00],
        [4.0606e-19, 1.0000e+00],
        [1.0000e+00, 0.0000e+00],
        [0.0000e+00, 1.0000e+00],
        [1.0000e+00, 0.0000e+00]], grad_fn=<SoftmaxBackward0>)
Results on test set:
  SVM with LINEAR kernel: 1.0 (13/13)
  SVM with POLYNOMIAL kernel: 1.0 (13/13)
  SVM with GAUSSIAN kernel: 1.0 (13/13)
  logistic regression: 1.0 (13/13)
  MLP classifier: 1.0 (13/13)
  (class occurence counts: {3: 11, 4: 2})