Trainer implementation

* Add Deconv2d
* Fix BatchGenerator save option when using current directory

layers.py

@@ -45,6 +45,20 @@ class Layer(nn.Module):
         return output
 
 
+class Linear(Layer):
+    def __init__(self, in_channels: int, out_channels: int, activation=0, batch_norm=None, **kwargs):
+        super().__init__(activation, batch_norm)
+
+        self.fc = nn.Linear(in_channels, out_channels, **kwargs)
+        self.batch_norm = nn.BatchNorm1d(
+            out_channels,
+            momentum=Layer.BATCH_NORM_MOMENTUM,
+            track_running_stats=Layer.BATCH_NORM_TRAINING) if self.batch_norm else None
+
+    def forward(self, input_data: torch.Tensor) -> torch.Tensor:
+        return super().forward(self.fc(input_data))
+
+
 class Conv1d(Layer):
     def __init__(self, in_channels: int, out_channels: int, kernel_size: int = 3,
                  stride: Union[int, Tuple[int, int]] = 1, activation=0, batch_norm=None, **kwargs):
@@ -93,15 +107,18 @@ class Conv3d(Layer):
         return super().forward(self.conv(input_data))
 
 
-class Linear(Layer):
-    def __init__(self, in_channels: int, out_channels: int, activation=0, batch_norm=None, **kwargs):
+class Deconv2d(Layer):
+    def __init__(self, in_channels: int, out_channels: int, kernel_size: int = 3,
+                 stride: Union[int, Tuple[int, int]] = 1, activation=0, batch_norm=None, **kwargs):
         super().__init__(activation, batch_norm)
 
-        self.fc = nn.Linear(in_channels, out_channels, **kwargs)
-        self.batch_norm = nn.BatchNorm1d(
+        self.deconv = nn.ConvTranspose2d(
+            in_channels, out_channels, kernel_size, stride=stride,
+            bias=not self.batch_norm, **kwargs)
+        self.batch_norm = nn.BatchNorm2d(
             out_channels,
             momentum=Layer.BATCH_NORM_MOMENTUM,
-            track_running_stats=Layer.BATCH_NORM_TRAINING) if self.batch_norm else None
+            track_running_stats=not Layer.BATCH_NORM_TRAINING) if self.batch_norm else None
 
     def forward(self, input_data: torch.Tensor) -> torch.Tensor:
-        return super().forward(self.fc(input_data))
+        return super().forward(self.deconv(input_data))