fix simplenet for timm finetuning recipe

if during model creation, the number of classes differed from imagenets 1000 classes
simplenet would crash because the pretrained weights wouldnt match.
now when generating architectures, we check for this and if encountered with one,
only swap the classifier after the model has been loaded with original weights.

Author: Coderx7

ImageNet/training_scripts/imagenet_training/timm/models/simplenet.py

@@ -344,7 +344,7 @@ def forward_features(self, x: torch.Tensor) -> torch.Tensor:
         return self.features(x)
 
     def forward_head(self, x: torch.Tensor, pre_logits: bool = False):
-        x_ = self.forward_features(x)
+        x = self.forward_features(x)
         if pre_logits:
             return x
         else: