Models: Bike Sharing¶
-
class
model.
BikeModel
¶ - Description:
- The model is a vanilla feedforward neural network that consists of 5 layers. Each layer is followed with a batch normalization layer and a Relu function.
- Dataset:
- Bike Sharing.
- Model:
- Group 1:
- Linear Layer:
- input features = 19, output features = 100
- Batch normalization:
- input features = 100
Relu
- Group 2:
- Linear Layer:
- input features = 100, output features = 50
- Batch normalization:
- input features = 50
Relu
- Group 3:
- Linear Layer:
- input features = 50, output features = 20
- Batch normalization:
- input features = 20
Relu
- Group 4:
- Linear Layer:
- input features = 20, output features = 10
- Batch normalization:
- input features = 10
Relu
Group 5: Linear Layer:
input features = 20, output features = 1
- Args:
- None.
-
forward
(x)¶ Defines the computation performed at every call.
Should be overridden by all subclasses.
Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.