kitcar_ml.onboarding package
Subpackages
Submodules
kitcar_ml.onboarding.model module
Classes:
Neural network class. |
- class OnboardingNet[source]
Bases:
ModuleNeural network class.
The
forward()defines how images are passed through the network.Methods:
forward(x)Handle input.
load(path)Load model parameters from file.
save(path)Save model parameters to file.
Attributes:
- forward(x: Tensor) Tensor[source]
Handle input.
- Parameters
x – Input image
- Returns
Output class as 10-dimensional tensor.
- training: bool
- _parameters: Dict[str, Optional[Parameter]]
- _buffers: Dict[str, Optional[Tensor]]
- _non_persistent_buffers_set: Set[str]
- _backward_hooks: Dict[int, Callable]
- _is_full_backward_hook: Optional[bool]
- _forward_hooks: Dict[int, Callable]
- _forward_pre_hooks: Dict[int, Callable]
- _state_dict_hooks: Dict[int, Callable]
- _load_state_dict_pre_hooks: Dict[int, Callable]
- _load_state_dict_post_hooks: Dict[int, Callable]
- _modules: Dict[str, Optional[Module]]
kitcar_ml.onboarding.script module
Functions:
|
Create a dataloader. |
|
Train the |
|
Test the |
- get_dataloader(label_file: str, batch_size: int = 16) BaseDataLoader[source]
Create a dataloader.
- Returns
Labeled dataloader object that can be used to load training/test data.