Loading...
Searching...
No Matches
CNN Class Reference
Implements an architecture consisting of a multi-layer CNN followed by an MLP, according to parameters specified in the input config. More...
Inheritance diagram for CNN:Public Member Functions | |
| __init__ (self, dict config) | |
| torch.Tensor | forward (self, torch.Tensor x) |
| Forward pass through the network. | |
| None | load_cpp_model (self, str model_path) |
| Loads a model saved in cpp jit format. | |
| None | load_model (self, str model_path) |
| Loads a model saved in pytorch format. | |
| Public Member Functions inherited from CNNConfigParser | |
| None | parse (self, dict config) |
| Parse the configuration for the CNN model. | |
Public Attributes | |
| cnn_backbone = CNNBackBone(self.config) | |
| mlp | |
| linear = torch.nn.Linear(self.latent_size, self.output_dim) | |
| Public Attributes inherited from CNNConfigParser | |
| config = None | |
| input_dim = None | |
| output_dim = None | |
| num_layers = None | |
| latent_size = None | |
| kernel_size = None | |
| image_size = None | |
Detailed Description
Implements an architecture consisting of a multi-layer CNN followed by an MLP, according to parameters specified in the input config.
Constructor & Destructor Documentation
◆ __init__()
| __init__ | ( | self, | |
| dict | config ) |
Reimplemented from CNNConfigParser.
Member Function Documentation
◆ forward()
| torch.Tensor forward | ( | self, | |
| torch.Tensor | x ) |
◆ load_cpp_model()
| None load_cpp_model | ( | self, | |
| str | model_path ) |
◆ load_model()
| None load_model | ( | self, | |
| str | model_path ) |
Member Data Documentation
◆ cnn_backbone
| cnn_backbone = CNNBackBone(self.config) |
