Utilities

This section lists out all the utility functions present througout TensorNet.

Common Utilities

tensornet.utils.set_seed(seed: int, cuda: bool)[source]

Set seed to make the results reproducible.

Parameters

  • seed (int) – Random seed value.

  • cuda (bool) – Whether CUDA is available.

tensornet.utils.initialize_cuda(seed: int) → Tuple[bool, torch.device][source]

Check if GPU is availabe and set seed.

Parameters

seed (int) – Random seed value.

Returns

2-element tuple containing

  • (bool): if cuda is available

  • (torch.device): device name

tensornet.utils.get_predictions(model: torch.nn.modules.module.Module, loader: torch.utils.data.dataloader.DataLoader, device: Union[str, torch.device], sample_count: int = 25)[source]

Get correct and incorrect model predictions.

Parameters

  • model (torch.nn.Module) – Model Instance.

  • loader (torch.utils.data.DataLoader) – Data Loader.

  • device (str or torch.device) – Device where data will be loaded.

  • (obj (sample_count) – int, optional): Total number of predictions to store from each correct and incorrect samples. (default: 25)

tensornet.utils.class_level_accuracy(model: torch.nn.modules.module.Module, loader: torch.utils.data.dataloader.DataLoader, device: Union[str, torch.device], classes: Union[List[str], Tuple[str]])[source]

Print test accuracy for each class in dataset.

Parameters

  • model (torch.nn.Module) – Model Instance.

  • loader (torch.utils.data.DataLoader) – Data Loader.

  • device (str or torch.device) – Device where data will be loaded.

  • classes (list or tuple) – List of classes in the dataset.

tensornet.utils.plot_metric(data: Union[List[float], Dict[str, List[float]]], metric: str, title: str = None, size: Tuple[int] = 7, 5, legend_font: int = 15, legend_loc: str = 'lower right')[source]

Plot accuracy graph or loss graph.

Parameters

  • data (list or dict) – If only single plot then this is a list, else for multiple plots this is a dict with keys containing the plot name and values being a list of points to plot.

  • metric (str) – Metric name which is to be plotted. Can be either loss or accuracy.

  • title (str, optional) – Title of the plot, if no title given then it is determined from the x and y label.

  • size (tuple, optional) – Size of the plot. (default: ‘(7, 5)’)

  • legend_loc (str, optional) – Location of the legend box in the plot. No legend will be plotted if there is only a single plot. (default: ‘lower right’)

  • legend_font (int, optional) – Font size of the legend (default: ‘15’)

tensornet.utils.plot_predictions(data: List[dict], classes: Union[List[str], Tuple[str]], plot_title: str, plot_path: str)[source]

Display data.

Parameters

  • data (list) – List of images, model predictions and ground truths. Images should be numpy arrays.

  • classes (list or tuple) – List of classes in the dataset.

  • plot_title (str) – Title for the plot.

  • plot_path (str) – Complete path for saving the plot.

tensornet.utils.save_and_show_result(classes: Union[List[str], Tuple[str]], correct_pred: Optional[List[dict]] = None, incorrect_pred: Optional[List[dict]] = None, path: Optional[str] = None)[source]

Display network predictions.

Parameters

  • classes (list or tuple) – List of classes in the dataset.

  • correct_pred (list, optional) – Contains correct model predictions and labels.

  • incorrect_pred (list, optional) – Contains incorrect model predictions and labels.

  • path (str, optional) – Path where the results will be saved.

Model Utilities

Utility methods used by classes and methods present in the Models section.

tensornet.models.utils.summary(model: torch.nn.modules.module.Module, input_size: Union[Tuple[int], List[int], Dict[str, Union[tuple, list]]], batch_size: int = - 1, dtypes: Optional = None)[source]

Display model summary.

Parameters

  • model (torch.nn.Module) – Model instance.

  • input_size (tuple, list or dict) – Input size for the model.

  • batch_size (int, optional) – Batch size. (default: -1)

  • dtypes (optional) – Model input data types.

Data Utilities

Utility methods used by classes and methods present in the Data section.

tensornet.data.utils.unnormalize(image, mean, std, transpose=False)[source]

Un-normalize a given image.

Parameters

  • image (numpy.ndarray or torch.Tensor) – A ndarray or tensor. If tensor, it should be in CPU.

  • mean (float or tuple) – Mean. It can be a single value or a tuple with 3 values (one for each channel).

  • std (float or tuple) – Standard deviation. It can be a single value or a tuple with 3 values (one for each channel).

  • transpose (bool, optional) – If True, transposed output will be returned. This param is effective only when image is a tensor. If tensor, the output will have channel number as the last dim. (default: False)

Returns

Unnormalized image

Return type

(numpy.ndarray or torch.Tensor)

tensornet.data.utils.normalize(image, mean, std, transpose=False)[source]

Normalize a given image.

Parameters

  • image (numpy.ndarray or torch.Tensor) – A ndarray or tensor. If tensor, it should be in CPU.

  • mean (float or tuple) – Mean. It can be a single value or a tuple with 3 values (one for each channel).

  • std (float or tuple) – Standard deviation. It can be a single value or a tuple with 3 values (one for each channel).

  • transpose (bool, optional) – If True, transposed output will be returned. This param is effective only when image is a tensor. If tensor, the output will have channel number as the last dim. (default: False)

Returns

Normalized image

Return type

(numpy.ndarray or torch.Tensor)

tensornet.data.utils.to_numpy(tensor)[source]

Convert 3-D torch tensor to a 3-D numpy array.

Parameters

tensor (torch.Tensor) – Tensor to be converted.

Returns

Image in numpy form.

Return type

(numpy.ndarray)

tensornet.data.utils.to_tensor(ndarray)[source]

Convert 3-D numpy array to 3-D torch tensor.

Parameters

ndarray (numpy.ndarray) – Array to be converted.

Returns

Image in tensor form.

Return type

(torch.Tensor)