Mnist module¶
-
mnist.show_example_image(data: numpy.array, label: numpy.array, true_labels: dict) → None[source]¶ Prints first image of given data
Parameters: - data (np.array) – images
- label (np.array) – labels of images
- true_labels (dict) – dictionary with names of labels
Returns: None
Return type: None
-
mnist.get_train_and_test() → tuple[source]¶ Function for load dataset from pickle file and return test and train set
Returns: tuple of np.arrays Return type: tuple
-
mnist.get_dict_labels() → dict[source]¶ Returns: dictionary with name of labels in mnist dataset Return type: dict
-
mnist.main()[source]¶ Todo
- TODO: Make stratified train/test split
- TODO: Stochastic gradien descent and mini batch
- TODO: Adam solver
- TODO: Learning rate change during training