ContinualMNIST¶
-
class
cl_gym.benchmarks.mnist.
ContinualMNIST
(num_tasks: int, per_task_examples: Optional[int] = None, per_task_joint_examples: Optional[int] = 0, per_task_memory_examples: Optional[int] = 0, per_task_subset_examples: Optional[int] = 0, task_input_transforms: Optional[list] = None, task_target_transforms: Optional[list] = None)[source]¶ Bases:
cl_gym.benchmarks.base.Benchmark
Base class for (Permuted/Rotated/Split)-MNIST benchmarks.
-
precompute_memory_indices
()[source]¶ For each task, (randomly) computes the indices of the subset of data points in the task’s dataset. Then, once load_memory() method is called, uses these indices to return a PyTorch Subset dataset. .. note:: This method will be called only if the benchmark is initiated with per_task_memory_examples.
-