il_representations.scripts package

Module contents

The scripts package contains the scripts that we use to perform representation learning, imitation learning, evaluation, dataset generation, and so on.

Submodules

il_representations.scripts.collate_configs module

il_representations.scripts.grab_some_stuff_and_pickle_it module

il_representations.scripts.il_test module

il_representations.scripts.il_train module

il_representations.scripts.interpret module

il_representations.scripts.joint_training module

il_representations.scripts.joint_training_cluster module

il_representations.scripts.mkdataset_demos module

il_representations.scripts.mkdataset_random module

il_representations.scripts.pretrain_n_adapt module

il_representations.scripts.render_dataset module

il_representations.scripts.run_rep_learner module

il_representations.scripts.save_traced_net module

Trace & save a network for a MAGICAL environment. Capable of automatically figuring out where the encoder is.

il_representations.scripts.save_traced_net.auto_save_name(module_path: str) str

Use config.json files to automatically come up with a name for the given encoder.

il_representations.scripts.save_traced_net.fetch_encoder(net: torch.nn.Module) torch.nn.Module
il_representations.scripts.save_traced_net.get_config_path(module_path: str) Optional[str]

Keep walking up the tree until we find a config.json.

il_representations.scripts.save_traced_net.load_eval_net(net_path: str) torch.nn.Module

Load a network on disk, making sure it ends up on the CPU & in eval mode.

il_representations.scripts.save_traced_net.main(args: argparse.Namespace) None
il_representations.scripts.save_traced_net.pre_order_children(net: torch.nn.Module) Iterator[Tuple[str, torch.nn.Module]]

Traverse module tree in pre-order.

il_representations.scripts.save_traced_net.trace_encoder(encoder: torch.nn.Module) torch.nn.Module

Generate a random example of the appropriate size & use it to trace the given network.

il_representations.scripts.truncate_datasets_icml module