def main():
    parser = build_args_parser()
    args = parser.parse_args()
    print(args)

    # Get experiment folder
    experiment_path = args.name
    if not os.path.isdir(experiment_path):
        # If not a directory, it must be the name of the experiment.
        experiment_path = pjoin(".", "experiments", args.name)

    if not os.path.isdir(experiment_path):
        parser.error('Cannot find experiment: {0}!'.format(args.name))

    # Load experiments hyperparameters
    try:
        hyperparams = smartutils.load_dict_from_json_file(pjoin(experiment_path, "hyperparams.json"))
    except FileNotFoundError:
        hyperparams = smartutils.load_dict_from_json_file(pjoin(experiment_path, "..", "hyperparams.json"))

    with Timer("Loading dataset", newline=True):
        volume_manager = VolumeManager()
        dataset = datasets.load_tractography_dataset([args.streamlines], volume_manager, name="dataset", use_sh_coeffs=hyperparams['use_sh_coeffs'])
        print("Dataset size:", len(dataset))

    with Timer("Loading model"):
        model = None
        if hyperparams['model'] == 'gru_regression':
            from learn2track.models import GRU_Regression
            model = GRU_Regression.create(experiment_path, volume_manager=volume_manager)
        elif hyperparams['model'] == 'gru_mixture':
            from learn2track.models import GRU_Mixture
            model = GRU_Mixture.create(experiment_path, volume_manager=volume_manager)
        elif hyperparams['model'] == 'gru_multistep':
            from learn2track.models import GRU_Multistep_Gaussian
            model = GRU_Multistep_Gaussian.create(experiment_path, volume_manager=volume_manager)
            model.k = 1
            model.m = 1
        elif hyperparams['model'] == 'ffnn_regression':
            from learn2track.models import FFNN_Regression
            model = FFNN_Regression.create(experiment_path, volume_manager=volume_manager)
        else:
            raise NameError("Unknown model: {}".format(hyperparams['model']))
        print(str(model))

    tractogram_file = pjoin(experiment_path, args.out)
    if not os.path.isfile(tractogram_file) or args.force:
        if args.method == 'prediction':
            tractogram = prediction_tractogram(hyperparams, model, dataset, args.batch_size, args.prediction)
        elif args.method == 'evaluation':
            tractogram = evaluation_tractogram(hyperparams, model, dataset, args.batch_size, args.metric)
        else:
            raise ValueError("Unrecognized method: {}".format(args.method))

        tractogram.affine_to_rasmm = dataset.subjects[0].signal.affine
        nib.streamlines.save(tractogram, tractogram_file)
    else:
        print("Tractogram already exists. (use --force to generate it again)")
Ejemplo n.º 2
0
def main():
    parser = build_parser()
    args = parser.parse_args()
    print(args)

    # Get experiment folder
    experiment_path = args.name
    if not os.path.isdir(experiment_path):
        # If not a directory, it must be the name of the experiment.
        experiment_path = pjoin(".", "experiments", args.name)

    if not os.path.isdir(experiment_path):
        parser.error("Cannot find experiment: {0}!".format(args.name))

    # Load experiments hyperparameters
    try:
        hyperparams = smartutils.load_dict_from_json_file(pjoin(experiment_path, "hyperparams.json"))
    except FileNotFoundError:
        hyperparams = smartutils.load_dict_from_json_file(pjoin(experiment_path, "..", "hyperparams.json"))

    with Timer("Loading dataset", newline=True):
        volume_manager = VolumeManager()
        dataset = datasets.load_tractography_dataset(
            [args.subject], volume_manager, name="dataset", use_sh_coeffs=hyperparams["use_sh_coeffs"]
        )
        print("Dataset size:", len(dataset))

    with Timer("Loading model"):
        if hyperparams["model"] == "gru_regression":
            from learn2track.models import GRU_Regression

            model = GRU_Regression.create(experiment_path, volume_manager=volume_manager)
        else:
            raise NameError("Unknown model: {}".format(hyperparams["model"]))

    with Timer("Building evaluation function"):
        loss = loss_factory(hyperparams, model, dataset)
        batch_scheduler = batch_schedulers.TractographyBatchScheduler(
            dataset,
            batch_size=1000,
            noisy_streamlines_sigma=None,
            use_data_augment=False,  # Otherwise it doubles the number of losses :-/
            seed=1234,
            shuffle_streamlines=False,
            normalize_target=hyperparams["normalize"],
        )

        loss_view = views.LossView(loss=loss, batch_scheduler=batch_scheduler)
        losses = loss_view.losses.view()

    with Timer("Saving streamlines"):
        tractogram = Tractogram(dataset.streamlines, affine_to_rasmm=dataset.subjects[0].signal.affine)
        tractogram.data_per_streamline["loss"] = losses
        nib.streamlines.save(tractogram, args.out)
Ejemplo n.º 3
0
def main():
    parser = build_args_parser()
    args = parser.parse_args()
    print(args)

    # Get experiment folder
    experiment_path = args.name
    if not os.path.isdir(experiment_path):
        # If not a directory, it must be the name of the experiment.
        experiment_path = pjoin(".", "experiments", args.name)

    if not os.path.isdir(experiment_path):
        parser.error('Cannot find experiment: {0}!'.format(args.name))

    # Load experiments hyperparameters
    try:
        hyperparams = smartutils.load_dict_from_json_file(
            pjoin(experiment_path, "hyperparams.json"))
    except FileNotFoundError:
        hyperparams = smartutils.load_dict_from_json_file(
            pjoin(experiment_path, "..", "hyperparams.json"))

    with Timer("Loading dataset", newline=True):
        volume_manager = VolumeManager()
        dataset = datasets.load_tractography_dataset(
            [args.streamlines],
            volume_manager,
            name="dataset",
            use_sh_coeffs=hyperparams['use_sh_coeffs'])
        print("Dataset size:", len(dataset))

    with Timer("Loading model"):
        model = None
        if hyperparams['model'] == 'gru_regression':
            from learn2track.models import GRU_Regression
            model = GRU_Regression.create(experiment_path,
                                          volume_manager=volume_manager)
        elif hyperparams['model'] == 'gru_mixture':
            from learn2track.models import GRU_Mixture
            model = GRU_Mixture.create(experiment_path,
                                       volume_manager=volume_manager)
        elif hyperparams['model'] == 'gru_multistep':
            from learn2track.models import GRU_Multistep_Gaussian
            model = GRU_Multistep_Gaussian.create(
                experiment_path, volume_manager=volume_manager)
            model.k = 1
            model.m = 1
        elif hyperparams['model'] == 'ffnn_regression':
            from learn2track.models import FFNN_Regression
            model = FFNN_Regression.create(experiment_path,
                                           volume_manager=volume_manager)
        else:
            raise NameError("Unknown model: {}".format(hyperparams['model']))
        print(str(model))

    tractogram_file = pjoin(experiment_path, args.out)
    if not os.path.isfile(tractogram_file) or args.force:
        if args.method == 'prediction':
            tractogram = prediction_tractogram(hyperparams, model, dataset,
                                               args.batch_size,
                                               args.prediction)
        elif args.method == 'evaluation':
            tractogram = evaluation_tractogram(hyperparams, model, dataset,
                                               args.batch_size, args.metric)
        else:
            raise ValueError("Unrecognized method: {}".format(args.method))

        tractogram.affine_to_rasmm = dataset.subjects[0].signal.affine
        nib.streamlines.save(tractogram, tractogram_file)
    else:
        print("Tractogram already exists. (use --force to generate it again)")
Ejemplo n.º 4
0
def main():
    parser = build_argparser()
    args = parser.parse_args()
    print(args)
    print("Using Theano v.{}".format(theano.version.short_version))

    hyperparams_to_exclude = ['max_epoch', 'force', 'name', 'view', 'shuffle_streamlines']
    # Use this for hyperparams added in a new version, but nonexistent from older versions
    retrocompatibility_defaults = {'feed_previous_direction': False,
                                   'normalize': False}
    experiment_path, hyperparams, resuming = utils.maybe_create_experiment_folder(args, exclude=hyperparams_to_exclude,
                                                                                  retrocompatibility_defaults=retrocompatibility_defaults)

    # Log the command currently running.
    with open(pjoin(experiment_path, 'cmd.txt'), 'a') as f:
        f.write(" ".join(sys.argv) + "\n")

    print("Resuming:" if resuming else "Creating:", experiment_path)

    with Timer("Loading dataset", newline=True):
        trainset_volume_manager = VolumeManager()
        validset_volume_manager = VolumeManager()
        trainset = datasets.load_tractography_dataset(args.train_subjects, trainset_volume_manager, name="trainset", use_sh_coeffs=args.use_sh_coeffs)
        validset = datasets.load_tractography_dataset(args.valid_subjects, validset_volume_manager, name="validset", use_sh_coeffs=args.use_sh_coeffs)
        print("Dataset sizes:", len(trainset), " |", len(validset))

        if args.view:
            tsne_view(trainset, trainset_volume_manager)
            sys.exit(0)

        batch_scheduler = batch_scheduler_factory(hyperparams, dataset=trainset, train_mode=True)
        print("An epoch will be composed of {} updates.".format(batch_scheduler.nb_updates_per_epoch))
        print(trainset_volume_manager.data_dimension, args.hidden_sizes, batch_scheduler.target_size)

    with Timer("Creating model"):
        input_size = trainset_volume_manager.data_dimension
        if hyperparams['feed_previous_direction']:
            input_size += 3

        model = model_factory(hyperparams,
                              input_size=input_size,
                              output_size=batch_scheduler.target_size,
                              volume_manager=trainset_volume_manager)
        model.initialize(weigths_initializer_factory(args.weights_initialization,
                                                     seed=args.initialization_seed))

    with Timer("Building optimizer"):
        loss = loss_factory(hyperparams, model, trainset)

        if args.clip_gradient is not None:
            loss.append_gradient_modifier(DirectionClipping(threshold=args.clip_gradient))

        optimizer = optimizer_factory(hyperparams, loss)

    with Timer("Building trainer"):
        trainer = Trainer(optimizer, batch_scheduler)

        # Log training error
        loss_monitor = views.MonitorVariable(loss.loss)
        avg_loss = tasks.AveragePerEpoch(loss_monitor)
        trainer.append_task(avg_loss)

        # Print average training loss.
        trainer.append_task(tasks.Print("Avg. training loss:         : {}", avg_loss))

        # if args.learn_to_stop:
        #     l2err_monitor = views.MonitorVariable(T.mean(loss.mean_sqr_error))
        #     avg_l2err = tasks.AveragePerEpoch(l2err_monitor)
        #     trainer.append_task(avg_l2err)
        #
        #     crossentropy_monitor = views.MonitorVariable(T.mean(loss.cross_entropy))
        #     avg_crossentropy = tasks.AveragePerEpoch(crossentropy_monitor)
        #     trainer.append_task(avg_crossentropy)
        #
        #     trainer.append_task(tasks.Print("Avg. training L2 err:       : {}", avg_l2err))
        #     trainer.append_task(tasks.Print("Avg. training stopping:     : {}", avg_crossentropy))
        #     trainer.append_task(tasks.Print("L2 err : {0:.4f}", l2err_monitor, each_k_update=100))
        #     trainer.append_task(tasks.Print("stopping : {0:.4f}", crossentropy_monitor, each_k_update=100))

        # Print NLL mean/stderror.
        # train_loss = L2DistanceForSequences(model, trainset)
        # train_batch_scheduler = StreamlinesBatchScheduler(trainset, batch_size=1000,
        #                                                   noisy_streamlines_sigma=None,
        #                                                   nb_updates_per_epoch=None,
        #                                                   seed=1234)

        # train_error = views.LossView(loss=train_loss, batch_scheduler=train_batch_scheduler)
        # trainer.append_task(tasks.Print("Trainset - Error        : {0:.2f} | {1:.2f}", train_error.sum, train_error.mean))

        # HACK: To make sure all subjects in the volume_manager are used in a batch, we have to split the trainset/validset in 2 volume managers
        model.volume_manager = validset_volume_manager
        valid_loss = loss_factory(hyperparams, model, validset)
        valid_batch_scheduler = batch_scheduler_factory(hyperparams,
                                                        dataset=validset,
                                                        train_mode=False)

        valid_error = views.LossView(loss=valid_loss, batch_scheduler=valid_batch_scheduler)
        trainer.append_task(tasks.Print("Validset - Error        : {0:.2f} | {1:.2f}", valid_error.sum, valid_error.mean))

        # HACK: Restore trainset volume manager
        model.volume_manager = trainset_volume_manager

        lookahead_loss = valid_error.sum

        direction_norm = views.MonitorVariable(T.sqrt(sum(map(lambda d: T.sqr(d).sum(), loss.gradients.values()))))
        # trainer.append_task(tasks.Print("||d|| : {0:.4f}", direction_norm))

        # logger = tasks.Logger(train_error.mean, valid_error.mean, valid_error.sum, direction_norm)
        logger = tasks.Logger(valid_error.mean, valid_error.sum, direction_norm)
        trainer.append_task(logger)

        if args.view:
            import pylab as plt

            def _plot(*args, **kwargs):
                plt.figure(1)
                plt.clf()
                plt.show(False)
                plt.subplot(121)
                plt.plot(np.array(logger.get_variable_history(0)).flatten(), label="Train")
                plt.plot(np.array(logger.get_variable_history(1)).flatten(), label="Valid")
                plt.legend()

                plt.subplot(122)
                plt.plot(np.array(logger.get_variable_history(3)).flatten(), label="||d'||")
                plt.draw()

            trainer.append_task(tasks.Callback(_plot))

        # Callback function to stop training if NaN is detected.
        def detect_nan(obj, status):
            if np.isnan(model.parameters[0].get_value().sum()):
                print("NaN detected! Stopping training now.")
                sys.exit()

        trainer.append_task(tasks.Callback(detect_nan, each_k_update=1))

        # Callback function to save training progression.
        def save_training(obj, status):
            trainer.save(experiment_path)

        trainer.append_task(tasks.Callback(save_training))

        # Early stopping with a callback for saving every time model improves.
        def save_improvement(obj, status):
            """ Save best model and training progression. """
            if np.isnan(model.parameters[0].get_value().sum()):
                print("NaN detected! Not saving the model. Crashing now.")
                sys.exit()

            print("*** Best epoch: {0} ***\n".format(obj.best_epoch))
            model.save(experiment_path)

        # Print time for one epoch
        trainer.append_task(tasks.PrintEpochDuration())
        trainer.append_task(tasks.PrintTrainingDuration())
        trainer.append_task(tasks.PrintTime(each_k_update=100))  # Profiling

        # Add stopping criteria
        trainer.append_task(stopping_criteria.MaxEpochStopping(args.max_epoch))
        early_stopping = stopping_criteria.EarlyStopping(lookahead_loss, lookahead=args.lookahead, eps=args.lookahead_eps, callback=save_improvement)
        trainer.append_task(early_stopping)

    with Timer("Compiling Theano graph"):
        trainer.build_theano_graph()

    if resuming:
        if not os.path.isdir(pjoin(experiment_path, 'training')):
            print("No 'training/' folder. Assuming it failed before"
                  " the end of the first epoch. Starting a new training.")
        else:
            with Timer("Loading"):
                trainer.load(experiment_path)

    with Timer("Training"):
        trainer.train()
Ejemplo n.º 5
0
def main():
    parser = build_argparser()
    args = parser.parse_args()
    print(args)
    print("Using Theano v.{}".format(theano.version.short_version))

    hyperparams_to_exclude = ['max_epoch', 'force', 'name', 'view', 'shuffle_streamlines']
    # Use this for hyperparams added in a new version, but nonexistent from older versions
    retrocompatibility_defaults = {'feed_previous_direction': False,
                                   'predict_offset': False,
                                   'normalize': False,
                                   'sort_streamlines': False,
                                   'keep_step_size': False,
                                   'use_layer_normalization': False,
                                   'drop_prob': 0.,
                                   'use_zoneout': False,
                                   'skip_connections': False}
    experiment_path, hyperparams, resuming = utils.maybe_create_experiment_folder(args, exclude=hyperparams_to_exclude,
                                                                                  retrocompatibility_defaults=retrocompatibility_defaults)

    # Log the command currently running.
    with open(pjoin(experiment_path, 'cmd.txt'), 'a') as f:
        f.write(" ".join(sys.argv) + "\n")

    print("Resuming:" if resuming else "Creating:", experiment_path)

    with Timer("Loading dataset", newline=True):
        trainset_volume_manager = VolumeManager()
        validset_volume_manager = VolumeManager()
        trainset = datasets.load_tractography_dataset(args.train_subjects, trainset_volume_manager, name="trainset",
                                                      use_sh_coeffs=args.use_sh_coeffs)
        validset = datasets.load_tractography_dataset(args.valid_subjects, validset_volume_manager, name="validset",
                                                      use_sh_coeffs=args.use_sh_coeffs)
        print("Dataset sizes:", len(trainset), " |", len(validset))

        batch_scheduler = batch_scheduler_factory(hyperparams, dataset=trainset, train_mode=True)
        print("An epoch will be composed of {} updates.".format(batch_scheduler.nb_updates_per_epoch))
        print(trainset_volume_manager.data_dimension, args.hidden_sizes, batch_scheduler.target_size)

    with Timer("Creating model"):
        input_size = trainset_volume_manager.data_dimension
        if hyperparams['feed_previous_direction']:
            input_size += 3

        model = model_factory(hyperparams,
                              input_size=input_size,
                              output_size=batch_scheduler.target_size,
                              volume_manager=trainset_volume_manager)
        model.initialize(weigths_initializer_factory(args.weights_initialization,
                                                     seed=args.initialization_seed))

    with Timer("Building optimizer"):
        loss = loss_factory(hyperparams, model, trainset)

        if args.clip_gradient is not None:
            loss.append_gradient_modifier(DirectionClipping(threshold=args.clip_gradient))

        optimizer = optimizer_factory(hyperparams, loss)

    with Timer("Building trainer"):
        trainer = Trainer(optimizer, batch_scheduler)

        # Log training error
        loss_monitor = views.MonitorVariable(loss.loss)
        avg_loss = tasks.AveragePerEpoch(loss_monitor)
        trainer.append_task(avg_loss)

        # Print average training loss.
        trainer.append_task(tasks.Print("Avg. training loss:         : {}", avg_loss))

        # if args.learn_to_stop:
        #     l2err_monitor = views.MonitorVariable(T.mean(loss.mean_sqr_error))
        #     avg_l2err = tasks.AveragePerEpoch(l2err_monitor)
        #     trainer.append_task(avg_l2err)
        #
        #     crossentropy_monitor = views.MonitorVariable(T.mean(loss.cross_entropy))
        #     avg_crossentropy = tasks.AveragePerEpoch(crossentropy_monitor)
        #     trainer.append_task(avg_crossentropy)
        #
        #     trainer.append_task(tasks.Print("Avg. training L2 err:       : {}", avg_l2err))
        #     trainer.append_task(tasks.Print("Avg. training stopping:     : {}", avg_crossentropy))
        #     trainer.append_task(tasks.Print("L2 err : {0:.4f}", l2err_monitor, each_k_update=100))
        #     trainer.append_task(tasks.Print("stopping : {0:.4f}", crossentropy_monitor, each_k_update=100))

        # Print NLL mean/stderror.
        # train_loss = L2DistanceForSequences(model, trainset)
        # train_batch_scheduler = StreamlinesBatchScheduler(trainset, batch_size=1000,
        #                                                   noisy_streamlines_sigma=None,
        #                                                   nb_updates_per_epoch=None,
        #                                                   seed=1234)

        # train_error = views.LossView(loss=train_loss, batch_scheduler=train_batch_scheduler)
        # trainer.append_task(tasks.Print("Trainset - Error        : {0:.2f} | {1:.2f}", train_error.sum, train_error.mean))

        # HACK: To make sure all subjects in the volume_manager are used in a batch, we have to split the trainset/validset in 2 volume managers
        model.volume_manager = validset_volume_manager
        model.drop_prob = 0.  # Do not use dropout/zoneout for evaluation
        valid_loss = loss_factory(hyperparams, model, validset)
        valid_batch_scheduler = batch_scheduler_factory(hyperparams,
                                                        dataset=validset,
                                                        train_mode=False)

        valid_error = views.LossView(loss=valid_loss, batch_scheduler=valid_batch_scheduler)
        trainer.append_task(tasks.Print("Validset - Error        : {0:.2f} | {1:.2f}", valid_error.sum, valid_error.mean))

        if hyperparams['model'] == 'ffnn_regression':
            valid_batch_scheduler2 = batch_scheduler_factory(hyperparams,
                                                             dataset=validset,
                                                             train_mode=False)

            valid_l2 = loss_factory(hyperparams, model, validset, loss_type="expected_value")
            valid_l2_error = views.LossView(loss=valid_l2, batch_scheduler=valid_batch_scheduler2)
            trainer.append_task(tasks.Print("Validset - {}".format(valid_l2.__class__.__name__) + "\t: {0:.2f} | {1:.2f}", valid_l2_error.sum, valid_l2_error.mean))

        # HACK: Restore trainset volume manager
        model.volume_manager = trainset_volume_manager
        model.drop_prob = hyperparams['drop_prob']  # Restore dropout

        lookahead_loss = valid_error.sum

        direction_norm = views.MonitorVariable(T.sqrt(sum(map(lambda d: T.sqr(d).sum(), loss.gradients.values()))))
        # trainer.append_task(tasks.Print("||d|| : {0:.4f}", direction_norm))

        # logger = tasks.Logger(train_error.mean, valid_error.mean, valid_error.sum, direction_norm)
        logger = tasks.Logger(valid_error.mean, valid_error.sum, direction_norm)
        trainer.append_task(logger)

        if args.view:
            import pylab as plt

            def _plot(*args, **kwargs):
                plt.figure(1)
                plt.clf()
                plt.show(False)
                plt.subplot(121)
                plt.plot(np.array(logger.get_variable_history(0)).flatten(), label="Train")
                plt.plot(np.array(logger.get_variable_history(1)).flatten(), label="Valid")
                plt.legend()

                plt.subplot(122)
                plt.plot(np.array(logger.get_variable_history(3)).flatten(), label="||d'||")
                plt.draw()

            trainer.append_task(tasks.Callback(_plot))

        # Callback function to stop training if NaN is detected.
        def detect_nan(obj, status):
            if np.isnan(model.parameters[0].get_value().sum()):
                print("NaN detected! Stopping training now.")
                sys.exit()

        trainer.append_task(tasks.Callback(detect_nan, each_k_update=1))

        # Callback function to save training progression.
        def save_training(obj, status):
            trainer.save(experiment_path)

        trainer.append_task(tasks.Callback(save_training))

        # Early stopping with a callback for saving every time model improves.
        def save_improvement(obj, status):
            """ Save best model and training progression. """
            if np.isnan(model.parameters[0].get_value().sum()):
                print("NaN detected! Not saving the model. Crashing now.")
                sys.exit()

            print("*** Best epoch: {0} ***\n".format(obj.best_epoch))
            model.save(experiment_path)

        # Print time for one epoch
        trainer.append_task(tasks.PrintEpochDuration())
        trainer.append_task(tasks.PrintTrainingDuration())
        trainer.append_task(tasks.PrintTime(each_k_update=100))  # Profiling

        # Add stopping criteria
        trainer.append_task(stopping_criteria.MaxEpochStopping(args.max_epoch))
        early_stopping = stopping_criteria.EarlyStopping(lookahead_loss, lookahead=args.lookahead, eps=args.lookahead_eps, callback=save_improvement)
        trainer.append_task(early_stopping)

    with Timer("Compiling Theano graph"):
        trainer.build_theano_graph()

    if resuming:
        if not os.path.isdir(pjoin(experiment_path, 'training')):
            print("No 'training/' folder. Assuming it failed before"
                  " the end of the first epoch. Starting a new training.")
        else:
            with Timer("Loading"):
                trainer.load(experiment_path)

    with Timer("Training"):
        trainer.train()
Ejemplo n.º 6
0
def main():
    parser = build_parser()
    args = parser.parse_args()
    print(args)

    # Get experiment folder
    experiment_path = args.name
    if not os.path.isdir(experiment_path):
        # If not a directory, it must be the name of the experiment.
        experiment_path = pjoin(".", "experiments", args.name)

    if not os.path.isdir(experiment_path):
        parser.error('Cannot find experiment: {0}!'.format(args.name))

    # Load experiments hyperparameters
    try:
        hyperparams = smartutils.load_dict_from_json_file(pjoin(experiment_path, "hyperparams.json"))
    except FileNotFoundError:
        hyperparams = smartutils.load_dict_from_json_file(pjoin(experiment_path, "..", "hyperparams.json"))

    with Timer("Loading dataset", newline=True):
        volume_manager = VolumeManager()
        dataset = datasets.load_tractography_dataset(args.subjects, volume_manager, name="dataset", use_sh_coeffs=hyperparams['use_sh_coeffs'])
        print("Dataset size:", len(dataset))

    with Timer("Loading model"):
        model = None
        if hyperparams['model'] == 'gru_regression':
            from learn2track.models import GRU_Regression
            model = GRU_Regression.create(experiment_path, volume_manager=volume_manager)
        elif hyperparams['model'] == 'gru_mixture':
            from learn2track.models import GRU_Mixture
            model = GRU_Mixture.create(experiment_path, volume_manager=volume_manager)
        elif hyperparams['model'] == 'gru_multistep':
            from learn2track.models import GRU_Multistep_Gaussian
            model = GRU_Multistep_Gaussian.create(experiment_path, volume_manager=volume_manager)
            model.k = 1
            model.m = 1
        elif hyperparams['model'] == 'ffnn_regression':
            from learn2track.models import FFNN_Regression
            model = FFNN_Regression.create(experiment_path, volume_manager=volume_manager)
        else:
            raise NameError("Unknown model: {}".format(hyperparams['model']))

    with Timer("Building evaluation function"):
        # Override K for gru_multistep
        if 'k' in hyperparams:
            hyperparams['k'] = 1

        batch_scheduler = batch_scheduler_factory(hyperparams, dataset, train_mode=False, batch_size_override=args.batch_size)
        loss = loss_factory(hyperparams, model, dataset, loss_type=args.loss_type)
        l2_error = views.LossView(loss=loss, batch_scheduler=batch_scheduler)

    with Timer("Evaluating...", newline=True):
        results_file = pjoin(experiment_path, "results.json")
        results = {}
        if os.path.isfile(results_file) and not args.force:
            print("Loading saved results... (use --force to re-run evaluation)")
            results = smartutils.load_dict_from_json_file(results_file)

        tag = ""
        if args.loss_type == 'expected_value' or hyperparams['model'] == 'gru_regression':
            tag = "_EV_L2_error"
        elif args.loss_type == 'maximum_component':
            tag = "_MC_L2_error"
        elif hyperparams['model'] == 'gru_mixture' or hyperparams['model'] == 'gru_multistep':
            tag = "_NLL"

        entry = args.dataset_name + tag

        if entry not in results or args.force:
            with Timer("Evaluating {}".format(entry)):
                dummy_status = Status()  # Forces recomputing results
                results[entry] = {'mean': float(l2_error.mean.view(dummy_status)), 'stderror': float(l2_error.stderror.view(dummy_status))}
                smartutils.save_dict_to_json_file(results_file, results)  # Update results file.

        print("{}: {:.4f} ± {:.4f}".format(entry, results[entry]['mean'], results[entry]['stderror']))
Ejemplo n.º 7
0
def main():
    parser = build_argparser()
    args = parser.parse_args()
    print(args)
    print("Using Theano v.{}".format(theano.version.short_version))

    with Timer("Loading dataset", newline=True):
        volume_manager = VolumeManager()
        dataset = datasets.load_tractography_dataset(
            args.subjects,
            volume_manager,
            name="dataset",
            use_sh_coeffs=args.use_sh_coeffs)
        print("Total streamlines: {}".format(len(dataset)))

    with Timer("Running T-SNE", newline=True):

        batch_scheduler = TractographyBatchScheduler(
            dataset,
            batch_size=min(len(dataset), 100000),
            noisy_streamlines_sigma=False,
            seed=1234,
            normalize_target=True)
        rng = np.random.RandomState(42)
        rng.shuffle(batch_scheduler.indices)

        # bundle_name_pattern = "CST_Left"
        # batch_inputs, batch_targets, batch_mask = batch_scheduler._prepare_batch(trainset.get_bundle(bundle_name_pattern, return_idx=True))
        inputs, _, mask = batch_scheduler._next_batch(0)

        # Keep the same number of streamlines per subject
        new_inputs = []
        new_mask = []
        for i in range(len(args.subjects)):
            subset = inputs[:, 0, -1] == i
            if subset.sum() < args.nb_streamlines_per_subject:
                raise NameError(
                    "Not enough streamlines for subject #{}".format(i))

            new_inputs += [inputs[subset][:args.nb_streamlines_per_subject]]
            new_mask += [mask[subset][:args.nb_streamlines_per_subject]]

        inputs = np.concatenate([new_inputs], axis=0)
        mask = np.concatenate([new_mask], axis=0)

        mask = mask.astype(bool)
        idx = np.arange(mask.sum())
        rng.shuffle(idx)

        coords = T.matrix('coords')
        eval_at_coords = theano.function([coords],
                                         volume_manager.eval_at_coords(coords))

        M = 2000 * len(dataset.subjects)
        coords = inputs[mask][idx[:M]]
        X = eval_at_coords(coords)

        from sklearn.manifold.t_sne import TSNE
        tsne = TSNE(n_components=2, verbose=2, random_state=42)
        Y = tsne.fit_transform(X)

        import matplotlib.pyplot as plt
        plt.figure()
        ids = range(len(dataset.subjects))
        markers = ['s', 'o', '^', 'v', '<', '>', 'h']
        colors = ['cyan', 'darkorange', 'darkgreen', 'magenta', 'pink', 'k']
        for i, marker, color in zip(ids, markers, colors):
            idx = coords[:, -1] == i
            print("Subject #{}: ".format(i), idx.sum())
            plt.scatter(Y[idx, 0],
                        Y[idx, 1],
                        20,
                        color=color,
                        marker=marker,
                        label="Subject #{}".format(i))

        plt.legend()
        plt.show()
Ejemplo n.º 8
0
def main():
    parser = build_parser()
    args = parser.parse_args()
    print(args)

    # Get experiment folder
    experiment_path = args.name
    if not os.path.isdir(experiment_path):
        # If not a directory, it must be the name of the experiment.
        experiment_path = pjoin(".", "experiments", args.name)

    if not os.path.isdir(experiment_path):
        parser.error('Cannot find experiment: {0}!'.format(args.name))

    # Load experiments hyperparameters
    try:
        hyperparams = smartutils.load_dict_from_json_file(
            pjoin(experiment_path, "hyperparams.json"))
    except FileNotFoundError:
        hyperparams = smartutils.load_dict_from_json_file(
            pjoin(experiment_path, "..", "hyperparams.json"))

    # Use this for hyperparams added in a new version, but nonexistent from older versions
    retrocompatibility_defaults = {
        'feed_previous_direction': False,
        'predict_offset': False,
        'normalize': False,
        'keep_step_size': False,
        'sort_streamlines': False,
        'use_layer_normalization': False,
        'drop_prob': 0.,
        'use_zoneout': False
    }
    for new_hyperparams, default_value in retrocompatibility_defaults.items():
        if new_hyperparams not in hyperparams:
            hyperparams[new_hyperparams] = default_value

    with Timer("Loading dataset", newline=True):
        volume_manager = VolumeManager()
        dataset = datasets.load_tractography_dataset(
            args.subjects,
            volume_manager,
            name="dataset",
            use_sh_coeffs=hyperparams['use_sh_coeffs'])
        print("Dataset size:", len(dataset))

    with Timer("Loading model"):
        model = None
        if hyperparams['model'] == 'gru_regression':
            from learn2track.models import GRU_Regression
            model = GRU_Regression.create(experiment_path,
                                          volume_manager=volume_manager)
        elif hyperparams['model'] == 'gru_gaussian':
            from learn2track.models import GRU_Gaussian
            model = GRU_Gaussian.create(experiment_path,
                                        volume_manager=volume_manager)
        elif hyperparams['model'] == 'gru_mixture':
            from learn2track.models import GRU_Mixture
            model = GRU_Mixture.create(experiment_path,
                                       volume_manager=volume_manager)
        elif hyperparams['model'] == 'gru_multistep':
            from learn2track.models import GRU_Multistep_Gaussian
            model = GRU_Multistep_Gaussian.create(
                experiment_path, volume_manager=volume_manager)
            model.k = 1
            model.m = 1
        elif hyperparams['model'] == 'ffnn_regression':
            from learn2track.models import FFNN_Regression
            model = FFNN_Regression.create(experiment_path,
                                           volume_manager=volume_manager)
        else:
            raise NameError("Unknown model: {}".format(hyperparams['model']))
        model.drop_prob = 0.  # Make sure dropout/zoneout is not used when testing

    with Timer("Building evaluation function"):
        # Override K for gru_multistep
        if 'k' in hyperparams:
            hyperparams['k'] = 1

        batch_scheduler = batch_scheduler_factory(
            hyperparams,
            dataset,
            train_mode=False,
            batch_size_override=args.batch_size)
        loss = loss_factory(hyperparams,
                            model,
                            dataset,
                            loss_type=args.loss_type)
        l2_error = views.LossView(loss=loss, batch_scheduler=batch_scheduler)

    with Timer("Evaluating...", newline=True):
        results_file = pjoin(experiment_path, "results.json")
        results = {}
        if os.path.isfile(results_file) and not args.force:
            print(
                "Loading saved results... (use --force to re-run evaluation)")
            results = smartutils.load_dict_from_json_file(results_file)

        tag = ""
        if args.loss_type == 'expected_value' or hyperparams[
                'model'] == 'gru_regression':
            tag = "_EV_L2_error"
        elif args.loss_type == 'maximum_component':
            tag = "_MC_L2_error"
        elif hyperparams['model'] in [
                'gru_gaussian', 'gru_mixture', 'gru_multistep'
        ]:
            tag = "_NLL"

        entry = args.dataset_name + tag

        if entry not in results or args.force:
            with Timer("Evaluating {}".format(entry)):
                dummy_status = Status()  # Forces recomputing results
                results[entry] = {
                    'mean': float(l2_error.mean.view(dummy_status)),
                    'stderror': float(l2_error.stderror.view(dummy_status))
                }
                smartutils.save_dict_to_json_file(
                    results_file, results)  # Update results file.

        print("{}: {:.4f} ± {:.4f}".format(entry, results[entry]['mean'],
                                           results[entry]['stderror']))