Python monitor.Monitor类代码示例

 def channel_scaling_checker(num_examples, mode, num_batches, batch_size):
     num_features = 2
     monitor = Monitor(DummyModel(num_features))
     dataset = DummyDataset(num_examples, num_features)
     monitor.add_dataset(dataset=dataset, mode=mode,
                             num_batches=num_batches, batch_size=batch_size)
     vis_batch = T.matrix()
     mean = vis_batch.mean()
     data_specs = (monitor.model.get_input_space(),
                   monitor.model.get_input_source())
     monitor.add_channel(name='mean', ipt=vis_batch, val=mean, dataset=dataset,
                         data_specs=data_specs)
     monitor()
     assert 'mean' in monitor.channels
     mean = monitor.channels['mean']
     assert len(mean.val_record) == 1
     actual = mean.val_record[0]
     X = dataset.get_design_matrix()
     if batch_size is not None and num_batches is not None:
         total = min(num_examples, num_batches * batch_size)
     else:
         total = num_examples
     expected = X[:total].mean()
     if not np.allclose(expected, actual):
         raise AssertionError("Expected monitor to contain %f but it has "
                              "%f" % (expected, actual))

def test_serialization_guard():

    # tests that Train refuses to serialize the dataset

    dim = 2
    m = 11

    rng = np.random.RandomState([28,9,2012])
    X = rng.randn(m, dim)
    dataset = DenseDesignMatrix(X=X)

    model = DummyModel(dim)
    # make the dataset part of the model, so it will get
    # serialized
    model.dataset = dataset

    Monitor.get_monitor(model)

    algorithm = DummyAlgorithm()

    train = Train(dataset, model, algorithm, save_path='_tmp_unit_test.pkl',
                 save_freq=1, extensions=None)

    try:
        train.main_loop()
    except RuntimeError:
        return
    assert False # train did not complain, this is a bug

 def channel_scaling_checker(num_examples, mode, num_batches, batch_size):
     num_features = 2
     monitor = Monitor(DummyModel(num_features))
     dataset = DummyDataset(num_examples, num_features)
     try:
         monitor.add_dataset(dataset=dataset, mode=mode,
                             num_batches=num_batches, batch_size=batch_size)
     except NotImplementedError:
         # make sure this was due to the unimplemented batch_size case
         if num_batches is None:
             assert num_examples % batch_size != 0
         else:
             assert num_examples % num_batches != 0
         raise SkipTest()
     vis_batch = T.matrix()
     mean = vis_batch.mean()
     monitor.add_channel(name='mean', ipt=vis_batch, val=mean, dataset=dataset)
     monitor()
     assert 'mean' in monitor.channels
     mean = monitor.channels['mean']
     assert len(mean.val_record) == 1
     actual = mean.val_record[0]
     X = dataset.get_design_matrix()
     if batch_size is not None and num_batches is not None:
         total = min(num_examples, num_batches * batch_size)
     else:
         total = num_examples
     expected = X[:total].mean()
     if not np.allclose(expected, actual):
         raise AssertionError("Expected monitor to contain %f but it has "
                              "%f" % (expected, actual))

 def prep_valtest_monitor(self, model, batch_size):
     minibatch = T.as_tensor_variable(
                     self.valid_ddm.get_batch_topo(batch_size), 
                     name='minibatch'
                 )
     target = T.matrix('target')
     Accuracy = self.get_classification_accuracy(model, minibatch, target)           
     monitor = Monitor.get_monitor(model)
     
     monitor.add_dataset(self.valid_ddm, 'sequential', batch_size)
     monitor.add_channel("Validation Classification Accuracy",
                         (minibatch, target),
                         Accuracy,
                         self.valid_ddm)
     monitor.add_channel("Validation Missclassification",
                         (minibatch, target),
                         1.0-Accuracy,
                         self.valid_ddm)
                         
     if self.test_ddm is not None:
         monitor.add_dataset(self.test_ddm, 'sequential', batch_size)
         monitor.add_channel("Test Classification Accuracy",
                             (minibatch, target),
                             Accuracy,
                             self.test_ddm)

def test_reject_empty():

    # Test that Monitor raises an error if asked to iterate over 0 batches

    BATCH_SIZE = 2
    num_examples = BATCH_SIZE
    NUM_FEATURES = 3

    model = DummyModel(NUM_FEATURES)
    monitor = Monitor.get_monitor(model)

    monitoring_dataset = DummyDataset(num_examples = num_examples,
            num_features = NUM_FEATURES)

    monitor.add_dataset(monitoring_dataset, 'sequential', batch_size=BATCH_SIZE,
            num_batches = 0)

    name = 'z'

    monitor.add_channel(name = name,
            ipt = model.input_space.make_theano_batch(),
            val = 0.,
            data_specs=(model.get_input_space(), model.get_input_source()))

    try:
        monitor()
    except ValueError:
        return
    assert False

    def main_loop(self):
        """
        Repeatedly runs an epoch of the training algorithm, runs any
        epoch-level callbacks, and saves the model.
        """
        if self.algorithm is None:
            self.model.monitor = Monitor.get_monitor(self.model)
            self.run_callbacks_and_monitoring()
            while self.model.train(dataset=self.dataset):
                self.run_callbacks_and_monitoring()
                if self.save_freq > 0 and self.epochs % self.save_freq == 0:
                    self.save()
                self.epochs += 1
            self.run_callbacks_and_monitoring()
            if self.save_freq > 0:
                self.save()
        else:
            self.algorithm.setup(model=self.model, dataset=self.dataset)
            self.run_callbacks_and_monitoring()
            epoch_start = datetime.datetime.now()
            while self.algorithm.train(dataset=self.dataset):
                epoch_end = datetime.datetime.now()
                print 'Time this epoch:', str(epoch_end - epoch_start)
                epoch_start = datetime.datetime.now()
                self.run_callbacks_and_monitoring()
                if self.save_freq > 0 and self.epochs % self.save_freq == 0:
                    self.save()
                self.epochs += 1
            self.run_callbacks_and_monitoring()

            if self.save_freq > 0:
                self.save()

 def setup_monitor(self):
     if self.topo_view:
         print "topo view"
         self.minibatch = T.as_tensor_variable(
                     self.valid_ddm.get_batch_topo(self.batch_size), 
                     name='minibatch'
                 )
     else:
         print "design view"
         batch = self.valid_ddm.get_batch_design(self.batch_size)
         if isinstance(batch, spp.csr_matrix):
             print "sparse2"
             self.minibatch = self.model.get_input_space().make_batch_theano()
             print type(self.minibatch)
         else:
             self.minibatch = T.as_tensor_variable(
                     self.valid_ddm.get_batch_design(self.batch_size), 
                     name='minibatch'
                 )
                     
     self.target = T.matrix('target')  
     
     self.monitor = Monitor.get_monitor(self.model)
     self.log_channel_names = []
     self.log_channel_names.extend(self.base_channel_names)
     
     self.monitor.add_dataset(self.valid_ddm, 'sequential', 
                                 self.batch_size)
     if self.test_ddm is not None:
         self.monitor.add_dataset(self.test_ddm, 'sequential', 
                                     self.batch_size)

def test_ambig_data():

    # test that the right error is raised if you
    # add a channel to a monitor that has multiple datasets
    # and don't specify the dataset

    BATCH_SIZE = 2
    num_examples = BATCH_SIZE
    NUM_FEATURES = 3

    model = DummyModel(NUM_FEATURES)
    monitor = Monitor.get_monitor(model)

    first = DummyDataset(num_examples = num_examples,
            num_features = NUM_FEATURES)
    second = DummyDataset(num_examples = num_examples,
            num_features = NUM_FEATURES)

    monitor.add_dataset(first, 'sequential', batch_size=BATCH_SIZE)
    monitor.add_dataset(second, 'sequential', batch_size=BATCH_SIZE)


    name = 'num_prereq_calls'

    try:
        monitor.add_channel(name = name,
            ipt = model.input_space.make_theano_batch(),
            val = 0.,
            data_specs=(model.get_input_space(), model.get_input_source()))
    except ValueError as e:
        assert exc_message(e) == _err_ambig_data
        return
    assert False

def test_prereqs_batch():

    # Test that prereqs get run before each monitoring batch

    BATCH_SIZE = 2
    num_examples = 2 * BATCH_SIZE
    NUM_FEATURES = 3

    model = DummyModel(NUM_FEATURES)
    monitor = Monitor.get_monitor(model)

    monitoring_dataset = DummyDataset(num_examples=num_examples, num_features=NUM_FEATURES)

    monitor.add_dataset(monitoring_dataset, "sequential", batch_size=BATCH_SIZE)

    sign = sharedX(1.0)

    def prereq(X, y):
        sign.set_value(-sign.get_value())

    name = "batches_should_cancel_to_0"

    monitor.add_channel(name=name, ipt=model.input_space.make_theano_batch(), val=sign, prereqs=[prereq])

    channel = monitor.channels[name]

    assert len(channel.val_record) == 0
    monitor()
    assert channel.val_record == [0]
    monitor()
    assert channel.val_record == [0, 0]

 def prep_valtest_monitor(self, model, batch_size):
     if self.topo_view:
         print "topo view"
         minibatch = T.as_tensor_variable(
                         self.valid_ddm.get_batch_topo(batch_size), 
                         name='minibatch'
                     )
     else:
         print "design view"
         minibatch = T.as_tensor_variable(
                         self.valid_ddm.get_batch_design(batch_size), 
                         name='minibatch'
                     )
     target = T.matrix('target')
     valMSE = MissingTargetCost()(model, minibatch, target)
     monitor = Monitor.get_monitor(model)
     
     monitor.add_dataset(self.valid_ddm, 'sequential', batch_size)
     monitor.add_channel("Validation MSE",
                         (minibatch, target),
                         valMSE,
                         self.valid_ddm)
                         
     if self.test_ddm is not None:
         monitor.add_dataset(self.test_ddm, 'sequential', batch_size)
         monitor.add_channel("Test MSE",
                             (minibatch, target),
                             valMSE,
                             self.test_ddm)

    def setup(self, model, dataset):
        """
        Allows the training algorithm to do some preliminary configuration
        *before* we actually start training the model. The dataset is provided
        in case other derived training algorithms need to modify model based on
        the dataset.

        Parameters
        ----------
        model: a Python object representing the model to train loosely
        implementing the interface of models.model.Model.

        dataset: a pylearn2.datasets.dataset.Dataset object used to draw
        training data
        """
        self.model = model

        self.monitor = Monitor.get_monitor(model)

        if self.monitoring_dataset is not None:
            # Get the data specifications needed by the model
            space, source = model.get_monitoring_data_specs()

            # Create Theano variables for each of the individual components
            # of that data. Usually, it will be X for inputs and Y for targets.
            # First, we need to find these components, and put them in a tuple
            mapping = DataSpecsMapping((space, source))
            space_tuple = mapping.flatten(space, return_tuple=True)
            source_tuple = mapping.flatten(source, return_tuple=True)
            # Then, build a flat tuple of these Theano variables
            ipt = tuple(sp.make_theano_batch(name='monitor_%s' % src)
                    for (sp, src) in safe_zip(space_tuple, source_tuple))
            # Finally, organize them back into a structure expected by the
            # monitoring channels of the model
            nested_ipt = mapping.nest(ipt)

            self.monitor.add_dataset(dataset=self.monitoring_dataset,
                                mode="sequential",
                                batch_size=self.batch_size,
                                num_batches=self.monitoring_batches)

            channels = model.get_monitoring_channels(nested_ipt)
            if not isinstance(channels, dict):
                raise TypeError("model.get_monitoring_channels must return a "
                                "dictionary, but it returned " + str(channels))
            for name in channels:
                J = channels[name]
                if isinstance(J, tuple):
                    assert len(J) == 2
                    J, prereqs = J
                else:
                    prereqs = None

                self.monitor.add_channel(name=name,
                                         ipt=nested_ipt,
                                         val=J,
                                         prereqs=prereqs,
                                         data_specs=(space, source))
        self.first = True
        self.bSetup = True

 def setup_monitor(self):
     if self.topo_view:
         print "topo view"
         self.minibatch = T.as_tensor_variable(
                     self.valid_ddm.get_batch_topo(self.batch_size), 
                     name='minibatch'
                 )
     else:
         print "design view"
         self.minibatch = T.as_tensor_variable(
                     self.valid_ddm.get_batch_design(self.batch_size), 
                     name='minibatch'
                 )
                     
     self.target = T.tensor3('target')  
     
     self.monitor = Monitor.get_monitor(self.model)
     self.log_channel_names = []
     self.log_channel_names.extend(self.base_channel_names)
     
     self.monitor.add_dataset(self.valid_ddm, 'sequential', 
                                 self.batch_size)
     if self.test_ddm is not None:
         self.monitor.add_dataset(self.test_ddm, 'sequential', 
                                     self.batch_size)

def test_prereqs():

    # Test that prereqs get run before the monitoring channels are computed

    BATCH_SIZE = 2
    num_examples = BATCH_SIZE
    NUM_FEATURES = 3

    model = DummyModel(NUM_FEATURES)
    monitor = Monitor.get_monitor(model)

    monitoring_dataset = DummyDataset(num_examples = num_examples,
            num_features = NUM_FEATURES)

    monitor.add_dataset(monitoring_dataset, 'sequential', batch_size=BATCH_SIZE)

    prereq_counter = sharedX(0.)
    def prereq(*data):
        prereq_counter.set_value(prereq_counter.get_value() + 1.)

    name = 'num_prereq_calls'

    monitor.add_channel(name = name,
            ipt = model.input_space.make_theano_batch(),
            val = prereq_counter,
            prereqs = [ prereq ],
            data_specs=(model.get_input_space(), model.get_input_source()))

    channel = monitor.channels[name]

    assert len(channel.val_record) == 0
    monitor()
    assert channel.val_record == [1]
    monitor()
    assert channel.val_record == [1,2]

def test_save_load_save():

    """
    Test that a monitor can be saved, then loaded, and then the loaded
    copy can be saved again.
    This only tests that the serialization and deserialization processes
    don't raise an exception. It doesn't test for correctness at all.
    """

    model = DummyModel(1)
    monitor = Monitor.get_monitor(model)

    num_examples = 2
    num_features = 3
    num_batches = 1
    batch_size = 2

    dataset = DummyDataset(num_examples, num_features)
    monitor.add_dataset(dataset=dataset,
                            num_batches=num_batches, batch_size=batch_size)
    vis_batch = T.matrix()
    mean = vis_batch.mean()
    data_specs = (monitor.model.get_input_space(),
                  monitor.model.get_input_source())
    monitor.add_channel(name='mean', ipt=vis_batch, val=mean, dataset=dataset,
                        data_specs=data_specs)

    saved = to_string(monitor)
    monitor = from_string(saved)
    saved_again = to_string(monitor)

    def setup(self, model, dataset):
        """
        Initialize the training algorithm. Should be called
        once before calls to train.

        Parameters
        ----------
        model : object
            Model to be trained.  Object implementing the pylearn2 Model
            interface.
        dataset : object
            Dataset on which to train.  Object implementing the
            pylearn2 Dataset interface.
        """

        self.model = model

        self.monitor = Monitor.get_monitor(model)
        self.monitor.set_dataset(dataset=self.monitoring_dataset,
                                 batches=self.monitoring_batches,
                                 batch_size=self.batch_size)

        X = T.matrix(name='sgd_X')
        J = self.cost(model, X)
        if J.name is None:
            J.name = 'sgd_cost(' + X.name + ')'
        self.monitor.add_channel(name=J.name, ipt=X, val=J)
        params = model.get_params()

        for i, param in enumerate(params):
            if param.name is None:
                param.name = 'sgd_params[%d]' % i

        grads = dict(zip(params, T.grad(J, params)))

        for param in grads:
            if grads[param].name is None:
                grads[param].name = ('grad(%(costname)s, %(paramname)s)' %
                                     {'costname': J.name,
                                      'paramname': param.name})

        learning_rate = T.scalar('sgd_learning_rate')

        updates = dict(zip(params, [param - learning_rate * grads[param]
                                    for param in params]))

        for param in updates:
            if updates[param].name is None:
                updates[param].name = 'sgd_update(' + param.name + ')'

        model.censor_updates(updates)
        for param in updates:
            if updates[param] is None:
                updates[param].name = 'censor(sgd_update(' + param.name + '))'

        self.sgd_update = function([X, learning_rate], updates=updates,
                                   name='sgd_update')
        self.params = params
        self.bSetup = True