def initialize(self):
""" Initialize data containers and theano functions for training."""
self.rng = RandomState(30948348)
self.data_batches = []
self.y_batches = []
self.input_time_length = get_input_time_length(self.cnt_model)
self.n_sample_preds = get_n_sample_preds(self.cnt_model)
self.n_classes = self.cnt_model.output_shape[1]
# create train function
log.info("Compile train function...")
self._create_train_function()
log.info("Done compiling train function.")
def initialize(self):
""" Initialize data containers and theano functions for training."""
self.rng = RandomState(30948348)
self.data_batches = []
self.y_batches = []
self.input_time_length = get_input_time_length(self.cnt_model)
self.n_sample_preds = get_n_sample_preds(self.cnt_model)
self.n_classes = self.cnt_model.output_shape[1]
# create train function
log.info("Compile train function...")
self._create_train_function()
log.info("Done compiling train function.")
def compute_trial_acts(model, i_layer, iterator, train_set):
"""Compute activations per trial per sample for given layer of the model.
Parameters
----------
model: Lasagne layer
Final layer of the model.
i_layer: int
Index of layer to compute activations for.
iterator: DatasetIterator
Iterator to get batches from.
train_set: Dataset (Cnt)
Dataset to use.
Returns
-------
trial_acts: 3darray of float
Activations per trial per sample. #trialx#channelx#sample
"""
# compute number of inputs per trial
i_trial_starts, i_trial_ends = compute_trial_start_end_samples(
train_set.y,
check_trial_lengths_equal=True,
input_time_length=iterator.input_time_length)
# +1 since trial ends is inclusive
n_trial_len = i_trial_ends[0] - i_trial_starts[0] + 1
n_inputs_per_trial = int(
np.ceil(n_trial_len / float(iterator.n_sample_preds)))
log.info("Create theano function...")
all_layers = lasagne.layers.get_all_layers(model)
all_out_fn = create_pred_fn(all_layers[i_layer])
assert (iterator.input_time_length == get_input_time_length(model))
assert (iterator.n_sample_preds == get_n_sample_preds(model))
log.info("Compute activations...")
all_outs_per_batch = [
all_out_fn(batch[0])
for batch in iterator.get_batches(train_set, False)
]
batch_sizes = [
len(batch[0]) for batch in iterator.get_batches(train_set, False)
]
all_outs_per_batch = np.array(all_outs_per_batch)
n_trials = len(i_trial_starts)
log.info("Transform to trial activations...")
trial_acts = get_trial_acts(all_outs_per_batch,
batch_sizes,
n_trials=n_trials,
n_inputs_per_trial=n_inputs_per_trial,
n_trial_len=n_trial_len,
n_sample_preds=iterator.n_sample_preds)
log.info("Done.")
return trial_acts
def compute_trial_acts(model, i_layer, iterator, train_set):
"""Compute activations per trial per sample for given layer of the model.
Parameters
----------
model: Lasagne layer
Final layer of the model.
i_layer: int
Index of layer to compute activations for.
iterator: DatasetIterator
Iterator to get batches from.
train_set: Dataset (Cnt)
Dataset to use.
Returns
-------
trial_acts: 3darray of float
Activations per trial per sample. #trialx#channelx#sample
"""
# compute number of inputs per trial
i_trial_starts, i_trial_ends = compute_trial_start_end_samples(
train_set.y, check_trial_lengths_equal=True,
input_time_length=iterator.input_time_length)
# +1 since trial ends is inclusive
n_trial_len = i_trial_ends[0] - i_trial_starts[0] + 1
n_inputs_per_trial = int(np.ceil(n_trial_len / float(iterator.n_sample_preds)))
log.info("Create theano function...")
all_layers = lasagne.layers.get_all_layers(model)
all_out_fn = create_pred_fn(all_layers[i_layer])
assert(iterator.input_time_length == get_input_time_length(model))
assert(iterator.n_sample_preds == get_n_sample_preds(model))
log.info("Compute activations...")
all_outs_per_batch = [all_out_fn(batch[0])
for batch in iterator.get_batches(train_set, False)]
batch_sizes = [len(batch[0]) for batch in iterator.get_batches(train_set, False)]
all_outs_per_batch = np.array(all_outs_per_batch)
n_trials = len(i_trial_starts)
log.info("Transform to trial activations...")
trial_acts = get_trial_acts(all_outs_per_batch,
batch_sizes, n_trials=n_trials,
n_inputs_per_trial=n_inputs_per_trial,
n_trial_len=n_trial_len,
n_sample_preds=iterator.n_sample_preds)
log.info("Done.")
return trial_acts
def create_experiment(yaml_filename, seed=9859295):
"""Utility function to create experiment from yaml file"""
# for reproducibility for layer weights
# should be same seed as in experiment_runner.py
lasagne.random.set_rng(RandomState(seed))
train_dict = yaml_parse.load(open(yaml_filename, 'r'))
layers = load_layers_from_dict(train_dict)
final_layer = layers[-1]
dataset = train_dict['dataset']
splitter = train_dict['dataset_splitter']
if (np.any([hasattr(l, 'n_stride') for l in layers])):
n_sample_preds = get_n_sample_preds(final_layer)
# for backwards compatibility input time length also
input_time_length = get_input_time_length(final_layer)
log.info("Setting n_sample preds automatically to {:d}".format(
n_sample_preds))
for monitor in train_dict['exp_args']['monitors']:
if hasattr(monitor, 'n_sample_preds'):
monitor.n_sample_preds = n_sample_preds
if hasattr(monitor, 'input_time_length'):
monitor.input_time_length = input_time_length
train_dict['exp_args']['iterator'].n_sample_preds = n_sample_preds
log.info("Input window length is {:d}".format(
get_model_input_window(final_layer)))
# add early stop chan, encessary for backwards compatibility
exp_args = train_dict['exp_args']
exp_args['remember_best_chan'] = train_dict['exp_args'].pop(
'remember_best_chan', 'valid_misclass')
exp_args['run_after_early_stop'] = train_dict['exp_args'].pop(
'run_after_early_stop', True)
exp = Experiment(final_layer, dataset, splitter, **exp_args)
assert len(np.setdiff1d(
layers, lasagne.layers.get_all_layers(final_layer))) == 0, (
"All layers "
"should be used, unused {:s}".format(
str(
np.setdiff1d(layers,
lasagne.layers.get_all_layers(final_layer)))))
return exp
def create_experiment(yaml_filename, seed=9859295):
"""Utility function to create experiment from yaml file"""
# for reproducibility for layer weights
# should be same seed as in experiment_runner.py
lasagne.random.set_rng(RandomState(seed))
train_dict = yaml_parse.load(open(yaml_filename, 'r'))
layers = load_layers_from_dict(train_dict)
final_layer = layers[-1]
dataset = train_dict['dataset']
splitter = train_dict['dataset_splitter']
if (np.any([hasattr(l, 'n_stride') for l in layers])):
n_sample_preds = get_n_sample_preds(final_layer)
# for backwards compatibility input time length also
input_time_length = get_input_time_length(final_layer)
log.info("Setting n_sample preds automatically to {:d}".format(
n_sample_preds))
for monitor in train_dict['exp_args']['monitors']:
if hasattr(monitor, 'n_sample_preds'):
monitor.n_sample_preds = n_sample_preds
if hasattr(monitor, 'input_time_length'):
monitor.input_time_length = input_time_length
train_dict['exp_args']['iterator'].n_sample_preds = n_sample_preds
log.info("Input window length is {:d}".format(
get_model_input_window(final_layer)))
# add early stop chan, encessary for backwards compatibility
exp_args = train_dict['exp_args']
exp_args['remember_best_chan'] = train_dict['exp_args'].pop('remember_best_chan',
'valid_misclass')
exp_args['run_after_early_stop'] = train_dict['exp_args'].pop('run_after_early_stop',
True)
exp = Experiment(final_layer, dataset, splitter,
**exp_args)
assert len(np.setdiff1d(layers,
lasagne.layers.get_all_layers(final_layer))) == 0, ("All layers "
"should be used, unused {:s}".format(str(np.setdiff1d(layers,
lasagne.layers.get_all_layers(final_layer)))))
return exp
def get_n_samples_pred_window(self):
return get_input_time_length(self.model)