def _run(storm_metafile_name, warning_dir_name):
"""Finds which storms are linked to an NWS tornado warning.
This is effectively the main method.
:param storm_metafile_name: See documentation at top of file.
:param warning_dir_name: Same.
"""
print(
'Reading storm metadata from: "{0:s}"...'.format(storm_metafile_name))
full_storm_id_strings, valid_times_unix_sec = (
tracking_io.read_ids_and_times(storm_metafile_name))
secondary_id_strings = (
temporal_tracking.full_to_partial_ids(full_storm_id_strings)[-1])
these_times_unix_sec = numpy.concatenate(
(valid_times_unix_sec, valid_times_unix_sec - NUM_SECONDS_PER_DAY,
valid_times_unix_sec + NUM_SECONDS_PER_DAY))
spc_date_strings = [
time_conversion.time_to_spc_date_string(t)
for t in these_times_unix_sec
]
spc_date_strings = numpy.unique(numpy.array(spc_date_strings))
linked_secondary_id_strings = []
for this_spc_date_string in spc_date_strings:
this_file_name = '{0:s}/tornado_warnings_{1:s}.p'.format(
warning_dir_name, this_spc_date_string)
print('Reading warnings from: "{0:s}"...'.format(this_file_name))
this_file_handle = open(this_file_name, 'rb')
this_warning_table = pickle.load(this_file_handle)
this_file_handle.close()
this_num_warnings = len(this_warning_table.index)
for k in range(this_num_warnings):
linked_secondary_id_strings += (
this_warning_table[LINKED_SECONDARY_IDS_KEY].values[k])
print(SEPARATOR_STRING)
storm_warned_flags = numpy.array(
[s in linked_secondary_id_strings for s in secondary_id_strings],
dtype=bool)
print(('{0:d} of {1:d} storm objects are linked to an NWS tornado warning!'
).format(numpy.sum(storm_warned_flags), len(storm_warned_flags)))
def _run(cnn_file_name, upconvnet_file_name, top_example_dir_name,
baseline_storm_metafile_name, trial_storm_metafile_name,
num_baseline_examples, num_trial_examples, num_novel_examples,
cnn_feature_layer_name, percent_svd_variance_to_keep,
output_file_name):
"""Runs novelty detection.
This is effectively the main method.
:param cnn_file_name: See documentation at top of file.
:param upconvnet_file_name: Same.
:param top_example_dir_name: Same.
:param baseline_storm_metafile_name: Same.
:param trial_storm_metafile_name: Same.
:param num_baseline_examples: Same.
:param num_trial_examples: Same.
:param num_novel_examples: Same.
:param cnn_feature_layer_name: Same.
:param percent_svd_variance_to_keep: Same.
:param output_file_name: Same.
:raises: ValueError: if dimensions of first CNN input matrix != dimensions
of upconvnet output.
"""
print('Reading trained CNN from: "{0:s}"...'.format(cnn_file_name))
cnn_model_object = cnn.read_model(cnn_file_name)
cnn_metafile_name = '{0:s}/model_metadata.p'.format(
os.path.split(cnn_file_name)[0]
)
print('Reading trained upconvnet from: "{0:s}"...'.format(
upconvnet_file_name))
upconvnet_model_object = cnn.read_model(upconvnet_file_name)
# ucn_output_dimensions = numpy.array(
# upconvnet_model_object.output.get_shape().as_list()[1:], dtype=int
# )
if isinstance(cnn_model_object.input, list):
first_cnn_input_tensor = cnn_model_object.input[0]
else:
first_cnn_input_tensor = cnn_model_object.input
cnn_input_dimensions = numpy.array(
first_cnn_input_tensor.get_shape().as_list()[1:], dtype=int
)
# if not numpy.array_equal(cnn_input_dimensions, ucn_output_dimensions):
# error_string = (
# 'Dimensions of first CNN input matrix ({0:s}) should equal '
# 'dimensions of upconvnet output ({1:s}).'
# ).format(str(cnn_input_dimensions), str(ucn_output_dimensions))
#
# raise ValueError(error_string)
print('Reading CNN metadata from: "{0:s}"...'.format(cnn_metafile_name))
cnn_metadata_dict = cnn.read_model_metadata(cnn_metafile_name)
print('Reading metadata for baseline examples from: "{0:s}"...'.format(
baseline_storm_metafile_name))
baseline_full_id_strings, baseline_times_unix_sec = (
tracking_io.read_ids_and_times(baseline_storm_metafile_name)
)
print('Reading metadata for trial examples from: "{0:s}"...'.format(
trial_storm_metafile_name))
trial_full_id_strings, trial_times_unix_sec = (
tracking_io.read_ids_and_times(trial_storm_metafile_name)
)
if 0 < num_baseline_examples < len(baseline_full_id_strings):
baseline_full_id_strings = baseline_full_id_strings[
:num_baseline_examples]
baseline_times_unix_sec = baseline_times_unix_sec[
:num_baseline_examples]
if 0 < num_trial_examples < len(trial_full_id_strings):
trial_full_id_strings = trial_full_id_strings[:num_trial_examples]
trial_times_unix_sec = trial_times_unix_sec[:num_trial_examples]
num_trial_examples = len(trial_full_id_strings)
if num_novel_examples <= 0:
num_novel_examples = num_trial_examples + 0
num_novel_examples = min([num_novel_examples, num_trial_examples])
print('Number of novel examples to find: {0:d}'.format(num_novel_examples))
bad_baseline_indices = tracking_utils.find_storm_objects(
all_id_strings=baseline_full_id_strings,
all_times_unix_sec=baseline_times_unix_sec,
id_strings_to_keep=trial_full_id_strings,
times_to_keep_unix_sec=trial_times_unix_sec, allow_missing=True)
print('Removing {0:d} trial examples from baseline set...'.format(
len(bad_baseline_indices)
))
baseline_times_unix_sec = numpy.delete(
baseline_times_unix_sec, bad_baseline_indices
)
baseline_full_id_strings = numpy.delete(
numpy.array(baseline_full_id_strings), bad_baseline_indices
)
baseline_full_id_strings = baseline_full_id_strings.tolist()
# num_baseline_examples = len(baseline_full_id_strings)
print(SEPARATOR_STRING)
list_of_baseline_input_matrices, _ = testing_io.read_specific_examples(
top_example_dir_name=top_example_dir_name,
desired_full_id_strings=baseline_full_id_strings,
desired_times_unix_sec=baseline_times_unix_sec,
option_dict=cnn_metadata_dict[cnn.TRAINING_OPTION_DICT_KEY],
list_of_layer_operation_dicts=cnn_metadata_dict[
cnn.LAYER_OPERATIONS_KEY]
)
print(SEPARATOR_STRING)
list_of_trial_input_matrices, _ = testing_io.read_specific_examples(
top_example_dir_name=top_example_dir_name,
desired_full_id_strings=trial_full_id_strings,
desired_times_unix_sec=trial_times_unix_sec,
option_dict=cnn_metadata_dict[cnn.TRAINING_OPTION_DICT_KEY],
list_of_layer_operation_dicts=cnn_metadata_dict[
cnn.LAYER_OPERATIONS_KEY]
)
print(SEPARATOR_STRING)
novelty_dict = novelty_detection.do_novelty_detection(
list_of_baseline_input_matrices=list_of_baseline_input_matrices,
list_of_trial_input_matrices=list_of_trial_input_matrices,
cnn_model_object=cnn_model_object,
cnn_feature_layer_name=cnn_feature_layer_name,
upconvnet_model_object=upconvnet_model_object,
num_novel_examples=num_novel_examples, multipass=False,
percent_svd_variance_to_keep=percent_svd_variance_to_keep)
print(SEPARATOR_STRING)
print('Adding metadata to novelty-detection results...')
novelty_dict = novelty_detection.add_metadata(
novelty_dict=novelty_dict,
baseline_full_id_strings=baseline_full_id_strings,
baseline_storm_times_unix_sec=baseline_times_unix_sec,
trial_full_id_strings=trial_full_id_strings,
trial_storm_times_unix_sec=trial_times_unix_sec,
cnn_file_name=cnn_file_name, upconvnet_file_name=upconvnet_file_name)
print('Denormalizing inputs and outputs of novelty detection...')
novelty_dict[novelty_detection.BASELINE_INPUTS_KEY] = (
model_interpretation.denormalize_data(
list_of_input_matrices=novelty_dict[
novelty_detection.BASELINE_INPUTS_KEY
],
model_metadata_dict=cnn_metadata_dict)
)
novelty_dict[novelty_detection.TRIAL_INPUTS_KEY] = (
model_interpretation.denormalize_data(
list_of_input_matrices=novelty_dict[
novelty_detection.TRIAL_INPUTS_KEY
],
model_metadata_dict=cnn_metadata_dict)
)
cnn_metadata_dict[
cnn.TRAINING_OPTION_DICT_KEY][trainval_io.SOUNDING_FIELDS_KEY] = None
novelty_dict[novelty_detection.NOVEL_IMAGES_UPCONV_KEY] = (
model_interpretation.denormalize_data(
list_of_input_matrices=[
novelty_dict[novelty_detection.NOVEL_IMAGES_UPCONV_KEY]
],
model_metadata_dict=cnn_metadata_dict)
)[0]
novelty_dict[novelty_detection.NOVEL_IMAGES_UPCONV_SVD_KEY] = (
model_interpretation.denormalize_data(
list_of_input_matrices=[
novelty_dict[novelty_detection.NOVEL_IMAGES_UPCONV_SVD_KEY]
],
model_metadata_dict=cnn_metadata_dict)
)[0]
print('Writing results to: "{0:s}"...'.format(output_file_name))
novelty_detection.write_standard_file(novelty_dict=novelty_dict,
pickle_file_name=output_file_name)
def _run(model_file_name, component_type_string, target_class, layer_name,
ideal_activation, neuron_indices, channel_index, top_example_dir_name,
storm_metafile_name, num_examples, randomize_weights,
cascading_random, output_file_name):
"""Computes saliency map for each storm object and each model component.
This is effectively the main method.
:param model_file_name: See documentation at top of file.
:param component_type_string: Same.
:param target_class: Same.
:param layer_name: Same.
:param ideal_activation: Same.
:param neuron_indices: Same.
:param channel_index: Same.
:param top_example_dir_name: Same.
:param storm_metafile_name: Same.
:param num_examples: Same.
:param randomize_weights: Same.
:param cascading_random: Same.
:param output_file_name: Same.
"""
# Check input args.
file_system_utils.mkdir_recursive_if_necessary(file_name=output_file_name)
model_interpretation.check_component_type(component_type_string)
# Read model and metadata.
print('Reading model from: "{0:s}"...'.format(model_file_name))
model_object = cnn.read_model(model_file_name)
model_metafile_name = '{0:s}/model_metadata.p'.format(
os.path.split(model_file_name)[0])
print(
'Reading model metadata from: "{0:s}"...'.format(model_metafile_name))
model_metadata_dict = cnn.read_model_metadata(model_metafile_name)
training_option_dict = model_metadata_dict[cnn.TRAINING_OPTION_DICT_KEY]
training_option_dict[trainval_io.REFLECTIVITY_MASK_KEY] = None
output_dir_name, pathless_output_file_name = os.path.split(
output_file_name)
extensionless_output_file_name, output_file_extension = os.path.splitext(
pathless_output_file_name)
if randomize_weights:
conv_dense_layer_names = _find_conv_and_dense_layers(model_object)
conv_dense_layer_names.reverse()
num_sets = len(conv_dense_layer_names)
else:
conv_dense_layer_names = []
num_sets = 1
print(
'Reading storm metadata from: "{0:s}"...'.format(storm_metafile_name))
full_storm_id_strings, storm_times_unix_sec = (
tracking_io.read_ids_and_times(storm_metafile_name))
print(SEPARATOR_STRING)
if 0 < num_examples < len(full_storm_id_strings):
full_storm_id_strings = full_storm_id_strings[:num_examples]
storm_times_unix_sec = storm_times_unix_sec[:num_examples]
example_dict = testing_io.read_predictors_specific_examples(
top_example_dir_name=top_example_dir_name,
desired_full_id_strings=full_storm_id_strings,
desired_times_unix_sec=storm_times_unix_sec,
option_dict=training_option_dict,
layer_operation_dicts=model_metadata_dict[cnn.LAYER_OPERATIONS_KEY])
print(SEPARATOR_STRING)
predictor_matrices = example_dict[testing_io.INPUT_MATRICES_KEY]
sounding_pressure_matrix_pa = example_dict[
testing_io.SOUNDING_PRESSURES_KEY]
denorm_predictor_matrices = trainval_io.separate_shear_and_reflectivity(
list_of_input_matrices=copy.deepcopy(predictor_matrices),
training_option_dict=training_option_dict)
print('Denormalizing model inputs...')
denorm_predictor_matrices = model_interpretation.denormalize_data(
list_of_input_matrices=denorm_predictor_matrices,
model_metadata_dict=model_metadata_dict)
print(SEPARATOR_STRING)
for k in range(num_sets):
if randomize_weights:
if cascading_random:
_reset_weights_in_layer(model_object=model_object,
layer_name=conv_dense_layer_names[k])
this_model_object = model_object
this_output_file_name = (
'{0:s}/{1:s}_cascading-random_{2:s}{3:s}').format(
output_dir_name, extensionless_output_file_name,
conv_dense_layer_names[k].replace('_', '-'),
output_file_extension)
else:
this_model_object = keras.models.Model.from_config(
model_object.get_config())
this_model_object.set_weights(model_object.get_weights())
_reset_weights_in_layer(model_object=this_model_object,
layer_name=conv_dense_layer_names[k])
this_output_file_name = '{0:s}/{1:s}_random_{2:s}{3:s}'.format(
output_dir_name, extensionless_output_file_name,
conv_dense_layer_names[k].replace('_', '-'),
output_file_extension)
else:
this_model_object = model_object
this_output_file_name = output_file_name
# print(K.eval(this_model_object.get_layer(name='dense_3').weights[0]))
if component_type_string == CLASS_COMPONENT_TYPE_STRING:
print('Computing saliency maps for target class {0:d}...'.format(
target_class))
saliency_matrices = (
saliency_maps.get_saliency_maps_for_class_activation(
model_object=this_model_object,
target_class=target_class,
list_of_input_matrices=predictor_matrices))
elif component_type_string == NEURON_COMPONENT_TYPE_STRING:
print(
('Computing saliency maps for neuron {0:s} in layer "{1:s}"...'
).format(str(neuron_indices), layer_name))
saliency_matrices = (
saliency_maps.get_saliency_maps_for_neuron_activation(
model_object=this_model_object,
layer_name=layer_name,
neuron_indices=neuron_indices,
list_of_input_matrices=predictor_matrices,
ideal_activation=ideal_activation))
else:
print((
'Computing saliency maps for channel {0:d} in layer "{1:s}"...'
).format(channel_index, layer_name))
saliency_matrices = (
saliency_maps.get_saliency_maps_for_channel_activation(
model_object=this_model_object,
layer_name=layer_name,
channel_index=channel_index,
list_of_input_matrices=predictor_matrices,
stat_function_for_neuron_activations=K.max,
ideal_activation=ideal_activation))
saliency_matrices = trainval_io.separate_shear_and_reflectivity(
list_of_input_matrices=saliency_matrices,
training_option_dict=training_option_dict)
print('Writing saliency maps to file: "{0:s}"...'.format(
this_output_file_name))
saliency_metadata_dict = saliency_maps.check_metadata(
component_type_string=component_type_string,
target_class=target_class,
layer_name=layer_name,
ideal_activation=ideal_activation,
neuron_indices=neuron_indices,
channel_index=channel_index)
saliency_maps.write_standard_file(
pickle_file_name=this_output_file_name,
denorm_predictor_matrices=denorm_predictor_matrices,
saliency_matrices=saliency_matrices,
full_storm_id_strings=full_storm_id_strings,
storm_times_unix_sec=storm_times_unix_sec,
model_file_name=model_file_name,
metadata_dict=saliency_metadata_dict,
sounding_pressure_matrix_pa=sounding_pressure_matrix_pa)
def _run(model_file_name, top_example_dir_name, storm_metafile_name,
output_dir_name):
"""Uses trained CNN to make predictions for specific examples.
This is effectively the main method.
:param model_file_name: See documentation at top of file.
:param top_example_dir_name: Same.
:param storm_metafile_name: Same.
:param output_dir_name: Same.
:raises: ValueError: if the model does multi-class classification.
"""
print('Reading CNN from: "{0:s}"...'.format(model_file_name))
model_object = cnn.read_model(model_file_name)
num_output_neurons = (
model_object.layers[-1].output.get_shape().as_list()[-1]
)
if num_output_neurons > 2:
error_string = (
'The model has {0:d} output neurons, which suggests {0:d}-class '
'classification. This script handles only binary classification.'
).format(num_output_neurons)
raise ValueError(error_string)
soundings_only = False
if isinstance(model_object.input, list):
list_of_input_tensors = model_object.input
else:
list_of_input_tensors = [model_object.input]
if len(list_of_input_tensors) == 1:
these_spatial_dim = numpy.array(
list_of_input_tensors[0].get_shape().as_list()[1:-1], dtype=int
)
soundings_only = len(these_spatial_dim) == 1
cnn_metafile_name = cnn.find_metafile(
model_file_name=model_file_name, raise_error_if_missing=True
)
print('Reading CNN metadata from: "{0:s}"...'.format(cnn_metafile_name))
cnn_metadata_dict = cnn.read_model_metadata(cnn_metafile_name)
print('Reading storm metadata from: "{0:s}"...'.format(storm_metafile_name))
desired_full_id_strings, desired_times_unix_sec = (
tracking_io.read_ids_and_times(storm_metafile_name)
)
unique_spc_date_strings = list(set([
time_conversion.time_to_spc_date_string(t)
for t in desired_times_unix_sec
]))
example_file_names = [
input_examples.find_example_file(
top_directory_name=top_example_dir_name, shuffled=False,
spc_date_string=d, raise_error_if_missing=True
) for d in unique_spc_date_strings
]
first_spc_date_string = time_conversion.time_to_spc_date_string(
numpy.min(desired_times_unix_sec)
)
last_spc_date_string = time_conversion.time_to_spc_date_string(
numpy.max(desired_times_unix_sec)
)
training_option_dict = cnn_metadata_dict[cnn.TRAINING_OPTION_DICT_KEY]
training_option_dict[trainval_io.EXAMPLE_FILES_KEY] = example_file_names
training_option_dict[trainval_io.FIRST_STORM_TIME_KEY] = (
time_conversion.get_start_of_spc_date(first_spc_date_string)
)
training_option_dict[trainval_io.LAST_STORM_TIME_KEY] = (
time_conversion.get_end_of_spc_date(last_spc_date_string)
)
training_option_dict[trainval_io.NUM_EXAMPLES_PER_BATCH_KEY] = (
NUM_EXAMPLES_PER_BATCH
)
if soundings_only:
generator_object = testing_io.sounding_generator(
option_dict=training_option_dict,
desired_full_id_strings=desired_full_id_strings,
desired_times_unix_sec=desired_times_unix_sec)
elif cnn_metadata_dict[cnn.LAYER_OPERATIONS_KEY] is not None:
generator_object = testing_io.gridrad_generator_2d_reduced(
option_dict=training_option_dict,
desired_full_id_strings=desired_full_id_strings,
desired_times_unix_sec=desired_times_unix_sec,
list_of_operation_dicts=cnn_metadata_dict[
cnn.LAYER_OPERATIONS_KEY]
)
elif cnn_metadata_dict[cnn.CONV_2D3D_KEY]:
generator_object = testing_io.myrorss_generator_2d3d(
option_dict=training_option_dict,
desired_full_id_strings=desired_full_id_strings,
desired_times_unix_sec=desired_times_unix_sec)
else:
generator_object = testing_io.generator_2d_or_3d(
option_dict=training_option_dict,
desired_full_id_strings=desired_full_id_strings,
desired_times_unix_sec=desired_times_unix_sec)
include_soundings = (
training_option_dict[trainval_io.SOUNDING_FIELDS_KEY] is not None
)
full_storm_id_strings = []
storm_times_unix_sec = numpy.array([], dtype=int)
observed_labels = numpy.array([], dtype=int)
class_probability_matrix = None
while True:
try:
this_storm_object_dict = next(generator_object)
print(SEPARATOR_STRING)
except StopIteration:
break
full_storm_id_strings += this_storm_object_dict[testing_io.FULL_IDS_KEY]
storm_times_unix_sec = numpy.concatenate((
storm_times_unix_sec,
this_storm_object_dict[testing_io.STORM_TIMES_KEY]
))
observed_labels = numpy.concatenate((
observed_labels, this_storm_object_dict[testing_io.TARGET_ARRAY_KEY]
))
if soundings_only:
these_predictor_matrices = [
this_storm_object_dict[testing_io.SOUNDING_MATRIX_KEY]
]
else:
these_predictor_matrices = this_storm_object_dict[
testing_io.INPUT_MATRICES_KEY]
if include_soundings:
this_sounding_matrix = these_predictor_matrices[-1]
else:
this_sounding_matrix = None
if soundings_only:
this_probability_matrix = cnn.apply_cnn_soundings_only(
model_object=model_object, sounding_matrix=this_sounding_matrix,
verbose=True)
elif cnn_metadata_dict[cnn.CONV_2D3D_KEY]:
if training_option_dict[trainval_io.UPSAMPLE_REFLECTIVITY_KEY]:
this_probability_matrix = cnn.apply_2d_or_3d_cnn(
model_object=model_object,
radar_image_matrix=these_predictor_matrices[0],
sounding_matrix=this_sounding_matrix, verbose=True)
else:
this_probability_matrix = cnn.apply_2d3d_cnn(
model_object=model_object,
reflectivity_matrix_dbz=these_predictor_matrices[0],
azimuthal_shear_matrix_s01=these_predictor_matrices[1],
sounding_matrix=this_sounding_matrix, verbose=True)
else:
this_probability_matrix = cnn.apply_2d_or_3d_cnn(
model_object=model_object,
radar_image_matrix=these_predictor_matrices[0],
sounding_matrix=this_sounding_matrix, verbose=True)
print(SEPARATOR_STRING)
if class_probability_matrix is None:
class_probability_matrix = this_probability_matrix + 0.
else:
class_probability_matrix = numpy.concatenate(
(class_probability_matrix, this_probability_matrix), axis=0
)
output_file_name = prediction_io.find_ungridded_file(
directory_name=output_dir_name, raise_error_if_missing=False)
print('Writing results to: "{0:s}"...'.format(output_file_name))
prediction_io.write_ungridded_predictions(
netcdf_file_name=output_file_name,
class_probability_matrix=class_probability_matrix,
observed_labels=observed_labels, storm_ids=full_storm_id_strings,
storm_times_unix_sec=storm_times_unix_sec,
target_name=training_option_dict[trainval_io.TARGET_NAME_KEY],
model_file_name=model_file_name
)
def _run(storm_metafile_name, top_tracking_dir_name, latitude_buffer_deg,
longitude_buffer_deg, rap_directory_name, ruc_directory_name,
lead_time_seconds, lag_time_seconds, field_name_grib1,
output_dir_name):
"""Plots RAP/RUC field centered on each example (storm object).
This is effectively the main method.
:param storm_metafile_name: See documentation at top of file.
:param top_tracking_dir_name: Same.
:param latitude_buffer_deg: Same.
:param longitude_buffer_deg: Same.
:param rap_directory_name: Same.
:param ruc_directory_name: Same.
:param lead_time_seconds: Same.
:param lag_time_seconds: Same.
:param field_name_grib1: Same.
:param output_dir_name: Same.
"""
file_system_utils.mkdir_recursive_if_necessary(
directory_name=output_dir_name
)
error_checking.assert_is_geq(latitude_buffer_deg, 1.)
error_checking.assert_is_geq(longitude_buffer_deg, 1.)
error_checking.assert_is_greater(lead_time_seconds, 0)
error_checking.assert_is_greater(lag_time_seconds, 0)
print('Reading metadata from: "{0:s}"...'.format(storm_metafile_name))
full_storm_id_strings, storm_times_unix_sec = (
tracking_io.read_ids_and_times(storm_metafile_name)
)
init_times_unix_sec = (
storm_times_unix_sec + lead_time_seconds - lag_time_seconds
)
init_times_unix_sec = number_rounding.floor_to_nearest(
init_times_unix_sec, INIT_TIME_INTERVAL_SEC
)
init_times_unix_sec = init_times_unix_sec.astype(int)
num_examples = len(full_storm_id_strings)
rap_file_names = [None] * num_examples
ruc_file_names = [None] * num_examples
for i in range(num_examples):
if init_times_unix_sec[i] >= FIRST_RAP_TIME_UNIX_SEC:
rap_file_names[i] = nwp_model_io.find_rap_file_any_grid(
top_directory_name=rap_directory_name,
init_time_unix_sec=init_times_unix_sec[i],
lead_time_hours=0, raise_error_if_missing=True
)
continue
ruc_file_names[i] = nwp_model_io.find_ruc_file_any_grid(
top_directory_name=ruc_directory_name,
init_time_unix_sec=init_times_unix_sec[i],
lead_time_hours=0, raise_error_if_missing=True
)
for i in range(num_examples):
_plot_rapruc_one_example(
full_storm_id_string=full_storm_id_strings[i],
storm_time_unix_sec=storm_times_unix_sec[i],
top_tracking_dir_name=top_tracking_dir_name,
latitude_buffer_deg=latitude_buffer_deg,
longitude_buffer_deg=longitude_buffer_deg,
lead_time_seconds=lead_time_seconds,
field_name_grib1=field_name_grib1, output_dir_name=output_dir_name,
rap_file_name=rap_file_names[i], ruc_file_name=ruc_file_names[i]
)
def _run(model_file_name, top_example_dir_name, storm_metafile_name,
num_examples, do_backwards_test, separate_radar_heights,
num_bootstrap_reps, output_file_name):
"""Runs permutation test with specific examples (storm objects).
This is effectively the main method.
:param model_file_name: See documentation at top of file.
:param top_example_dir_name: Same.
:param storm_metafile_name: Same.
:param num_examples: Same.
:param do_backwards_test: Same.
:param separate_radar_heights: Same.
:param num_bootstrap_reps: Same.
:param output_file_name: Same.
"""
print('Reading model from: "{0:s}"...'.format(model_file_name))
model_object = cnn.read_model(model_file_name)
metafile_name = cnn.find_metafile(model_file_name=model_file_name)
print('Reading metadata from: "{0:s}"...'.format(metafile_name))
cnn_metadata_dict = cnn.read_model_metadata(metafile_name)
training_option_dict = cnn_metadata_dict[cnn.TRAINING_OPTION_DICT_KEY]
print(
'Reading storm metadata from: "{0:s}"...'.format(storm_metafile_name))
full_storm_id_strings, storm_times_unix_sec = (
tracking_io.read_ids_and_times(storm_metafile_name))
print(SEPARATOR_STRING)
if 0 < num_examples < len(full_storm_id_strings):
numpy.random.seed(RANDOM_SEED)
good_indices = numpy.random.permutation(len(full_storm_id_strings))
good_indices = good_indices[:num_examples]
full_storm_id_strings = [
full_storm_id_strings[k] for k in good_indices
]
storm_times_unix_sec = storm_times_unix_sec[good_indices]
example_dict = testing_io.read_predictors_specific_examples(
top_example_dir_name=top_example_dir_name,
desired_full_id_strings=full_storm_id_strings,
desired_times_unix_sec=storm_times_unix_sec,
option_dict=training_option_dict,
layer_operation_dicts=cnn_metadata_dict[cnn.LAYER_OPERATIONS_KEY])
print(SEPARATOR_STRING)
predictor_matrices = example_dict[testing_io.INPUT_MATRICES_KEY]
target_values = example_dict[testing_io.TARGET_ARRAY_KEY]
correlation_matrix, predictor_names = correlation.get_pearson_correlations(
predictor_matrices=predictor_matrices,
cnn_metadata_dict=cnn_metadata_dict,
separate_radar_heights=separate_radar_heights)
print(SEPARATOR_STRING)
num_predictors = len(predictor_names)
for i in range(num_predictors):
for j in range(i, num_predictors):
print(('Pearson correlation between "{0:s}" and "{1:s}" = {2:.3f}'
).format(predictor_names[i], predictor_names[j],
correlation_matrix[i, j]))
print(SEPARATOR_STRING)
if do_backwards_test:
result_dict = permutation.run_backwards_test(
model_object=model_object,
predictor_matrices=predictor_matrices,
target_values=target_values,
cnn_metadata_dict=cnn_metadata_dict,
cost_function=permutation_utils.negative_auc_function,
separate_radar_heights=separate_radar_heights,
num_bootstrap_reps=num_bootstrap_reps)
else:
result_dict = permutation.run_forward_test(
model_object=model_object,
predictor_matrices=predictor_matrices,
target_values=target_values,
cnn_metadata_dict=cnn_metadata_dict,
cost_function=permutation_utils.negative_auc_function,
separate_radar_heights=separate_radar_heights,
num_bootstrap_reps=num_bootstrap_reps)
print(SEPARATOR_STRING)
result_dict[permutation_utils.MODEL_FILE_KEY] = model_file_name
result_dict[permutation_utils.TARGET_VALUES_KEY] = target_values
result_dict[permutation_utils.FULL_IDS_KEY] = full_storm_id_strings
result_dict[permutation_utils.STORM_TIMES_KEY] = storm_times_unix_sec
print('Writing results to: "{0:s}"...'.format(output_file_name))
permutation_utils.write_results(result_dict=result_dict,
pickle_file_name=output_file_name)
def _run(activation_file_name, storm_metafile_name, num_examples,
top_example_dir_name, num_radar_rows, num_radar_columns,
allow_whitespace, colour_bar_length, output_dir_name):
"""Plots one or more examples (storm objects) for human input.
This is effectively the main method.
:param activation_file_name: See documentation at top of file.
:param storm_metafile_name: Same.
:param num_examples: Same.
:param top_example_dir_name: Same.
:param num_radar_rows: Same.
:param num_radar_columns: Same.
:param allow_whitespace: Same.
:param colour_bar_length: Same.
:param output_dir_name: Same.
"""
if num_radar_rows <= 0:
num_radar_rows = None
if num_radar_columns <= 0:
num_radar_columns = None
if activation_file_name in ['', 'None']:
activation_file_name = None
if activation_file_name is None:
print('Reading data from: "{0:s}"...'.format(storm_metafile_name))
full_storm_id_strings, storm_times_unix_sec = (
tracking_io.read_ids_and_times(storm_metafile_name))
training_option_dict = dict()
training_option_dict[trainval_io.SOUNDING_FIELDS_KEY] = None
training_option_dict[trainval_io.SOUNDING_HEIGHTS_KEY] = None
training_option_dict[trainval_io.NUM_ROWS_KEY] = num_radar_rows
training_option_dict[trainval_io.NUM_COLUMNS_KEY] = num_radar_columns
training_option_dict[trainval_io.NORMALIZATION_TYPE_KEY] = None
training_option_dict[trainval_io.TARGET_NAME_KEY] = DUMMY_TARGET_NAME
training_option_dict[trainval_io.BINARIZE_TARGET_KEY] = False
training_option_dict[trainval_io.SAMPLING_FRACTIONS_KEY] = None
training_option_dict[trainval_io.REFLECTIVITY_MASK_KEY] = None
model_metadata_dict = {cnn.LAYER_OPERATIONS_KEY: None}
else:
print('Reading data from: "{0:s}"...'.format(activation_file_name))
activation_matrix, activation_metadata_dict = (
model_activation.read_file(activation_file_name))
num_model_components = activation_matrix.shape[1]
if num_model_components > 1:
error_string = (
'The file should contain activations for only one model '
'component, not {0:d}.').format(num_model_components)
raise TypeError(error_string)
full_storm_id_strings = activation_metadata_dict[
model_activation.FULL_IDS_KEY]
storm_times_unix_sec = activation_metadata_dict[
model_activation.STORM_TIMES_KEY]
model_file_name = activation_metadata_dict[
model_activation.MODEL_FILE_NAME_KEY]
model_metafile_name = '{0:s}/model_metadata.p'.format(
os.path.split(model_file_name)[0])
print('Reading metadata from: "{0:s}"...'.format(model_metafile_name))
model_metadata_dict = cnn.read_model_metadata(model_metafile_name)
training_option_dict = model_metadata_dict[
cnn.TRAINING_OPTION_DICT_KEY]
training_option_dict[trainval_io.NORMALIZATION_TYPE_KEY] = None
training_option_dict[trainval_io.SAMPLING_FRACTIONS_KEY] = None
training_option_dict[trainval_io.REFLECTIVITY_MASK_KEY] = None
training_option_dict[trainval_io.RADAR_FIELDS_KEY] = SHEAR_FIELD_NAMES
training_option_dict[trainval_io.RADAR_HEIGHTS_KEY] = REFL_HEIGHTS_M_AGL
training_option_dict[trainval_io.UPSAMPLE_REFLECTIVITY_KEY] = False
model_metadata_dict[cnn.TRAINING_OPTION_DICT_KEY] = training_option_dict
if 0 < num_examples < len(full_storm_id_strings):
full_storm_id_strings = full_storm_id_strings[:num_examples]
storm_times_unix_sec = storm_times_unix_sec[:num_examples]
print(SEPARATOR_STRING)
example_dict = testing_io.read_predictors_specific_examples(
top_example_dir_name=top_example_dir_name,
desired_full_id_strings=full_storm_id_strings,
desired_times_unix_sec=storm_times_unix_sec,
option_dict=model_metadata_dict[cnn.TRAINING_OPTION_DICT_KEY],
layer_operation_dicts=model_metadata_dict[cnn.LAYER_OPERATIONS_KEY])
print(SEPARATOR_STRING)
predictor_matrices = example_dict[testing_io.INPUT_MATRICES_KEY]
# TODO(thunderhoser): The rest of this code is very HACKY.
predictor_matrices[0] = trainval_io.upsample_reflectivity(
predictor_matrices[0][..., 0])
predictor_matrices[0] = numpy.expand_dims(predictor_matrices[0], axis=-1)
example_dict = {
input_examples.RADAR_FIELDS_KEY: SHEAR_FIELD_NAMES,
input_examples.REFL_IMAGE_MATRIX_KEY: predictor_matrices[0],
input_examples.AZ_SHEAR_IMAGE_MATRIX_KEY: predictor_matrices[1],
input_examples.RADAR_HEIGHTS_KEY: REFL_HEIGHTS_M_AGL
}
example_dict = input_examples.reduce_examples_3d_to_2d(
example_dict=example_dict,
list_of_operation_dicts=[REFL_LAYER_OPERATION_DICT])
predictor_matrices = [example_dict[input_examples.RADAR_IMAGE_MATRIX_KEY]]
layer_operation_dicts = [{
input_examples.RADAR_FIELD_KEY: f,
input_examples.MIN_HEIGHT_KEY: h1,
input_examples.MAX_HEIGHT_KEY: h2,
input_examples.OPERATION_NAME_KEY: op
} for f, h1, h2, op in zip(
example_dict[input_examples.RADAR_FIELDS_KEY], example_dict[
input_examples.MIN_RADAR_HEIGHTS_KEY], example_dict[
input_examples.MAX_RADAR_HEIGHTS_KEY], example_dict[
input_examples.RADAR_LAYER_OPERATION_NAMES_KEY])]
model_metadata_dict[cnn.LAYER_OPERATIONS_KEY] = layer_operation_dicts
figure_file_names = plot_examples.plot_examples(
list_of_predictor_matrices=predictor_matrices,
model_metadata_dict=model_metadata_dict,
pmm_flag=False,
output_dir_name=output_dir_name,
plot_soundings=False,
allow_whitespace=allow_whitespace,
plot_panel_names=False,
add_titles=False,
label_colour_bars=True,
colour_bar_length=colour_bar_length,
colour_bar_font_size=COLOUR_BAR_FONT_SIZE,
figure_resolution_dpi=FIGURE_RESOLUTION_DPI,
refl_opacity=REFL_OPACITY,
plot_grid_lines=False,
full_storm_id_strings=full_storm_id_strings,
storm_times_unix_sec=storm_times_unix_sec)
for this_file_name in figure_file_names:
print('Resizing image to {0:d} pixels: "{1:s}"...'.format(
FIGURE_SIZE_PIXELS, this_file_name))
imagemagick_utils.resize_image(input_file_name=this_file_name,
output_file_name=this_file_name,
output_size_pixels=FIGURE_SIZE_PIXELS)
def _run(model_file_name, top_example_dir_name, storm_metafile_name,
num_examples, output_file_name):
"""Creates dummy saliency map for each storm object.
This is effectively the main method.
:param model_file_name: See documentation at top of file.
:param top_example_dir_name: Same.
:param storm_metafile_name: Same.
:param num_examples: Same.
:param output_file_name: Same.
"""
file_system_utils.mkdir_recursive_if_necessary(file_name=output_file_name)
model_metafile_name = '{0:s}/model_metadata.p'.format(
os.path.split(model_file_name)[0])
print(
'Reading model metadata from: "{0:s}"...'.format(model_metafile_name))
model_metadata_dict = cnn.read_model_metadata(model_metafile_name)
training_option_dict = model_metadata_dict[cnn.TRAINING_OPTION_DICT_KEY]
training_option_dict[trainval_io.REFLECTIVITY_MASK_KEY] = None
print(
'Reading storm metadata from: "{0:s}"...'.format(storm_metafile_name))
full_storm_id_strings, storm_times_unix_sec = (
tracking_io.read_ids_and_times(storm_metafile_name))
print(SEPARATOR_STRING)
if 0 < num_examples < len(full_storm_id_strings):
full_storm_id_strings = full_storm_id_strings[:num_examples]
storm_times_unix_sec = storm_times_unix_sec[:num_examples]
example_dict = testing_io.read_predictors_specific_examples(
top_example_dir_name=top_example_dir_name,
desired_full_id_strings=full_storm_id_strings,
desired_times_unix_sec=storm_times_unix_sec,
option_dict=training_option_dict,
layer_operation_dicts=model_metadata_dict[cnn.LAYER_OPERATIONS_KEY])
print(SEPARATOR_STRING)
predictor_matrices = example_dict[testing_io.INPUT_MATRICES_KEY]
sounding_pressure_matrix_pa = (
example_dict[testing_io.SOUNDING_PRESSURES_KEY])
radar_matrix = predictor_matrices[0]
num_examples = radar_matrix.shape[0]
num_channels = radar_matrix.shape[-1]
num_spatial_dim = len(radar_matrix.shape) - 2
if num_spatial_dim == 2:
kernel_matrix = numpy.expand_dims(EDGE_DETECTOR_MATRIX_2D, axis=-1)
else:
kernel_matrix = numpy.expand_dims(EDGE_DETECTOR_MATRIX_3D, axis=-1)
kernel_matrix = numpy.repeat(kernel_matrix, num_channels, axis=-1)
kernel_matrix = numpy.expand_dims(kernel_matrix, axis=-1)
kernel_matrix = numpy.repeat(kernel_matrix, num_channels, axis=-1)
radar_saliency_matrix = numpy.full(radar_matrix.shape, numpy.nan)
for i in range(num_examples):
if numpy.mod(i, 10) == 0:
print((
'Have created dummy saliency map for {0:d} of {1:d} examples...'
).format(i, num_examples))
if num_spatial_dim == 2:
this_saliency_matrix = standalone_utils.do_2d_convolution(
feature_matrix=radar_matrix[i, ...],
kernel_matrix=kernel_matrix,
pad_edges=True,
stride_length_px=1)
else:
this_saliency_matrix = standalone_utils.do_3d_convolution(
feature_matrix=radar_matrix[i, ...],
kernel_matrix=kernel_matrix,
pad_edges=True,
stride_length_px=1)
radar_saliency_matrix[i, ...] = this_saliency_matrix[0, ...]
print('Have created dummy saliency map for all {0:d} examples!'.format(
num_examples))
print(SEPARATOR_STRING)
saliency_matrices = [
radar_saliency_matrix if k == 0 else predictor_matrices[k]
for k in range(len(predictor_matrices))
]
saliency_matrices = trainval_io.separate_shear_and_reflectivity(
list_of_input_matrices=saliency_matrices,
training_option_dict=training_option_dict)
denorm_predictor_matrices = trainval_io.separate_shear_and_reflectivity(
list_of_input_matrices=copy.deepcopy(predictor_matrices),
training_option_dict=training_option_dict)
print('Denormalizing model inputs...')
denorm_predictor_matrices = model_interpretation.denormalize_data(
list_of_input_matrices=denorm_predictor_matrices,
model_metadata_dict=model_metadata_dict)
print('Writing saliency maps to file: "{0:s}"...'.format(output_file_name))
saliency_metadata_dict = saliency_maps.check_metadata(
component_type_string=model_interpretation.CLASS_COMPONENT_TYPE_STRING,
target_class=1)
saliency_maps.write_standard_file(
pickle_file_name=output_file_name,
denorm_predictor_matrices=denorm_predictor_matrices,
saliency_matrices=saliency_matrices,
full_storm_id_strings=full_storm_id_strings,
storm_times_unix_sec=storm_times_unix_sec,
model_file_name=model_file_name,
metadata_dict=saliency_metadata_dict,
sounding_pressure_matrix_pa=sounding_pressure_matrix_pa)
def _run(model_file_name, init_function_name, storm_metafile_name,
num_examples, top_example_dir_name, component_type_string,
target_class, layer_name, neuron_indices, channel_index,
num_iterations, ideal_activation, learning_rate, output_file_name):
"""Runs backwards optimization on a trained CNN.
This is effectively the main method.
:param model_file_name: See documentation at top of file.
:param init_function_name: Same.
:param storm_metafile_name: Same.
:param num_examples: Same.
:param top_example_dir_name: Same.
:param component_type_string: Same.
:param target_class: Same.
:param layer_name: Same.
:param neuron_indices: Same.
:param channel_index: Same.
:param num_iterations: Same.
:param ideal_activation: Same.
:param learning_rate: Same.
:param output_file_name: Same.
"""
model_interpretation.check_component_type(component_type_string)
if ideal_activation <= 0:
ideal_activation = None
if init_function_name in ['', 'None']:
init_function_name = None
model_metafile_name = '{0:s}/model_metadata.p'.format(
os.path.split(model_file_name)[0])
print 'Reading model metadata from: "{0:s}"...'.format(model_metafile_name)
model_metadata_dict = cnn.read_model_metadata(model_metafile_name)
if init_function_name is None:
print 'Reading storm metadata from: "{0:s}"...'.format(
storm_metafile_name)
storm_ids, storm_times_unix_sec = tracking_io.read_ids_and_times(
storm_metafile_name)
if 0 < num_examples < len(storm_ids):
storm_ids = storm_ids[:num_examples]
storm_times_unix_sec = storm_times_unix_sec[:num_examples]
list_of_init_matrices = testing_io.read_specific_examples(
desired_storm_ids=storm_ids,
desired_times_unix_sec=storm_times_unix_sec,
option_dict=model_metadata_dict[cnn.TRAINING_OPTION_DICT_KEY],
top_example_dir_name=top_example_dir_name,
list_of_layer_operation_dicts=model_metadata_dict[
cnn.LAYER_OPERATIONS_KEY])[0]
num_examples = list_of_init_matrices[0].shape[0]
print SEPARATOR_STRING
else:
storm_ids = None
storm_times_unix_sec = None
num_examples = 1
init_function = _create_initializer(
init_function_name=init_function_name,
model_metadata_dict=model_metadata_dict)
print 'Reading model from: "{0:s}"...'.format(model_file_name)
model_object = cnn.read_model(model_file_name)
list_of_optimized_matrices = None
for i in range(num_examples):
if init_function_name is None:
this_init_arg = [a[[i], ...] for a in list_of_init_matrices]
else:
this_init_arg = init_function
if component_type_string == CLASS_COMPONENT_TYPE_STRING:
print(
'\nOptimizing {0:d}th of {1:d} images for target class {2:d}...'
).format(i + 1, num_examples, target_class)
these_optimized_matrices = backwards_opt.optimize_input_for_class(
model_object=model_object,
target_class=target_class,
init_function_or_matrices=this_init_arg,
num_iterations=num_iterations,
learning_rate=learning_rate)
elif component_type_string == NEURON_COMPONENT_TYPE_STRING:
print(
'\nOptimizing {0:d}th of {1:d} images for neuron {2:s} in layer'
' "{3:s}"...').format(i + 1, num_examples, str(neuron_indices),
layer_name)
these_optimized_matrices = backwards_opt.optimize_input_for_neuron(
model_object=model_object,
layer_name=layer_name,
neuron_indices=neuron_indices,
init_function_or_matrices=this_init_arg,
num_iterations=num_iterations,
learning_rate=learning_rate,
ideal_activation=ideal_activation)
else:
print(
'\nOptimizing {0:d}th of {1:d} images for channel {2:d} in '
'layer "{3:s}"...').format(i + 1, num_examples, channel_index,
layer_name)
these_optimized_matrices = backwards_opt.optimize_input_for_channel(
model_object=model_object,
layer_name=layer_name,
channel_index=channel_index,
init_function_or_matrices=this_init_arg,
stat_function_for_neuron_activations=K.max,
num_iterations=num_iterations,
learning_rate=learning_rate,
ideal_activation=ideal_activation)
if list_of_optimized_matrices is None:
num_matrices = len(these_optimized_matrices)
list_of_optimized_matrices = [None] * num_matrices
for k in range(len(list_of_optimized_matrices)):
if list_of_optimized_matrices[k] is None:
list_of_optimized_matrices[
k] = these_optimized_matrices[k] + 0.
else:
list_of_optimized_matrices[k] = numpy.concatenate(
(list_of_optimized_matrices[k],
these_optimized_matrices[k]),
axis=0)
print SEPARATOR_STRING
print 'Denormalizing optimized examples...'
list_of_optimized_matrices = model_interpretation.denormalize_data(
list_of_input_matrices=list_of_optimized_matrices,
model_metadata_dict=model_metadata_dict)
if init_function_name is None:
print 'Denormalizing input examples...'
list_of_init_matrices = model_interpretation.denormalize_data(
list_of_input_matrices=list_of_init_matrices,
model_metadata_dict=model_metadata_dict)
this_init_arg = list_of_init_matrices
else:
this_init_arg = init_function_name + ''
print 'Writing results to: "{0:s}"...'.format(output_file_name)
backwards_opt.write_standard_file(
pickle_file_name=output_file_name,
list_of_optimized_matrices=list_of_optimized_matrices,
model_file_name=model_file_name,
init_function_name_or_matrices=this_init_arg,
num_iterations=num_iterations,
learning_rate=learning_rate,
component_type_string=component_type_string,
target_class=target_class,
layer_name=layer_name,
neuron_indices=neuron_indices,
channel_index=channel_index,
ideal_activation=ideal_activation,
storm_ids=storm_ids,
storm_times_unix_sec=storm_times_unix_sec)
def _run(cnn_file_name, upconvnet_file_name, top_example_dir_name,
baseline_storm_metafile_name, trial_storm_metafile_name,
num_baseline_examples, num_trial_examples, num_novel_examples,
cnn_feature_layer_name, percent_variance_to_keep, output_file_name):
"""Runs novelty detection.
This is effectively the main method.
:param cnn_file_name: See documentation at top of file.
:param upconvnet_file_name: Same.
:param top_example_dir_name: Same.
:param baseline_storm_metafile_name: Same.
:param trial_storm_metafile_name: Same.
:param num_baseline_examples: Same.
:param num_trial_examples: Same.
:param num_novel_examples: Same.
:param cnn_feature_layer_name: Same.
:param percent_variance_to_keep: Same.
:param output_file_name: Same.
:raises: ValueError: if dimensions of first CNN input matrix != dimensions
of upconvnet output.
"""
print('Reading trained CNN from: "{0:s}"...'.format(cnn_file_name))
cnn_model_object = cnn.read_model(cnn_file_name)
print('Reading trained upconvnet from: "{0:s}"...'.format(
upconvnet_file_name))
upconvnet_model_object = cnn.read_model(upconvnet_file_name)
_check_dimensions(cnn_model_object=cnn_model_object,
upconvnet_model_object=upconvnet_model_object)
print('Reading metadata for baseline examples from: "{0:s}"...'.format(
baseline_storm_metafile_name))
baseline_full_id_strings, baseline_times_unix_sec = (
tracking_io.read_ids_and_times(baseline_storm_metafile_name))
print('Reading metadata for trial examples from: "{0:s}"...'.format(
trial_storm_metafile_name))
trial_full_id_strings, trial_times_unix_sec = (
tracking_io.read_ids_and_times(trial_storm_metafile_name))
this_dict = _filter_examples(
trial_full_id_strings=trial_full_id_strings,
trial_times_unix_sec=trial_times_unix_sec,
num_trial_examples=num_trial_examples,
baseline_full_id_strings=baseline_full_id_strings,
baseline_times_unix_sec=baseline_times_unix_sec,
num_baseline_examples=num_baseline_examples,
num_novel_examples=num_novel_examples)
trial_full_id_strings = this_dict[TRIAL_STORM_IDS_KEY]
trial_times_unix_sec = this_dict[TRIAL_STORM_TIMES_KEY]
baseline_full_id_strings = this_dict[BASELINE_STORM_IDS_KEY]
baseline_times_unix_sec = this_dict[BASELINE_STORM_TIMES_KEY]
num_novel_examples = this_dict[NUM_NOVEL_EXAMPLES_KEY]
cnn_metafile_name = '{0:s}/model_metadata.p'.format(
os.path.split(cnn_file_name)[0])
print('Reading CNN metadata from: "{0:s}"...'.format(cnn_metafile_name))
cnn_metadata_dict = cnn.read_model_metadata(cnn_metafile_name)
print(SEPARATOR_STRING)
baseline_predictor_matrices = testing_io.read_predictors_specific_examples(
top_example_dir_name=top_example_dir_name,
desired_full_id_strings=baseline_full_id_strings,
desired_times_unix_sec=baseline_times_unix_sec,
option_dict=cnn_metadata_dict[cnn.TRAINING_OPTION_DICT_KEY],
layer_operation_dicts=cnn_metadata_dict[cnn.LAYER_OPERATIONS_KEY])[
testing_io.INPUT_MATRICES_KEY]
print(SEPARATOR_STRING)
trial_predictor_matrices = testing_io.read_predictors_specific_examples(
top_example_dir_name=top_example_dir_name,
desired_full_id_strings=trial_full_id_strings,
desired_times_unix_sec=trial_times_unix_sec,
option_dict=cnn_metadata_dict[cnn.TRAINING_OPTION_DICT_KEY],
layer_operation_dicts=cnn_metadata_dict[cnn.LAYER_OPERATIONS_KEY])[
testing_io.INPUT_MATRICES_KEY]
print(SEPARATOR_STRING)
novelty_dict = novelty_detection.do_novelty_detection(
baseline_predictor_matrices=baseline_predictor_matrices,
trial_predictor_matrices=trial_predictor_matrices,
cnn_model_object=cnn_model_object,
cnn_feature_layer_name=cnn_feature_layer_name,
upconvnet_model_object=upconvnet_model_object,
num_novel_examples=num_novel_examples,
multipass=False,
percent_variance_to_keep=percent_variance_to_keep)
print(SEPARATOR_STRING)
print('Denormalizing inputs and outputs of novelty detection...')
cnn_metadata_dict[cnn.TRAINING_OPTION_DICT_KEY][
trainval_io.SOUNDING_FIELDS_KEY] = None
novelty_dict[novelty_detection.BASELINE_MATRIX_KEY] = (
model_interpretation.denormalize_data(
list_of_input_matrices=baseline_predictor_matrices[[0]],
model_metadata_dict=cnn_metadata_dict))
novelty_dict[novelty_detection.TRIAL_MATRIX_KEY] = (
model_interpretation.denormalize_data(
list_of_input_matrices=trial_predictor_matrices[[0]],
model_metadata_dict=cnn_metadata_dict))
novelty_dict[novelty_detection.UPCONV_MATRIX_KEY] = (
model_interpretation.denormalize_data(
list_of_input_matrices=[
novelty_dict[novelty_detection.UPCONV_NORM_MATRIX_KEY]
],
model_metadata_dict=cnn_metadata_dict))[0]
novelty_dict.pop(novelty_detection.UPCONV_NORM_MATRIX_KEY)
novelty_dict[novelty_detection.UPCONV_SVD_MATRIX_KEY] = (
model_interpretation.denormalize_data(
list_of_input_matrices=[
novelty_dict[novelty_detection.UPCONV_NORM_SVD_MATRIX_KEY]
],
model_metadata_dict=cnn_metadata_dict))[0]
novelty_dict.pop(novelty_detection.UPCONV_NORM_SVD_MATRIX_KEY)
novelty_dict = novelty_detection.add_metadata(
novelty_dict=novelty_dict,
baseline_full_id_strings=baseline_full_id_strings,
baseline_times_unix_sec=baseline_times_unix_sec,
trial_full_id_strings=trial_full_id_strings,
trial_times_unix_sec=trial_times_unix_sec,
cnn_file_name=cnn_file_name,
upconvnet_file_name=upconvnet_file_name)
print('Writing results to: "{0:s}"...'.format(output_file_name))
novelty_detection.write_standard_file(novelty_dict=novelty_dict,
pickle_file_name=output_file_name)
def _run(storm_metafile_name, top_tracking_dir_name, lead_time_seconds,
output_file_name):
"""Plots spatial distribution of examples (storm objects) in file.
This is effectively the main method.
:param storm_metafile_name: See documentation at top of file.
:param top_tracking_dir_name: Same.
:param lead_time_seconds: Same.
:param output_file_name: Same.
"""
file_system_utils.mkdir_recursive_if_necessary(file_name=output_file_name)
# Read storm metadata.
print(
'Reading storm metadata from: "{0:s}"...'.format(storm_metafile_name))
orig_full_id_strings, orig_times_unix_sec = (
tracking_io.read_ids_and_times(storm_metafile_name))
orig_primary_id_strings = temporal_tracking.full_to_partial_ids(
orig_full_id_strings)[0]
# Find relevant tracking files.
spc_date_strings = [
time_conversion.time_to_spc_date_string(t) for t in orig_times_unix_sec
]
spc_date_strings += [
time_conversion.time_to_spc_date_string(t + lead_time_seconds)
for t in orig_times_unix_sec
]
spc_date_strings = list(set(spc_date_strings))
tracking_file_names = []
for this_spc_date_string in spc_date_strings:
tracking_file_names += tracking_io.find_files_one_spc_date(
top_tracking_dir_name=top_tracking_dir_name,
tracking_scale_metres2=DUMMY_TRACKING_SCALE_METRES2,
source_name=tracking_utils.SEGMOTION_NAME,
spc_date_string=this_spc_date_string,
raise_error_if_missing=False)[0]
file_times_unix_sec = numpy.array(
[tracking_io.file_name_to_time(f) for f in tracking_file_names],
dtype=int)
num_orig_storm_objects = len(orig_full_id_strings)
num_files = len(file_times_unix_sec)
keep_file_flags = numpy.full(num_files, 0, dtype=bool)
for i in range(num_orig_storm_objects):
these_flags = numpy.logical_and(
file_times_unix_sec >= orig_times_unix_sec[i],
file_times_unix_sec <= orig_times_unix_sec[i] + lead_time_seconds)
keep_file_flags = numpy.logical_or(keep_file_flags, these_flags)
del file_times_unix_sec
keep_file_indices = numpy.where(keep_file_flags)[0]
tracking_file_names = [tracking_file_names[k] for k in keep_file_indices]
# Read relevant tracking files.
num_files = len(tracking_file_names)
storm_object_tables = [None] * num_files
print(SEPARATOR_STRING)
for i in range(num_files):
print('Reading data from: "{0:s}"...'.format(tracking_file_names[i]))
this_table = tracking_io.read_file(tracking_file_names[i])
storm_object_tables[i] = this_table.loc[this_table[
tracking_utils.PRIMARY_ID_COLUMN].isin(
numpy.array(orig_primary_id_strings))]
if i == 0:
continue
storm_object_tables[i] = storm_object_tables[i].align(
storm_object_tables[0], axis=1)[0]
storm_object_table = pandas.concat(storm_object_tables,
axis=0,
ignore_index=True)
print(SEPARATOR_STRING)
# Find relevant storm objects.
orig_object_rows = tracking_utils.find_storm_objects(
all_id_strings=storm_object_table[
tracking_utils.FULL_ID_COLUMN].values.tolist(),
all_times_unix_sec=storm_object_table[
tracking_utils.VALID_TIME_COLUMN].values,
id_strings_to_keep=orig_full_id_strings,
times_to_keep_unix_sec=orig_times_unix_sec)
good_object_rows = numpy.array([], dtype=int)
for i in range(num_orig_storm_objects):
# Non-merging successors only!
first_rows = temporal_tracking.find_successors(
storm_object_table=storm_object_table,
target_row=orig_object_rows[i],
num_seconds_forward=lead_time_seconds,
max_num_sec_id_changes=1,
change_type_string=temporal_tracking.SPLIT_STRING,
return_all_on_path=True)
second_rows = temporal_tracking.find_successors(
storm_object_table=storm_object_table,
target_row=orig_object_rows[i],
num_seconds_forward=lead_time_seconds,
max_num_sec_id_changes=0,
change_type_string=temporal_tracking.MERGER_STRING,
return_all_on_path=True)
first_rows = first_rows.tolist()
second_rows = second_rows.tolist()
these_rows = set(first_rows) & set(second_rows)
these_rows = numpy.array(list(these_rows), dtype=int)
good_object_rows = numpy.concatenate((good_object_rows, these_rows))
good_object_rows = numpy.unique(good_object_rows)
storm_object_table = storm_object_table.iloc[good_object_rows]
times_of_day_sec = numpy.mod(
storm_object_table[tracking_utils.VALID_TIME_COLUMN].values,
NUM_SECONDS_IN_DAY)
storm_object_table = storm_object_table.assign(
**{tracking_utils.VALID_TIME_COLUMN: times_of_day_sec})
min_plot_latitude_deg = -LATLNG_BUFFER_DEG + numpy.min(
storm_object_table[tracking_utils.CENTROID_LATITUDE_COLUMN].values)
max_plot_latitude_deg = LATLNG_BUFFER_DEG + numpy.max(
storm_object_table[tracking_utils.CENTROID_LATITUDE_COLUMN].values)
min_plot_longitude_deg = -LATLNG_BUFFER_DEG + numpy.min(
storm_object_table[tracking_utils.CENTROID_LONGITUDE_COLUMN].values)
max_plot_longitude_deg = LATLNG_BUFFER_DEG + numpy.max(
storm_object_table[tracking_utils.CENTROID_LONGITUDE_COLUMN].values)
_, axes_object, basemap_object = (
plotting_utils.create_equidist_cylindrical_map(
min_latitude_deg=min_plot_latitude_deg,
max_latitude_deg=max_plot_latitude_deg,
min_longitude_deg=min_plot_longitude_deg,
max_longitude_deg=max_plot_longitude_deg,
resolution_string='i'))
plotting_utils.plot_coastlines(basemap_object=basemap_object,
axes_object=axes_object,
line_colour=BORDER_COLOUR,
line_width=BORDER_WIDTH * 2)
plotting_utils.plot_countries(basemap_object=basemap_object,
axes_object=axes_object,
line_colour=BORDER_COLOUR,
line_width=BORDER_WIDTH)
plotting_utils.plot_states_and_provinces(basemap_object=basemap_object,
axes_object=axes_object,
line_colour=BORDER_COLOUR,
line_width=BORDER_WIDTH)
plotting_utils.plot_parallels(basemap_object=basemap_object,
axes_object=axes_object,
num_parallels=NUM_PARALLELS,
line_width=BORDER_WIDTH)
plotting_utils.plot_meridians(basemap_object=basemap_object,
axes_object=axes_object,
num_meridians=NUM_MERIDIANS,
line_width=BORDER_WIDTH)
# colour_bar_object = storm_plotting.plot_storm_tracks(
# storm_object_table=storm_object_table, axes_object=axes_object,
# basemap_object=basemap_object, colour_map_object=COLOUR_MAP_OBJECT,
# colour_min_unix_sec=0, colour_max_unix_sec=NUM_SECONDS_IN_DAY - 1,
# line_width=TRACK_LINE_WIDTH,
# start_marker_type=None, end_marker_type=None
# )
colour_bar_object = storm_plotting.plot_storm_centroids(
storm_object_table=storm_object_table,
axes_object=axes_object,
basemap_object=basemap_object,
colour_map_object=COLOUR_MAP_OBJECT,
colour_min_unix_sec=0,
colour_max_unix_sec=NUM_SECONDS_IN_DAY - 1)
tick_times_unix_sec = numpy.linspace(0,
NUM_SECONDS_IN_DAY,
num=NUM_HOURS_IN_DAY + 1,
dtype=int)
tick_times_unix_sec = tick_times_unix_sec[:-1]
tick_times_unix_sec = tick_times_unix_sec[::2]
tick_time_strings = [
time_conversion.unix_sec_to_string(t, COLOUR_BAR_TIME_FORMAT)
for t in tick_times_unix_sec
]
colour_bar_object.set_ticks(tick_times_unix_sec)
colour_bar_object.set_ticklabels(tick_time_strings)
print('Saving figure to: "{0:s}"...'.format(output_file_name))
pyplot.savefig(output_file_name,
dpi=FIGURE_RESOLUTION_DPI,
pad_inches=0,
bbox_inches='tight')
pyplot.close()
def _run(activation_file_name, storm_metafile_name, num_examples,
allow_whitespace, top_example_dir_name, radar_field_names,
radar_heights_m_agl, plot_soundings, num_radar_rows,
num_radar_columns, output_dir_name):
"""Plots many dataset examples (storm objects).
This is effectively the main method.
:param activation_file_name: See documentation at top of file.
:param storm_metafile_name: Same.
:param num_examples: Same.
:param allow_whitespace: Same.
:param top_example_dir_name: Same.
:param radar_field_names: Same.
:param radar_heights_m_agl: Same.
:param plot_soundings: Same.
:param num_radar_rows: Same.
:param num_radar_columns: Same.
:param output_dir_name: Same.
:raises: TypeError: if activation file contains activations for more than
one model component.
"""
file_system_utils.mkdir_recursive_if_necessary(
directory_name=output_dir_name)
storm_activations = None
if activation_file_name in ['', 'None']:
activation_file_name = None
if activation_file_name is None:
print('Reading data from: "{0:s}"...'.format(storm_metafile_name))
full_storm_id_strings, storm_times_unix_sec = (
tracking_io.read_ids_and_times(storm_metafile_name))
training_option_dict = dict()
training_option_dict[trainval_io.RADAR_FIELDS_KEY] = radar_field_names
training_option_dict[
trainval_io.RADAR_HEIGHTS_KEY] = radar_heights_m_agl
training_option_dict[
trainval_io.SOUNDING_FIELDS_KEY] = SOUNDING_FIELD_NAMES
training_option_dict[
trainval_io.SOUNDING_HEIGHTS_KEY] = SOUNDING_HEIGHTS_M_AGL
training_option_dict[trainval_io.NUM_ROWS_KEY] = num_radar_rows
training_option_dict[trainval_io.NUM_COLUMNS_KEY] = num_radar_columns
training_option_dict[trainval_io.NORMALIZATION_TYPE_KEY] = None
training_option_dict[trainval_io.TARGET_NAME_KEY] = DUMMY_TARGET_NAME
training_option_dict[trainval_io.BINARIZE_TARGET_KEY] = False
training_option_dict[trainval_io.SAMPLING_FRACTIONS_KEY] = None
training_option_dict[trainval_io.REFLECTIVITY_MASK_KEY] = None
model_metadata_dict = {
cnn.TRAINING_OPTION_DICT_KEY: training_option_dict,
cnn.LAYER_OPERATIONS_KEY: None,
}
else:
print('Reading data from: "{0:s}"...'.format(activation_file_name))
activation_matrix, activation_metadata_dict = (
model_activation.read_file(activation_file_name))
num_model_components = activation_matrix.shape[1]
if num_model_components > 1:
error_string = (
'The file should contain activations for only one model '
'component, not {0:d}.').format(num_model_components)
raise TypeError(error_string)
full_storm_id_strings = activation_metadata_dict[
model_activation.FULL_IDS_KEY]
storm_times_unix_sec = activation_metadata_dict[
model_activation.STORM_TIMES_KEY]
storm_activations = activation_matrix[:, 0]
model_file_name = activation_metadata_dict[
model_activation.MODEL_FILE_NAME_KEY]
model_metafile_name = '{0:s}/model_metadata.p'.format(
os.path.split(model_file_name)[0])
print('Reading metadata from: "{0:s}"...'.format(model_metafile_name))
model_metadata_dict = cnn.read_model_metadata(model_metafile_name)
training_option_dict = model_metadata_dict[
cnn.TRAINING_OPTION_DICT_KEY]
training_option_dict[trainval_io.NORMALIZATION_TYPE_KEY] = None
training_option_dict[trainval_io.SAMPLING_FRACTIONS_KEY] = None
training_option_dict[trainval_io.REFLECTIVITY_MASK_KEY] = None
model_metadata_dict[
cnn.TRAINING_OPTION_DICT_KEY] = training_option_dict
model_metadata_dict[cnn.TRAINING_OPTION_DICT_KEY][
trainval_io.UPSAMPLE_REFLECTIVITY_KEY] = False
if 0 < num_examples < len(full_storm_id_strings):
full_storm_id_strings = full_storm_id_strings[:num_examples]
storm_times_unix_sec = storm_times_unix_sec[:num_examples]
if storm_activations is not None:
storm_activations = storm_activations[:num_examples]
print(SEPARATOR_STRING)
list_of_predictor_matrices = testing_io.read_specific_examples(
desired_full_id_strings=full_storm_id_strings,
desired_times_unix_sec=storm_times_unix_sec,
option_dict=model_metadata_dict[cnn.TRAINING_OPTION_DICT_KEY],
top_example_dir_name=top_example_dir_name,
list_of_layer_operation_dicts=model_metadata_dict[
cnn.LAYER_OPERATIONS_KEY])[0]
print(SEPARATOR_STRING)
plot_examples(list_of_predictor_matrices=list_of_predictor_matrices,
model_metadata_dict=model_metadata_dict,
output_dir_name=output_dir_name,
plot_soundings=plot_soundings,
allow_whitespace=allow_whitespace,
pmm_flag=False,
full_storm_id_strings=full_storm_id_strings,
storm_times_unix_sec=storm_times_unix_sec,
storm_activations=storm_activations)
def _run(model_file_name, init_function_name, storm_metafile_name,
num_examples, top_example_dir_name, component_type_string,
target_class, layer_name, neuron_indices, channel_index,
num_iterations, ideal_activation, learning_rate, l2_weight,
radar_constraint_weight, minmax_constraint_weight, output_file_name):
"""Runs backwards optimization on a trained CNN.
This is effectively the main method.
:param model_file_name: See documentation at top of file.
:param init_function_name: Same.
:param storm_metafile_name: Same.
:param num_examples: Same.
:param top_example_dir_name: Same.
:param component_type_string: Same.
:param target_class: Same.
:param layer_name: Same.
:param neuron_indices: Same.
:param channel_index: Same.
:param num_iterations: Same.
:param ideal_activation: Same.
:param learning_rate: Same.
:param l2_weight: Same.
:param radar_constraint_weight: Same.
:param minmax_constraint_weight: Same.
:param output_file_name: Same.
"""
if l2_weight <= 0:
l2_weight = None
if radar_constraint_weight <= 0:
radar_constraint_weight = None
if minmax_constraint_weight <= 0:
minmax_constraint_weight = None
if ideal_activation <= 0:
ideal_activation = None
if init_function_name in ['', 'None']:
init_function_name = None
model_interpretation.check_component_type(component_type_string)
model_metafile_name = '{0:s}/model_metadata.p'.format(
os.path.split(model_file_name)[0])
print(
'Reading model metadata from: "{0:s}"...'.format(model_metafile_name))
model_metadata_dict = cnn.read_model_metadata(model_metafile_name)
input_matrices = None
init_function = None
full_storm_id_strings = None
storm_times_unix_sec = None
sounding_pressure_matrix_pa = None
if init_function_name is None:
print('Reading storm metadata from: "{0:s}"...'.format(
storm_metafile_name))
full_storm_id_strings, storm_times_unix_sec = (
tracking_io.read_ids_and_times(storm_metafile_name))
if 0 < num_examples < len(full_storm_id_strings):
full_storm_id_strings = full_storm_id_strings[:num_examples]
storm_times_unix_sec = storm_times_unix_sec[:num_examples]
example_dict = testing_io.read_predictors_specific_examples(
top_example_dir_name=top_example_dir_name,
desired_full_id_strings=full_storm_id_strings,
desired_times_unix_sec=storm_times_unix_sec,
option_dict=model_metadata_dict[cnn.TRAINING_OPTION_DICT_KEY],
layer_operation_dicts=model_metadata_dict[
cnn.LAYER_OPERATIONS_KEY])
print(SEPARATOR_STRING)
input_matrices = example_dict[testing_io.INPUT_MATRICES_KEY]
sounding_pressure_matrix_pa = example_dict[
testing_io.SOUNDING_PRESSURES_KEY]
num_examples = input_matrices[0].shape[0]
else:
num_examples = 1
init_function = _create_initializer(
init_function_name=init_function_name,
model_metadata_dict=model_metadata_dict)
print('Reading model from: "{0:s}"...'.format(model_file_name))
model_object = cnn.read_model(model_file_name)
output_matrices = None
initial_activations = numpy.full(num_examples, numpy.nan)
final_activations = numpy.full(num_examples, numpy.nan)
for i in range(num_examples):
if init_function_name is None:
this_init_arg = [a[[i], ...] for a in input_matrices]
else:
this_init_arg = init_function
if component_type_string == CLASS_COMPONENT_TYPE_STRING:
print((
'\nOptimizing {0:d}th of {1:d} images for target class {2:d}...'
).format(i + 1, num_examples, target_class))
this_result_dict = backwards_opt.optimize_input_for_class(
model_object=model_object,
target_class=target_class,
init_function_or_matrices=this_init_arg,
num_iterations=num_iterations,
learning_rate=learning_rate,
l2_weight=l2_weight,
radar_constraint_weight=radar_constraint_weight,
minmax_constraint_weight=minmax_constraint_weight,
model_metadata_dict=model_metadata_dict)
elif component_type_string == NEURON_COMPONENT_TYPE_STRING:
print((
'\nOptimizing {0:d}th of {1:d} images for neuron {2:s} in layer'
' "{3:s}"...').format(i + 1, num_examples, str(neuron_indices),
layer_name))
this_result_dict = backwards_opt.optimize_input_for_neuron(
model_object=model_object,
layer_name=layer_name,
neuron_indices=neuron_indices,
init_function_or_matrices=this_init_arg,
num_iterations=num_iterations,
learning_rate=learning_rate,
l2_weight=l2_weight,
ideal_activation=ideal_activation,
radar_constraint_weight=radar_constraint_weight,
minmax_constraint_weight=minmax_constraint_weight,
model_metadata_dict=model_metadata_dict)
else:
print(('\nOptimizing {0:d}th of {1:d} images for channel {2:d} in '
'layer "{3:s}"...').format(i + 1, num_examples,
channel_index, layer_name))
this_result_dict = backwards_opt.optimize_input_for_channel(
model_object=model_object,
layer_name=layer_name,
channel_index=channel_index,
init_function_or_matrices=this_init_arg,
stat_function_for_neuron_activations=K.max,
num_iterations=num_iterations,
learning_rate=learning_rate,
l2_weight=l2_weight,
ideal_activation=ideal_activation,
radar_constraint_weight=radar_constraint_weight,
minmax_constraint_weight=minmax_constraint_weight,
model_metadata_dict=model_metadata_dict)
initial_activations[i] = this_result_dict[
backwards_opt.INITIAL_ACTIVATION_KEY]
final_activations[i] = this_result_dict[
backwards_opt.FINAL_ACTIVATION_KEY]
these_output_matrices = this_result_dict[
backwards_opt.NORM_OUTPUT_MATRICES_KEY]
if output_matrices is None:
output_matrices = [None] * len(these_output_matrices)
for k in range(len(output_matrices)):
if output_matrices[k] is None:
output_matrices[k] = these_output_matrices[k] + 0.
else:
output_matrices[k] = numpy.concatenate(
(output_matrices[k], these_output_matrices[k]), axis=0)
if init_function_name is None:
continue
these_input_matrices = this_result_dict[
backwards_opt.NORM_INPUT_MATRICES_KEY]
if input_matrices is None:
input_matrices = [None] * len(these_input_matrices)
for k in range(len(input_matrices)):
if input_matrices[k] is None:
input_matrices[k] = these_input_matrices[k] + 0.
else:
input_matrices[k] = numpy.concatenate(
(input_matrices[k], these_input_matrices[k]), axis=0)
print(SEPARATOR_STRING)
training_option_dict = model_metadata_dict[cnn.TRAINING_OPTION_DICT_KEY]
print('Denormalizing input examples...')
input_matrices = trainval_io.separate_shear_and_reflectivity(
list_of_input_matrices=input_matrices,
training_option_dict=training_option_dict)
input_matrices = model_interpretation.denormalize_data(
list_of_input_matrices=input_matrices,
model_metadata_dict=model_metadata_dict)
print('Denormalizing optimized examples...')
output_matrices = trainval_io.separate_shear_and_reflectivity(
list_of_input_matrices=output_matrices,
training_option_dict=training_option_dict)
output_matrices = model_interpretation.denormalize_data(
list_of_input_matrices=output_matrices,
model_metadata_dict=model_metadata_dict)
print('Writing results to: "{0:s}"...'.format(output_file_name))
bwo_metadata_dict = backwards_opt.check_metadata(
component_type_string=component_type_string,
num_iterations=num_iterations,
learning_rate=learning_rate,
target_class=target_class,
layer_name=layer_name,
ideal_activation=ideal_activation,
neuron_indices=neuron_indices,
channel_index=channel_index,
l2_weight=l2_weight,
radar_constraint_weight=radar_constraint_weight,
minmax_constraint_weight=minmax_constraint_weight)
backwards_opt.write_standard_file(
pickle_file_name=output_file_name,
denorm_input_matrices=input_matrices,
denorm_output_matrices=output_matrices,
initial_activations=initial_activations,
final_activations=final_activations,
model_file_name=model_file_name,
metadata_dict=bwo_metadata_dict,
full_storm_id_strings=full_storm_id_strings,
storm_times_unix_sec=storm_times_unix_sec,
sounding_pressure_matrix_pa=sounding_pressure_matrix_pa)
def _run(input_example_dir_name, storm_metafile_name, num_examples_in_subset,
subset_randomly, output_example_file_name):
"""Extracts desired examples and writes them to one file.
This is effectively the main method.
:param input_example_dir_name: See documentation at top of file.
:param storm_metafile_name: Same.
:param num_examples_in_subset: Same.
:param subset_randomly: Same.
:param output_example_file_name: Same.
"""
print(
'Reading storm metadata from: "{0:s}"...'.format(storm_metafile_name))
example_id_strings, example_times_unix_sec = (
tracking_io.read_ids_and_times(storm_metafile_name))
if not 0 < num_examples_in_subset < len(example_id_strings):
num_examples_in_subset = None
if num_examples_in_subset is not None:
if subset_randomly:
these_indices = numpy.linspace(0,
len(example_id_strings) - 1,
num=len(example_id_strings),
dtype=int)
these_indices = numpy.random.choice(these_indices,
size=num_examples_in_subset,
replace=False)
example_id_strings = [example_id_strings[k] for k in these_indices]
example_times_unix_sec = example_times_unix_sec[these_indices]
else:
example_id_strings = example_id_strings[:num_examples_in_subset]
example_times_unix_sec = (
example_times_unix_sec[:num_examples_in_subset])
example_spc_date_strings = numpy.array([
time_conversion.time_to_spc_date_string(t)
for t in example_times_unix_sec
])
spc_date_strings = numpy.unique(example_spc_date_strings)
example_file_name_by_day = [
input_examples.find_example_file(
top_directory_name=input_example_dir_name,
shuffled=False,
spc_date_string=d,
raise_error_if_missing=True) for d in spc_date_strings
]
num_days = len(spc_date_strings)
for i in range(num_days):
print('Reading data from: "{0:s}"...'.format(
example_file_name_by_day[i]))
all_example_dict = input_examples.read_example_file(
netcdf_file_name=example_file_name_by_day[i],
read_all_target_vars=True)
these_indices = numpy.where(
example_spc_date_strings == spc_date_strings[i])[0]
desired_indices = tracking_utils.find_storm_objects(
all_id_strings=all_example_dict[input_examples.FULL_IDS_KEY],
all_times_unix_sec=all_example_dict[
input_examples.STORM_TIMES_KEY],
id_strings_to_keep=[example_id_strings[k] for k in these_indices],
times_to_keep_unix_sec=example_times_unix_sec[these_indices],
allow_missing=False)
desired_example_dict = input_examples.subset_examples(
example_dict=all_example_dict, indices_to_keep=desired_indices)
print('Writing {0:d} desired examples to: "{1:s}"...'.format(
len(desired_indices), output_example_file_name))
input_examples.write_example_file(
netcdf_file_name=output_example_file_name,
example_dict=desired_example_dict,
append_to_file=i > 0)
def _run(upconvnet_file_name, storm_metafile_name, num_examples,
top_example_dir_name, top_output_dir_name):
"""Plots upconvnet reconstructions of many examples (storm objects).
This is effectively the main method.
:param upconvnet_file_name: See documentation at top of file.
:param storm_metafile_name: Same.
:param num_examples: Same.
:param top_example_dir_name: Same.
:param top_output_dir_name: Same.
"""
print 'Reading trained upconvnet from: "{0:s}"...'.format(
upconvnet_file_name)
upconvnet_model_object = cnn.read_model(upconvnet_file_name)
upconvnet_metafile_name = '{0:s}/model_metadata.p'.format(
os.path.split(upconvnet_file_name)[0]
)
print 'Reading upconvnet metadata from: "{0:s}"...'.format(
upconvnet_metafile_name)
upconvnet_metadata_dict = upconvnet.read_model_metadata(
upconvnet_metafile_name)
cnn_file_name = upconvnet_metadata_dict[upconvnet.CNN_FILE_KEY]
print 'Reading trained CNN from: "{0:s}"...'.format(cnn_file_name)
cnn_model_object = cnn.read_model(cnn_file_name)
cnn_metafile_name = '{0:s}/model_metadata.p'.format(
os.path.split(cnn_file_name)[0]
)
print 'Reading CNN metadata from: "{0:s}"...'.format(cnn_metafile_name)
cnn_metadata_dict = cnn.read_model_metadata(cnn_metafile_name)
training_option_dict = cnn_metadata_dict[cnn.TRAINING_OPTION_DICT_KEY]
print 'Reading storm IDs and times from: "{0:s}"...'.format(
storm_metafile_name)
storm_ids, storm_times_unix_sec = tracking_io.read_ids_and_times(
storm_metafile_name)
if 0 < num_examples < len(storm_ids):
storm_ids = storm_ids[:num_examples]
storm_times_unix_sec = storm_times_unix_sec[:num_examples]
print SEPARATOR_STRING
list_of_predictor_matrices = testing_io.read_specific_examples(
desired_storm_ids=storm_ids,
desired_times_unix_sec=storm_times_unix_sec,
option_dict=training_option_dict,
top_example_dir_name=top_example_dir_name,
list_of_layer_operation_dicts=cnn_metadata_dict[
cnn.LAYER_OPERATIONS_KEY]
)[0]
print SEPARATOR_STRING
actual_radar_matrix = list_of_predictor_matrices[0]
have_soundings = training_option_dict[trainval_io.SOUNDING_FIELDS_KEY]
if have_soundings:
sounding_matrix = list_of_predictor_matrices[-1]
else:
sounding_matrix = None
feature_matrix = cnn.apply_2d_or_3d_cnn(
model_object=cnn_model_object, radar_image_matrix=actual_radar_matrix,
sounding_matrix=sounding_matrix, verbose=True, return_features=True,
feature_layer_name=upconvnet_metadata_dict[
upconvnet.CNN_FEATURE_LAYER_KEY]
)
print '\n'
reconstructed_radar_matrix = upconvnet.apply_upconvnet(
model_object=upconvnet_model_object, feature_matrix=feature_matrix,
verbose=True)
print '\n'
print 'Denormalizing actual and reconstructed radar images...'
cnn_metadata_dict[
cnn.TRAINING_OPTION_DICT_KEY][trainval_io.SOUNDING_FIELDS_KEY] = None
actual_radar_matrix = model_interpretation.denormalize_data(
list_of_input_matrices=[actual_radar_matrix],
model_metadata_dict=cnn_metadata_dict
)[0]
reconstructed_radar_matrix = model_interpretation.denormalize_data(
list_of_input_matrices=[reconstructed_radar_matrix],
model_metadata_dict=cnn_metadata_dict
)[0]
print SEPARATOR_STRING
actual_output_dir_name = '{0:s}/actual_images'.format(top_output_dir_name)
file_system_utils.mkdir_recursive_if_necessary(
directory_name=actual_output_dir_name)
# TODO(thunderhoser): Calling a method in another script is hacky. If this
# method is going to be reused, should be in a module.
plot_input_examples.plot_examples(
list_of_predictor_matrices=[actual_radar_matrix], storm_ids=storm_ids,
storm_times_unix_sec=storm_times_unix_sec,
model_metadata_dict=cnn_metadata_dict,
output_dir_name=actual_output_dir_name)
print SEPARATOR_STRING
reconstructed_output_dir_name = '{0:s}/reconstructed_images'.format(
top_output_dir_name)
file_system_utils.mkdir_recursive_if_necessary(
directory_name=reconstructed_output_dir_name)
plot_input_examples.plot_examples(
list_of_predictor_matrices=[reconstructed_radar_matrix],
storm_ids=storm_ids, storm_times_unix_sec=storm_times_unix_sec,
model_metadata_dict=cnn_metadata_dict,
output_dir_name=reconstructed_output_dir_name)
def _run(model_file_name, target_class, target_layer_name,
top_example_dir_name, storm_metafile_name, num_examples,
output_file_name):
"""Runs Grad-CAM (gradient-weighted class-activation maps).
This is effectively the main method.
:param model_file_name: See documentation at top of file.
:param target_class: Same.
:param target_layer_name: Same.
:param top_example_dir_name: Same.
:param storm_metafile_name: Same.
:param num_examples: Same.
:param output_file_name: Same.
"""
file_system_utils.mkdir_recursive_if_necessary(file_name=output_file_name)
# Read model and metadata.
print('Reading model from: "{0:s}"...'.format(model_file_name))
model_object = cnn.read_model(model_file_name)
model_metafile_name = '{0:s}/model_metadata.p'.format(
os.path.split(model_file_name)[0])
print(
'Reading model metadata from: "{0:s}"...'.format(model_metafile_name))
model_metadata_dict = cnn.read_model_metadata(model_metafile_name)
training_option_dict = model_metadata_dict[cnn.TRAINING_OPTION_DICT_KEY]
training_option_dict[trainval_io.REFLECTIVITY_MASK_KEY] = None
print(
'Reading storm metadata from: "{0:s}"...'.format(storm_metafile_name))
full_id_strings, storm_times_unix_sec = tracking_io.read_ids_and_times(
storm_metafile_name)
print(SEPARATOR_STRING)
if 0 < num_examples < len(full_id_strings):
full_id_strings = full_id_strings[:num_examples]
storm_times_unix_sec = storm_times_unix_sec[:num_examples]
list_of_input_matrices, sounding_pressure_matrix_pascals = (
testing_io.read_specific_examples(
top_example_dir_name=top_example_dir_name,
desired_full_id_strings=full_id_strings,
desired_times_unix_sec=storm_times_unix_sec,
option_dict=training_option_dict,
list_of_layer_operation_dicts=model_metadata_dict[
cnn.LAYER_OPERATIONS_KEY]))
print(SEPARATOR_STRING)
list_of_cam_matrices = None
list_of_guided_cam_matrices = None
new_model_object = None
num_examples = len(full_id_strings)
for i in range(num_examples):
print('Running Grad-CAM for example {0:d} of {1:d}...'.format(
i + 1, num_examples))
these_input_matrices = [a[[i], ...] for a in list_of_input_matrices]
these_cam_matrices = gradcam.run_gradcam(
model_object=model_object,
list_of_input_matrices=these_input_matrices,
target_class=target_class,
target_layer_name=target_layer_name)
print('Running guided Grad-CAM for example {0:d} of {1:d}...'.format(
i + 1, num_examples))
these_guided_cam_matrices, new_model_object = (
gradcam.run_guided_gradcam(
orig_model_object=model_object,
list_of_input_matrices=these_input_matrices,
target_layer_name=target_layer_name,
list_of_cam_matrices=these_cam_matrices,
new_model_object=new_model_object))
if list_of_cam_matrices is None:
list_of_cam_matrices = copy.deepcopy(these_cam_matrices)
list_of_guided_cam_matrices = copy.deepcopy(
these_guided_cam_matrices)
else:
for j in range(len(these_cam_matrices)):
if list_of_cam_matrices[j] is None:
continue
list_of_cam_matrices[j] = numpy.concatenate(
(list_of_cam_matrices[j], these_cam_matrices[j]), axis=0)
list_of_guided_cam_matrices[j] = numpy.concatenate(
(list_of_guided_cam_matrices[j],
these_guided_cam_matrices[j]),
axis=0)
print(SEPARATOR_STRING)
upsample_refl = training_option_dict[trainval_io.UPSAMPLE_REFLECTIVITY_KEY]
if upsample_refl:
list_of_cam_matrices[0] = numpy.expand_dims(list_of_cam_matrices[0],
axis=-1)
num_channels = list_of_input_matrices[0].shape[-1]
list_of_cam_matrices[0] = numpy.repeat(a=list_of_cam_matrices[0],
repeats=num_channels,
axis=-1)
list_of_cam_matrices = trainval_io.separate_shear_and_reflectivity(
list_of_input_matrices=list_of_cam_matrices,
training_option_dict=training_option_dict)
list_of_cam_matrices[0] = list_of_cam_matrices[0][..., 0]
list_of_cam_matrices[1] = list_of_cam_matrices[1][..., 0]
list_of_guided_cam_matrices = trainval_io.separate_shear_and_reflectivity(
list_of_input_matrices=list_of_guided_cam_matrices,
training_option_dict=training_option_dict)
print('Denormalizing predictors...')
list_of_input_matrices = trainval_io.separate_shear_and_reflectivity(
list_of_input_matrices=list_of_input_matrices,
training_option_dict=training_option_dict)
list_of_input_matrices = model_interpretation.denormalize_data(
list_of_input_matrices=list_of_input_matrices,
model_metadata_dict=model_metadata_dict)
print('Writing class-activation maps to file: "{0:s}"...'.format(
output_file_name))
gradcam.write_standard_file(
pickle_file_name=output_file_name,
list_of_input_matrices=list_of_input_matrices,
list_of_cam_matrices=list_of_cam_matrices,
list_of_guided_cam_matrices=list_of_guided_cam_matrices,
model_file_name=model_file_name,
full_id_strings=full_id_strings,
storm_times_unix_sec=storm_times_unix_sec,
target_class=target_class,
target_layer_name=target_layer_name,
sounding_pressure_matrix_pascals=sounding_pressure_matrix_pascals)
def _run(model_file_name, target_class, target_layer_name,
top_example_dir_name, storm_metafile_name, num_examples,
randomize_weights, cascading_random, output_file_name):
"""Runs Grad-CAM (gradient-weighted class-activation maps).
This is effectively the main method.
:param model_file_name: See documentation at top of file.
:param target_class: Same.
:param target_layer_name: Same.
:param top_example_dir_name: Same.
:param storm_metafile_name: Same.
:param num_examples: Same.
:param randomize_weights: Same.
:param cascading_random: Same.
:param output_file_name: Same.
"""
file_system_utils.mkdir_recursive_if_necessary(file_name=output_file_name)
# Read model and metadata.
print('Reading model from: "{0:s}"...'.format(model_file_name))
model_object = cnn.read_model(model_file_name)
model_metafile_name = '{0:s}/model_metadata.p'.format(
os.path.split(model_file_name)[0])
print(
'Reading model metadata from: "{0:s}"...'.format(model_metafile_name))
model_metadata_dict = cnn.read_model_metadata(model_metafile_name)
training_option_dict = model_metadata_dict[cnn.TRAINING_OPTION_DICT_KEY]
training_option_dict[trainval_io.REFLECTIVITY_MASK_KEY] = None
output_dir_name, pathless_output_file_name = os.path.split(
output_file_name)
extensionless_output_file_name, output_file_extension = os.path.splitext(
pathless_output_file_name)
if randomize_weights:
conv_dense_layer_names = _find_conv_and_dense_layers(model_object)
conv_dense_layer_names.reverse()
num_sets = len(conv_dense_layer_names)
else:
conv_dense_layer_names = []
num_sets = 1
print(
'Reading storm metadata from: "{0:s}"...'.format(storm_metafile_name))
full_storm_id_strings, storm_times_unix_sec = (
tracking_io.read_ids_and_times(storm_metafile_name))
print(SEPARATOR_STRING)
if 0 < num_examples < len(full_storm_id_strings):
full_storm_id_strings = full_storm_id_strings[:num_examples]
storm_times_unix_sec = storm_times_unix_sec[:num_examples]
example_dict = testing_io.read_predictors_specific_examples(
top_example_dir_name=top_example_dir_name,
desired_full_id_strings=full_storm_id_strings,
desired_times_unix_sec=storm_times_unix_sec,
option_dict=training_option_dict,
layer_operation_dicts=model_metadata_dict[cnn.LAYER_OPERATIONS_KEY])
print(SEPARATOR_STRING)
predictor_matrices = example_dict[testing_io.INPUT_MATRICES_KEY]
sounding_pressure_matrix_pa = (
example_dict[testing_io.SOUNDING_PRESSURES_KEY])
print('Denormalizing model inputs...')
denorm_predictor_matrices = trainval_io.separate_shear_and_reflectivity(
list_of_input_matrices=copy.deepcopy(predictor_matrices),
training_option_dict=training_option_dict)
denorm_predictor_matrices = model_interpretation.denormalize_data(
list_of_input_matrices=denorm_predictor_matrices,
model_metadata_dict=model_metadata_dict)
print(SEPARATOR_STRING)
for k in range(num_sets):
if randomize_weights:
if cascading_random:
_reset_weights_in_layer(model_object=model_object,
layer_name=conv_dense_layer_names[k])
this_model_object = model_object
this_output_file_name = (
'{0:s}/{1:s}_cascading-random_{2:s}{3:s}').format(
output_dir_name, extensionless_output_file_name,
conv_dense_layer_names[k].replace('_', '-'),
output_file_extension)
else:
this_model_object = keras.models.Model.from_config(
model_object.get_config())
this_model_object.set_weights(model_object.get_weights())
_reset_weights_in_layer(model_object=this_model_object,
layer_name=conv_dense_layer_names[k])
this_output_file_name = '{0:s}/{1:s}_random_{2:s}{3:s}'.format(
output_dir_name, extensionless_output_file_name,
conv_dense_layer_names[k].replace('_', '-'),
output_file_extension)
else:
this_model_object = model_object
this_output_file_name = output_file_name
# print(K.eval(this_model_object.get_layer(name='dense_53').weights[0]))
these_cam_matrices, these_guided_cam_matrices = (
_run_gradcam_one_weight_set(
model_object=this_model_object,
target_class=target_class,
target_layer_name=target_layer_name,
predictor_matrices=predictor_matrices,
training_option_dict=training_option_dict))
print('Writing results to file: "{0:s}"...'.format(
this_output_file_name))
gradcam.write_standard_file(
pickle_file_name=this_output_file_name,
denorm_predictor_matrices=denorm_predictor_matrices,
cam_matrices=these_cam_matrices,
guided_cam_matrices=these_guided_cam_matrices,
full_storm_id_strings=full_storm_id_strings,
storm_times_unix_sec=storm_times_unix_sec,
model_file_name=model_file_name,
target_class=target_class,
target_layer_name=target_layer_name,
sounding_pressure_matrix_pa=sounding_pressure_matrix_pa)
print(SEPARATOR_STRING)
def _run(model_file_name, target_class, target_layer_name,
top_example_dir_name, storm_metafile_name, num_examples,
output_file_name):
"""Runs Grad-CAM (gradient-weighted class-activation maps).
This is effectively the main method.
:param model_file_name: See documentation at top of file.
:param target_class: Same.
:param target_layer_name: Same.
:param top_example_dir_name: Same.
:param storm_metafile_name: Same.
:param num_examples: Same.
:param output_file_name: Same.
"""
file_system_utils.mkdir_recursive_if_necessary(file_name=output_file_name)
# Read model and metadata.
print 'Reading model from: "{0:s}"...'.format(model_file_name)
model_object = cnn.read_model(model_file_name)
model_metafile_name = '{0:s}/model_metadata.p'.format(
os.path.split(model_file_name)[0])
print 'Reading model metadata from: "{0:s}"...'.format(model_metafile_name)
model_metadata_dict = cnn.read_model_metadata(model_metafile_name)
training_option_dict = model_metadata_dict[cnn.TRAINING_OPTION_DICT_KEY]
training_option_dict[trainval_io.REFLECTIVITY_MASK_KEY] = None
print 'Reading storm metadata from: "{0:s}"...'.format(storm_metafile_name)
storm_ids, storm_times_unix_sec = tracking_io.read_ids_and_times(
storm_metafile_name)
print SEPARATOR_STRING
if 0 < num_examples < len(storm_ids):
storm_ids = storm_ids[:num_examples]
storm_times_unix_sec = storm_times_unix_sec[:num_examples]
list_of_input_matrices, sounding_pressure_matrix_pascals = (
testing_io.read_specific_examples(
top_example_dir_name=top_example_dir_name,
desired_storm_ids=storm_ids,
desired_times_unix_sec=storm_times_unix_sec,
option_dict=training_option_dict,
list_of_layer_operation_dicts=model_metadata_dict[
cnn.LAYER_OPERATIONS_KEY]))
print SEPARATOR_STRING
class_activation_matrix = None
ggradcam_output_matrix = None
new_model_object = None
num_examples = len(storm_ids)
for i in range(num_examples):
print 'Running Grad-CAM for example {0:d} of {1:d}...'.format(
i + 1, num_examples)
these_input_matrices = [a[[i], ...] for a in list_of_input_matrices]
this_class_activation_matrix = gradcam.run_gradcam(
model_object=model_object,
list_of_input_matrices=these_input_matrices,
target_class=target_class,
target_layer_name=target_layer_name)
print 'Running guided Grad-CAM for example {0:d} of {1:d}...'.format(
i + 1, num_examples)
this_ggradcam_output_matrix, new_model_object = (
gradcam.run_guided_gradcam(
orig_model_object=model_object,
list_of_input_matrices=these_input_matrices,
target_layer_name=target_layer_name,
class_activation_matrix=this_class_activation_matrix,
new_model_object=new_model_object))
this_class_activation_matrix = numpy.expand_dims(
this_class_activation_matrix, axis=0)
this_ggradcam_output_matrix = numpy.expand_dims(
this_ggradcam_output_matrix, axis=0)
if class_activation_matrix is None:
class_activation_matrix = this_class_activation_matrix + 0.
ggradcam_output_matrix = this_ggradcam_output_matrix + 0.
else:
class_activation_matrix = numpy.concatenate(
(class_activation_matrix, this_class_activation_matrix),
axis=0)
ggradcam_output_matrix = numpy.concatenate(
(ggradcam_output_matrix, this_ggradcam_output_matrix), axis=0)
print SEPARATOR_STRING
print 'Denormalizing predictors...'
list_of_input_matrices = model_interpretation.denormalize_data(
list_of_input_matrices=list_of_input_matrices,
model_metadata_dict=model_metadata_dict)
print 'Writing class-activation maps to file: "{0:s}"...'.format(
output_file_name)
gradcam.write_standard_file(
pickle_file_name=output_file_name,
list_of_input_matrices=list_of_input_matrices,
class_activation_matrix=class_activation_matrix,
ggradcam_output_matrix=ggradcam_output_matrix,
model_file_name=model_file_name,
storm_ids=storm_ids,
storm_times_unix_sec=storm_times_unix_sec,
target_class=target_class,
target_layer_name=target_layer_name,
sounding_pressure_matrix_pascals=sounding_pressure_matrix_pascals)
def _run(model_file_name, layer_names, top_example_dir_name,
storm_metafile_name, num_examples, top_output_dir_name):
"""Evaluates CNN (convolutional neural net) predictions.
This is effectively the main method.
:param model_file_name: See documentation at top of file.
:param layer_names: Same.
:param top_example_dir_name: Same.
:param storm_metafile_name: Same.
:param num_examples: Same.
:param top_output_dir_name: Same.
:raises: ValueError: if feature maps do not have 2 or 3 spatial dimensions.
"""
print('Reading model from: "{0:s}"...'.format(model_file_name))
model_object = cnn.read_model(model_file_name)
model_metafile_name = '{0:s}/model_metadata.p'.format(
os.path.split(model_file_name)[0])
print(
'Reading model metadata from: "{0:s}"...'.format(model_metafile_name))
model_metadata_dict = cnn.read_model_metadata(model_metafile_name)
training_option_dict = model_metadata_dict[cnn.TRAINING_OPTION_DICT_KEY]
training_option_dict[trainval_io.REFLECTIVITY_MASK_KEY] = None
print(
'Reading storm metadata from: "{0:s}"...'.format(storm_metafile_name))
full_id_strings, storm_times_unix_sec = tracking_io.read_ids_and_times(
storm_metafile_name)
print(SEPARATOR_STRING)
if 0 < num_examples < len(full_id_strings):
full_id_strings = full_id_strings[:num_examples]
storm_times_unix_sec = storm_times_unix_sec[:num_examples]
list_of_predictor_matrices = testing_io.read_specific_examples(
top_example_dir_name=top_example_dir_name,
desired_full_id_strings=full_id_strings,
desired_times_unix_sec=storm_times_unix_sec,
option_dict=training_option_dict,
list_of_layer_operation_dicts=model_metadata_dict[
cnn.LAYER_OPERATIONS_KEY])[0]
print(SEPARATOR_STRING)
include_soundings = (training_option_dict[trainval_io.SOUNDING_FIELDS_KEY]
is not None)
if include_soundings:
sounding_matrix = list_of_predictor_matrices[-1]
else:
sounding_matrix = None
num_layers = len(layer_names)
feature_matrix_by_layer = [None] * num_layers
for k in range(num_layers):
if model_metadata_dict[cnn.CONV_2D3D_KEY]:
if training_option_dict[trainval_io.UPSAMPLE_REFLECTIVITY_KEY]:
feature_matrix_by_layer[k] = cnn.apply_2d_or_3d_cnn(
model_object=model_object,
radar_image_matrix=list_of_predictor_matrices[0],
sounding_matrix=sounding_matrix,
return_features=True,
feature_layer_name=layer_names[k])
else:
feature_matrix_by_layer[k] = cnn.apply_2d3d_cnn(
model_object=model_object,
reflectivity_matrix_dbz=list_of_predictor_matrices[0],
azimuthal_shear_matrix_s01=list_of_predictor_matrices[1],
sounding_matrix=sounding_matrix,
return_features=True,
feature_layer_name=layer_names[k])
else:
feature_matrix_by_layer[k] = cnn.apply_2d_or_3d_cnn(
model_object=model_object,
radar_image_matrix=list_of_predictor_matrices[0],
sounding_matrix=sounding_matrix,
return_features=True,
feature_layer_name=layer_names[k])
for k in range(num_layers):
this_output_dir_name = '{0:s}/{1:s}'.format(top_output_dir_name,
layer_names[k])
file_system_utils.mkdir_recursive_if_necessary(
directory_name=this_output_dir_name)
_plot_feature_maps_one_layer(feature_matrix=feature_matrix_by_layer[k],
full_id_strings=full_id_strings,
storm_times_unix_sec=storm_times_unix_sec,
layer_name=layer_names[k],
output_dir_name=this_output_dir_name)
print(SEPARATOR_STRING)
def _run(model_file_name, component_type_string, target_class, layer_name,
ideal_activation, neuron_indices, channel_index, top_example_dir_name,
storm_metafile_name, num_examples, output_file_name):
"""Computes saliency map for each storm object and each model component.
This is effectively the main method.
:param model_file_name: See documentation at top of file.
:param component_type_string: Same.
:param target_class: Same.
:param layer_name: Same.
:param ideal_activation: Same.
:param neuron_indices: Same.
:param channel_index: Same.
:param top_example_dir_name: Same.
:param storm_metafile_name: Same.
:param num_examples: Same.
:param output_file_name: Same.
"""
# Check input args.
file_system_utils.mkdir_recursive_if_necessary(file_name=output_file_name)
model_interpretation.check_component_type(component_type_string)
# Read model and metadata.
print 'Reading model from: "{0:s}"...'.format(model_file_name)
model_object = cnn.read_model(model_file_name)
model_metafile_name = '{0:s}/model_metadata.p'.format(
os.path.split(model_file_name)[0])
print 'Reading model metadata from: "{0:s}"...'.format(model_metafile_name)
model_metadata_dict = cnn.read_model_metadata(model_metafile_name)
training_option_dict = model_metadata_dict[cnn.TRAINING_OPTION_DICT_KEY]
training_option_dict[trainval_io.REFLECTIVITY_MASK_KEY] = None
print 'Reading storm metadata from: "{0:s}"...'.format(storm_metafile_name)
storm_ids, storm_times_unix_sec = tracking_io.read_ids_and_times(
storm_metafile_name)
print SEPARATOR_STRING
if 0 < num_examples < len(storm_ids):
storm_ids = storm_ids[:num_examples]
storm_times_unix_sec = storm_times_unix_sec[:num_examples]
list_of_input_matrices, sounding_pressure_matrix_pascals = (
testing_io.read_specific_examples(
top_example_dir_name=top_example_dir_name,
desired_storm_ids=storm_ids,
desired_times_unix_sec=storm_times_unix_sec,
option_dict=training_option_dict,
list_of_layer_operation_dicts=model_metadata_dict[
cnn.LAYER_OPERATIONS_KEY]))
print SEPARATOR_STRING
if component_type_string == CLASS_COMPONENT_TYPE_STRING:
print 'Computing saliency maps for target class {0:d}...'.format(
target_class)
list_of_saliency_matrices = (
saliency_maps.get_saliency_maps_for_class_activation(
model_object=model_object,
target_class=target_class,
list_of_input_matrices=list_of_input_matrices))
elif component_type_string == NEURON_COMPONENT_TYPE_STRING:
print('Computing saliency maps for neuron {0:s} in layer "{1:s}"...'
).format(str(neuron_indices), layer_name)
list_of_saliency_matrices = (
saliency_maps.get_saliency_maps_for_neuron_activation(
model_object=model_object,
layer_name=layer_name,
neuron_indices=neuron_indices,
list_of_input_matrices=list_of_input_matrices,
ideal_activation=ideal_activation))
else:
print('Computing saliency maps for channel {0:d} in layer "{1:s}"...'
).format(channel_index, layer_name)
list_of_saliency_matrices = (
saliency_maps.get_saliency_maps_for_channel_activation(
model_object=model_object,
layer_name=layer_name,
channel_index=channel_index,
list_of_input_matrices=list_of_input_matrices,
stat_function_for_neuron_activations=K.max,
ideal_activation=ideal_activation))
print 'Denormalizing model inputs...'
list_of_input_matrices = model_interpretation.denormalize_data(
list_of_input_matrices=list_of_input_matrices,
model_metadata_dict=model_metadata_dict)
print 'Writing saliency maps to file: "{0:s}"...'.format(output_file_name)
saliency_metadata_dict = saliency_maps.check_metadata(
component_type_string=component_type_string,
target_class=target_class,
layer_name=layer_name,
ideal_activation=ideal_activation,
neuron_indices=neuron_indices,
channel_index=channel_index)
saliency_maps.write_standard_file(
pickle_file_name=output_file_name,
list_of_input_matrices=list_of_input_matrices,
list_of_saliency_matrices=list_of_saliency_matrices,
storm_ids=storm_ids,
storm_times_unix_sec=storm_times_unix_sec,
model_file_name=model_file_name,
saliency_metadata_dict=saliency_metadata_dict,
sounding_pressure_matrix_pascals=sounding_pressure_matrix_pascals)
