def main(argv):
if len(argv) not in [3, 4] or argv[1] not in ["all", "test"]:
exit(0)
if len(argv) == 4 and argv[3] == "-i":
use_interactive_mode = True
else:
use_interactive_mode = False
train_data, test_data, train_labels, test_labels, label_names, dataset_name = get_data(argv)
df = runner.run(
train_data=train_data,
test_data=test_data,
preproc=Preprocessor,
preproc_params=None,
err_root_node=get_err_root_node(),
err_params_list=get_err_params_list(),
model_params_dict_list=get_model_params_dict_list(train_labels, test_labels),
use_interactive_mode=use_interactive_mode
)
print_results_by_model(df, dropped_columns=[
"train_labels", "test_labels", "reduced_test_data", "confusion_matrix", "predicted_test_labels",
"radius_generator", "missing_value", "normalized_params"
])
visualize(df, dataset_name, label_names, test_data, use_interactive_mode)
def main():
imgs, _, _, img_filenames = load_coco_val_2017()
df = runner.run(
train_data=None,
test_data=imgs,
preproc=Preprocessor,
preproc_params={"img_filenames": img_filenames},
err_root_node=get_err_root_node(),
err_params_list=get_err_params_list(),
model_params_dict_list=get_model_params_dict_list(),
n_processes=1
)
print_results_by_model(df, dropped_columns=["show_imgs", "mean", "radius_generator", "transparency_percentage",
"range", "snowflake_alpha", "snowstorm_alpha", "tar", "range"])
visualize(df)
def main(argv):
# Create some fake data
if len(argv) == 2:
train_data, test_data = get_data(argv)
else:
exit(0)
# Run the whole thing and get DataFrame for visualization
df = runner.run(train_data=train_data,
test_data=test_data,
preproc=Preprocessor,
preproc_params=None,
err_root_node=get_err_root_node(),
err_params_list=get_err_params_list(),
model_params_dict_list=get_model_params_dict_list())
print_results_by_model(df)
visualize(df)
def main(argv):
if len(argv) != 3 or argv[1] not in [
"passengers", "Jerusalem", "Eilat", "Miami", "Tel Aviv District"
]:
exit(0)
train_data, test_data, n_data, n_period, dataset_name = get_data(argv)
df = runner.run(
train_data=train_data,
test_data=test_data,
preproc=Preprocessor,
preproc_params={},
err_root_node=get_err_root_node(),
err_params_list=get_err_params_list(),
model_params_dict_list=get_model_params_dict_list(test_data, n_period),
)
print_results_by_model(
df,
dropped_columns=["err_train", "test_pred", "clean_test", "n_period"])
visualize(df, np.concatenate([train_data, test_data], axis=0), n_data,
dataset_name)
def main(argv):
if len(argv) not in [3, 4
] or argv[1] not in ["digits", "mnist", "fashion"]:
exit(0)
if len(argv) == 4 and argv[3] == "-i":
use_interactive_mode = True
else:
use_interactive_mode = False
data, labels, label_names, dataset_name = get_data(argv)
df = runner.run(train_data=None,
test_data=data,
preproc=Preprocessor,
preproc_params=None,
err_root_node=get_err_root_node(),
err_params_list=get_err_params_list(data),
model_params_dict_list=get_model_params_dict_list(
data, labels),
use_interactive_mode=use_interactive_mode)
print_results_by_model(
df, ["missing_value", "min_val", "max_val", "labels", "reduced_data"])
visualize(df, label_names, dataset_name, data, use_interactive_mode)
def main(argv):
if len(argv) != 2:
exit(0)
imgs, img_ids, class_names, _ = get_data(argv)
path_to_yolov3_weights, path_to_yolov3_cfg = load_yolov3()
df = runner.run(train_data=None,
test_data=imgs,
preproc=Preprocessor,
preproc_params=None,
err_root_node=get_err_root_node(),
err_params_list=get_err_params_list(),
model_params_dict_list=get_model_params_dict_list(
img_ids, class_names, path_to_yolov3_weights,
path_to_yolov3_cfg),
n_processes=1)
print_results_by_model(df, [
"img_ids", "class_names", "show_imgs", "mean", "radius_generator",
"transparency_percentage", "range", "snowflake_alpha",
"snowstorm_alpha"
])
visualize(df)