def main():
"""Main function for the task 4"""
feature_extraction_model = get_input_feature_extractor_model()
dimension_reduction_model = get_input_dimensionality_reduction_model()
k_value = get_input_k()
label = get_input_image_label()
folder = get_input_folder()
image_name = get_input_image(folder)
m_value = get_input_m()
if dimension_reduction_model != "NMF":
dist_func = "euclidean"
elif feature_extraction_model in ["CM", "LBP"]:
dist_func = "nvsc1"
else:
dist_func = "euclidean"
# dist_func = "cosine"
# dist_func = "chebyshev"
# dist_func = "manhattan"
# dist_func = "chi_square"
# dist_func = "euclidean"
print(global_constants.LINE_SEPARATOR)
print("User Inputs summary")
print(global_constants.LINE_SEPARATOR)
print("Feature Extraction Model: {}\nDimensionality Reduction Model: {}\nk-value: {}\nLabel: {}\nFolder: {}\n"
"Image: {}\nm-value: {}".format(feature_extraction_model, dimension_reduction_model, k_value, label, folder,
image_name, m_value))
print(global_constants.LINE_SEPARATOR)
# Saves the returned model
filename = "{0}_{1}_{2}_{3}".format(feature_extraction_model, dimension_reduction_model, label.replace(" ", ''),
str(k_value))
model = model_interact.load_model(filename=filename)
if not model:
print("Please run Task 3 for {}, {}, {} and {}".format(feature_extraction_model, dimension_reduction_model,
label, k_value))
sys.exit(1)
# Compute the reduced dimensions for the new query image and find m similar images
dim_reduction = DimensionReduction(feature_extraction_model, dimension_reduction_model, k_value, label)
result = dim_reduction.find_m_similar_images(model, m_value, folder, image_name, dist_func)
print(global_constants.LINE_SEPARATOR)
print("Similar Images")
print(global_constants.LINE_SEPARATOR)
for rec in result:
print(rec)
print(global_constants.LINE_SEPARATOR)
title = {
"Feature Extraction": feature_extraction_model,
"Dimension Reduction": dimension_reduction_model,
"k": k_value,
"Label": label,
"Distance": dist_func
}
show_images(os.path.abspath(os.path.join(folder, image_name)), result, title)
def main():
query_image = get_input_image("Hands")
no_images = get_input_k("t")
similar_images, img_vectors, query_image_vector = get_LSH_results(
query_image, no_images)
# while True:
# rerank_results(None)
relevancefeedback.relevance_fdbk("DT", query_image, similar_images,
img_vectors, query_image_vector)
pass
def main():
feature_extraction_model = get_input_feature_extractor_model()
dimension_reduction_model = get_input_dimensionality_reduction_model()
label = get_input_image_label()
k_value = get_input_k()
query_folder = get_input_folder()
image_name = get_input_image(query_folder)
m_value = 1
print(global_constants.LINE_SEPARATOR)
print("User Inputs summary")
print(global_constants.LINE_SEPARATOR)
print(
"Feature Extraction Model: {}\nDimensionality Reduction Model: {}\nLabel: {}\nk-value: {}\nQuery Folder: {}"
"\nImage: {}".format(feature_extraction_model,
dimension_reduction_model, label, k_value,
query_folder, image_name, m_value))
print(global_constants.LINE_SEPARATOR)
if dimension_reduction_model != "NMF":
dist_func = "euclidean"
elif feature_extraction_model in ["CM", "LBP"]:
dist_func = "nvsc1"
else:
dist_func = "euclidean"
# dist_func = "cosine"
# dist_func = "chebyshev"
# dist_func = "manhattan"
# dist_func = "chi_square"
# dist_func = "euclidean"
class1_label, class2_label = get_class_labels(label)
run_task3(feature_extraction_model, dimension_reduction_model,
class1_label, k_value)
result1 = run_task4(feature_extraction_model, dimension_reduction_model,
query_folder, image_name, dist_func, class1_label,
k_value, m_value)
class1_score = result1[0]['score']
# print(class1_score)
run_task3(feature_extraction_model, dimension_reduction_model,
class2_label, k_value)
result2 = run_task4(feature_extraction_model, dimension_reduction_model,
query_folder, image_name, dist_func, class2_label,
k_value, m_value)
class2_score = result2[0]['score']
# print(class2_score)
final_label = class1_label if class1_score > class2_score else class2_label
print(global_constants.LINE_SEPARATOR)
print("{} !!!".format(final_label.upper()))
print(global_constants.LINE_SEPARATOR)
def main():
"""Main function for the script"""
number_of_tasks = 6
print("Welcome to Phase 3!")
choice = get_task_number()
if choice == "0":
module_name = "phase3.load_csv"
elif choice == "1":
module_name = "phase3.task1"
elif choice == "2":
module_name = "p3task2"
elif choice == "3":
module_name = "phase3.task3"
elif choice == "5a":
l = get_input_k("L")
k = get_input_k("K")
comb = get_bool("Combine Models")
task5a(l, k, comb)
sys.exit(0)
elif choice == "5b":
query = get_input_image("Hands")
top = get_input_k("K")
comb = get_bool("Combine Models")
task5b(query, top, visualize=True, combine_models=comb)
sys.exit(0)
elif choice == "6a":
module_name = "task6_svm"
elif choice == "6b":
module_name = "task6_dt"
elif choice == "6c":
module_name = "task6_ppr"
elif choice == "4c":
module_name = "phase3.task4_ppr"
elif choice == "4b":
module_name = "task4_dt"
elif choice == "4a":
module_name = "task4_svm"
else:
module_name = "task{}".format(choice)
module = importlib.import_module('{0}'.format(module_name))
module.main()
def get_input_data():
"""Get Inputs from User"""
number_of_tasks = 2
choice = get_task_number(number_of_tasks)
if choice == 1:
folder = get_input_folder()
image = get_input_image(folder)
model = get_input_feature_extractor_model()
feature_extractor = ExtractFeatures(folder, model)
result = feature_extractor.execute(image)
# if model == "LBP":
# result = [float(x) for x in result.strip('[]').split(",")]
print(numpy.array(result))
elif choice == 2:
folder = get_input_folder()
model = get_input_feature_extractor_model()
feature_extractor = ExtractFeatures(folder, model)
feature_extractor.execute()
elif choice == 3:
pass
def main():
query = get_input_image("Hands")
no_images = get_input_k("t")
get_probability_revelance_feedback(query, no_images)
def main():
query_image = get_input_image("Hands")
no_images = get_input_k("t")
# query_image = get_input_image()
similar_images, img_vectors, query_image_vector = get_LSH_results(query_image, no_images)
relevancefeedback.relevance_fdbk("PPR", query_image,similar_images,img_vectors, query_image_vector)