def normalized_data(self, train_size, test_size, val_size):
"""
Normalize the input data
Separate them into train, test and validation dataset
:param train_size:
:param test_size:
:param val_size:
:return:
"""
X_train, Y_train, X_test, Y_test = getDataset(False)
X_train = getCIFAR_as_32Pixels_Image(X_train)
X_test = getCIFAR_as_32Pixels_Image(X_test)
mask = range(train_size, train_size + val_size)
X_val = X_train[mask]
y_val = Y_train[mask]
mask = range(train_size)
X_train = X_train[mask]
y_train = Y_train[mask]
mask = range(test_size)
X_test = X_test[mask]
y_test = Y_test[mask]
mean_image = np.mean(X_train, axis=0)
X_train -= mean_image
X_val -= mean_image
X_test -= mean_image
X_train = X_train.transpose(0, 3, 1, 2).copy()
X_val = X_val.transpose(0, 3, 1, 2).copy()
X_test = X_test.transpose(0, 3, 1, 2).copy()
return X_train, y_train, X_val, y_val, X_test, y_test
def normalized_data(self, train_size, test_size, val_size):
"""
Normalize the input data
Separate them into train, test and validation dataset
:param train_size:
:param test_size:
:param val_size:
:return:
"""
X_train, Y_train, X_test, Y_test = getDataset(False)
X_train = getCIFAR_as_32Pixels_Image(X_train)
X_test = getCIFAR_as_32Pixels_Image(X_test)
mask = range(train_size, train_size + val_size)
X_val = X_train[mask]
y_val = Y_train[mask]
mask = range(train_size)
X_train = X_train[mask]
y_train = Y_train[mask]
mask = range(test_size)
X_test = X_test[mask]
y_test = Y_test[mask]
mean_image = np.mean(X_train, axis=0)
X_train -= mean_image
X_val -= mean_image
X_test -= mean_image
X_train = X_train.transpose(0, 3, 1, 2).copy()
X_val = X_val.transpose(0, 3, 1, 2).copy()
X_test = X_test.transpose(0, 3, 1, 2).copy()
return X_train, y_train, X_val, y_val, X_test, y_test
group.add_argument("-z", "--zca", help="ZCA Whitening", action="store_true")
args = parser.parse_args()
if args.algo == KNN_ARGS:
# TO-DO When KNN is implemented, move this into their preprocessing step
# TO-DO Feature Extraction takes time, save them into h5 file and load them directly
X_train, y_train, X_test, y_test = getDataset(args.loadCIFAR)
if args.zca:
print("ZCA Pre Processing Started")
X_train = zca(X_train)
X_test = zca(X_test)
print("ZCA Pre Processing Completed")
elif args.features:
# Call Feature Extraction techiniques
X_train, y_train, X_test, y_test = getDataset(args.loadCIFAR)
X_train = getCIFAR_as_32Pixels_Image(X_train)
X_test = getCIFAR_as_32Pixels_Image(X_test)
ftsObj = getFeatureFunctions(args)
X_train = ftsObj.extract_features(X_train)
X_test = ftsObj.extract_features(X_test)
print(X_test.shape)
print("Started with implementing KNN")
executeKNN(X_train, y_train, X_test, y_test)
if args.algo == SOFTMAX_ARGS:
X_train, y_train, X_test, y_test = getDataset(args.loadCIFAR)
if args.zca:
print("ZCA Pre Processing Started")
X_train = zca(X_train)
X_test = zca(X_test)
X_train = getCIFAR_as_32Pixels_Image(X_train)
X_test = getCIFAR_as_32Pixels_Image(X_test)
action="store_true")
args = parser.parse_args()
if args.algo == KNN_ARGS:
# TO-DO When KNN is implemented, move this into their preprocessing step
# TO-DO Feature Extraction takes time, save them into h5 file and load them directly
X_train, y_train, X_test, y_test = getDataset(args.loadCIFAR)
if args.zca:
print("ZCA Pre Processing Started")
X_train = zca(X_train)
X_test = zca(X_test)
print("ZCA Pre Processing Completed")
elif args.features:
# Call Feature Extraction techiniques
X_train, y_train, X_test, y_test = getDataset(args.loadCIFAR)
X_train = getCIFAR_as_32Pixels_Image(X_train)
X_test = getCIFAR_as_32Pixels_Image(X_test)
ftsObj = getFeatureFunctions(args)
X_train = ftsObj.extract_features(X_train)
X_test = ftsObj.extract_features(X_test)
print(X_test.shape)
print("Started with implementing KNN")
executeKNN(X_train, y_train, X_test, y_test)
if args.algo == SOFTMAX_ARGS:
X_train, y_train, X_test, y_test = getDataset(args.loadCIFAR)
if args.zca:
print("ZCA Pre Processing Started")
X_train = zca(X_train)
X_test = zca(X_test)
X_train = getCIFAR_as_32Pixels_Image(X_train)
X_test = getCIFAR_as_32Pixels_Image(X_test)
