I am working on an image segmentation problem but I faced this issue. I am trying to create encode labels with multi diminutional array but it need to be flatten, encode and reshape
--------------------------------------------------------------------------- ValueError Traceback (most recent call last)
/var/folders/5m/kbzbl3b92tz0jp0jsmk20kp00000gn/T/ipykernel_83886/1032773058.py in <module>
3 from sklearn.preprocessing import LabelEncoder
4 labelencoder = LabelEncoder()
5 n, h, w = train_masks.shape
6 train_masks_reshaped = train_masks.reshape(-1,1)
7 train_masks_reshaped_encoded = labelencoder.fit_transform(train_masks_reshaped)
ValueError: not enough values to unpack (expected 3, got 1)
Here is the piece of code
from keras.utils import normalize
import glob
import numpy as np
SIZE_X = 128
SIZE_Y = 128
n_classes=4
#Capture training image info as a list
train_images = []
for directory_path in glob.glob("128_patches/images/"):
for img_path in glob.glob(os.path.join(directory_path, "*.tif")):
img = cv2.imread(img_path, 0)
#img = cv2.resize(img, (SIZE_Y, SIZE_X))
train_images.append(img)
#Convert list to array for machine learning processing
train_images = np.array(train_images)
#Capture mask/label info as a list
train_masks = []
for directory_path in glob.glob("128_patches/masks/"):
for mask_path in glob.glob(os.path.join(directory_path, "*.tif")):
mask = cv2.imread(mask_path, 0)
#mask = cv2.resize(mask, (SIZE_Y, SIZE_X), interpolation = cv2.INTER_NEAREST) #Otherwise ground truth changes due to interpolation
train_masks.append(mask)
#Convert list to array for machine learning processing
train_masks = np.array(train_masks)
#-----------------------------------------
#Encode labels...
from sklearn.preprocessing import LabelEncoder
labelencoder = LabelEncoder()
n, h, w = train_masks.shape
train_masks_reshaped = train_masks.reshape(-1,1)
train_masks_reshaped_encoded = labelencoder.fit_transform(train_masks_reshaped)
train_masks_encoded_original_shape = train_masks_reshaped_encoded.reshape(n, h, w)
np.unique(train_masks_encoded_original_shape)
#-----------------------------------------
train_images = np.expand_dims(train_images, axis=3)
train_images = normalize(train_images, axis=1)
train_masks_input = np.expand_dims(train_masks_encoded_original_shape, axis=3)
#Create a subset of data for quick testing
#Picking 10% for testing and remaining for training
from sklearn.model_selection import train_test_split
X1, X_test, y1, y_test = train_test_split(train_images, train_masks_input, test_size = 0.10, random_state = 0)
#Further split training data t a smaller subset for quick testing of models
X_train, X_do_not_use, y_train, y_do_not_use = train_test_split(X1, y1, test_size = 0.2, random_state = 0)
print("Class values in the dataset are ... ", np.unique(y_train)) # 0 is the background/few unlabeled
from keras.utils import to_categorical
train_masks_cat = to_categorical(y_train, num_classes=n_classes)
y_train_cat = train_masks_cat.reshape((y_train.shape[0], y_train.shape[1], y_train.shape[2], n_classes))
test_masks_cat = to_categorical(y_test, num_classes=n_classes)
y_test_cat = test_masks_cat.reshape((y_test.shape[0], y_test.shape[1], y_test.shape[2], n_classes))
#-----------------------------------------
from sklearn.utils import class_weight
class_weights = class_weight.compute_class_weight('balanced',
np.unique(train_masks_reshaped_encoded),
train_masks_reshaped_encoded)
print("Class weights are...:", class_weights)
This is the piece of code trying to encode labels
#Encode labels...
from sklearn.preprocessing import LabelEncoder
labelencoder = LabelEncoder()
n, h, w = train_masks.shape
train_masks_reshaped = train_masks.reshape(-1,1)
train_masks_reshaped_encoded = labelencoder.fit_transform(train_masks_reshaped)
train_masks_encoded_original_shape = train_masks_reshaped_encoded.reshape(n, h, w)
np.unique(train_masks_encoded_original_shape)
Can you please help me fix this issue? Thank you!
