CODEWITHSUNDEEP
pythontensorflowkerasconv-neural-networkimage-segmentation
DevanDev
DevanDev

Reputation: 321

Training the model gives ValueError when I add class weights

I was using multi class U-Net segmentation where I am encountering value error while training by data model. My multi class model is divided into 4 classes.

Code for training model:

from simple_multi_unet_model import multi_unet_model #Uses softmax 

from tensorflow.keras.utils import normalize
import os
import glob
import cv2
import numpy as np
from matplotlib import pyplot as plt
from sklearn.model_selection import train_test_split
import tensorflow as tf



#Resizing images, if needed
SIZE_X = 128 
SIZE_Y = 128
n_classes=4 #Number of classes for segmentation

#Capture training image info as a list
train_images = []

directory_path = '/home/Documents/Multiclass/images/'
list_of_files  = sorted( filter( os.path.isfile, glob.glob(directory_path + '*.png', recursive=True) ) )

 

for img_path in list_of_files:
        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 = []
labels_path =  '/home/Documents/Multiclass/labels/'
list_of_labels = sorted( filter( os.path.isfile, glob.glob(labels_path + '*.png', recursive=True) ) )

 
for mask_path in list_of_labels:
        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... but multi dim array so need to flatten, encode and reshape
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
x_train, X_test, y_train, y_test = train_test_split(train_images, train_masks_input, test_size = 0.10, random_state = 0)


print("Class values in the dataset are ... ", np.unique(y_train))  # 0 is the background/few unlabeled 

from tensorflow.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)


IMG_HEIGHT = x_train.shape[1]
IMG_WIDTH  = x_train.shape[2]
IMG_CHANNELS = x_train.shape[3]


def get_model():
    return multi_unet_model(n_classes=n_classes, IMG_HEIGHT=IMG_HEIGHT, IMG_WIDTH=IMG_WIDTH, IMG_CHANNELS=IMG_CHANNELS)

model = get_model()
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
model.summary()

#If starting with pre-trained weights. 
#model.load_weights('???.hdf5')

history = model.fit(x_train, y_train_cat, 
                    batch_size = 16, 
                    verbose=1, 
                    epochs=100, 
                    validation_data=(X_test, y_test_cat), 
                    class_weight=class_weights,
                    shuffle=False)

I used following approach to define class weights:

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)

The result is class_weights : 0.276965 ,13.5112 ,5.80929,6.97915.

I am encountering ValueError when I train my model. How can I possibly resolve it? Please suggest a better approach of using class weights if you think my approach is not viable.

  File "/home/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/engine/data_adapter.py", line 1185, in _configure_dataset_and_inferred_steps
    if class_weight:

ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()

Upvotes: 0

Views: 744

Answers (2)

Odewole Olusegun
Odewole Olusegun

Reputation: 66

I had the same problem but solved it with this!!!

You have to zip it together as a dictionary

Try The below code:

from sklearn.utils import class_weight

class_weights = dict(zip(np.unique(train_masks_reshaped_encoded), class_weight.compute_class_weight('balanced', np.unique(train_masks_reshaped_encoded), train_masks_reshaped_encoded)))

Upvotes: 1

R_Dax
R_Dax

Reputation: 724

My understanding of this error message is that numpy does not know whether to evaluate an array as True if any element is true, or as True only if all elements are true. Hence, a ValueError is returned because the boolean evaluation is ambiguous in this regard.

Therefore, when evaluating an array, you should use a.any() or a.all(), as indicated in the error message attached.

The error is likely to be occurring from somewhere else in your code (not shared?) when you try to evaluate the class weights in a boolean context.

Upvotes: 1

Related Questions