keras: Cannot weight classes when using multiple outputs

I have a model with 2 categorical outputs.
The first output layer can predict 2 classes: [0, 1]
and the second output layer can predict 3 classes: [0, 1, 2].

Due to classes imbalance i would like to use class weights for each output
but whenever i add the class weights, the script fails with an error. The script runs normally if the weights aren’t added.

I’ve made a minimal example that reproduces the issue:

from tensorflow.python.keras.models import Model
from tensorflow.python.keras.layers import Input, Dense
from tensorflow.python.data import Dataset
import tensorflow as tf
import numpy as np


def preprocess_sample(features, labels):
    label1, label2 = labels
    label1 = tf.one_hot(label1, 2)
    label2 = tf.one_hot(label2, 3)
    return features, (label1, label2)


batch_size = 32

num_samples = 1000
num_features = 10

features = np.random.rand(num_samples, num_features)
labels1 = np.random.randint(2, size=num_samples)
labels2 = np.random.randint(3, size=num_samples)

train = Dataset.from_tensor_slices((features, (labels1, labels2))).map(preprocess_sample).batch(batch_size).repeat()

# Model
inputs = Input(shape=(num_features, ))
output1 = Dense(2, activation='softmax', name='output1')(inputs)
output2 = Dense(3, activation='softmax', name='output2')(inputs)
model = Model(inputs, [output1, output2])

model.compile(loss='categorical_crossentropy', optimizer='adam')
class_weights = {'output1': {0: 1, 1: 10}, 'output2': {0: 5, 1: 1, 2: 10}}
model.fit(train, epochs=10, steps_per_epoch=num_samples // batch_size,
         #  class_weight=class_weights
          )

This scripts runs successfully.
But when you add the class weights by uncommenting the line # class_weight=class_weights
than the script crashes with the following error:

Traceback (most recent call last):
  File "test.py", line 35, in <module>
    class_weight=class_weights
  File "venv/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py", line 1536, in fit
    validation_split=validation_split)
  File "venv/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py", line 992, in _standardize_user_data
    class_weight, batch_size)
  File "venv/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py", line 1165, in _standardize_weights
    feed_sample_weight_modes)
  File "venv/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py", line 1164, in <listcomp>
    for (ref, sw, cw, mode) in zip(y, sample_weights, class_weights,
  File "venv/lib/python3.6/site-packages/tensorflow/python/keras/engine/training_utils.py", line 717, in standardize_weights
    y_classes = np.argmax(y, axis=1)
  File "venv/lib/python3.6/site-packages/numpy/core/fromnumeric.py", line 1004, in argmax
    return _wrapfunc(a, 'argmax', axis=axis, out=out)
  File "venv/lib/python3.6/site-packages/numpy/core/fromnumeric.py", line 62, in _wrapfunc
    return _wrapit(obj, method, *args, **kwds)
  File "venv/lib/python3.6/site-packages/numpy/core/fromnumeric.py", line 42, in _wrapit
    result = getattr(asarray(obj), method)(*args, **kwds)
numpy.core._internal.AxisError: axis 1 is out of bounds for array of dimension 1

About this issue

Original URL
State: closed
Created 6 years ago
Reactions: 19
Comments: 21 (1 by maintainers)

Most upvoted comments

has anyone found a solution / workaround for this in tf 2.4+ ?

ghost on Oct 5, 2021

i am using a dictionary of dictionaries for class_weights

eyaler on Dec 2, 2019

Did anyone manage to get this to work with TF>2.1? Struggling with the same issue working with TF 2.4.1 currently.

niki-j on Apr 6, 2021

When I install tensorflow 2.1.0 it still works.

saksham189 on Jul 30, 2020

@eyaler Is using a dictionary of dictionaries for class_weight in a multi output tf.keras model actually working for you? If this works, could you please paste a snippet? Thanks.

@mmilosav Did you find a solution for this in tf.keras?

I am finding that it doesn’t accept a dictionary in TF 2.2.

Thanks

shervin64 on May 13, 2020

I am having the same problem, but i get some other error:

ValueError: Expected class_weight to be a dict with keys from 0 to one less than the number of classes, found {'output1': {0: 1.0, 1: 1.0, 2: 1.0, 3: 1.0, 4: 1.0, 5: 1.0, 6: 1.0, 7: 1.0}, 'output2': {0: 1.684420772303595, 1: 0.7110736368746486}}

this is my model.fit() code:

class_weights = {'output1': {0: 1.0, 1: 1.0, 2: 1.0, 3: 1.0, 4: 1.0, 5: 1.0, 6: 1.0, 7: 1.0}, 'output2': {0: 1.684420772303595, 1: 0.7110736368746486}} model.fit(train_x, [train_age_y, train_gender_y], epochs=20, batch_size=32, validation_data=(test_x, [test_age_y, test_gender_y]), class_weight=class_weights, verbose=1)

I Have defined the model like this:

` def define_model(): img_input = Input(shape=(100, 100, 3))

layer1 = Conv2D(32, (3,3), padding='same', activation='relu')(img_input)
layer1 = BatchNormalization()(layer1)
layer1 = MaxPooling2D()(layer1)
layer1 = Dropout(0.2)(layer1)

layer2 = Conv2D(64, (3,3), padding='same', activation='relu')(layer1)
layer2 = BatchNormalization()(layer2)
layer2 = MaxPooling2D()(layer2)
layer2 = Dropout(0.2)(layer2)
    
layer3 = Conv2D(128, (3,3), padding='same', activation='relu')(layer2)
layer3 = BatchNormalization()(layer3)
layer3 = MaxPooling2D()(layer3)
layer3 = Dropout(0.3)(layer3)
    
layer4 = Conv2D(256, (3,3), padding='same', activation='relu')(layer3)
layer4 = BatchNormalization()(layer4)
layer4 = MaxPooling2D()(layer4)
layer4 = Dropout(0.3)(layer4)

flatten_gender = Flatten()(layer4)
    
layer5 = Conv2D(512, (3,3), padding='same', activation='relu')(layer4)
layer5 = BatchNormalization()(layer5)
layer5 = MaxPooling2D()(layer5)
layer5 = Dropout(0.3)(layer5)
    
layer6 = Conv2D(1024, (3,3), padding='same', activation='relu')(layer5)
layer6 = BatchNormalization()(layer6)
layer6 = MaxPooling2D()(layer6)
layer6 = Dropout(0.3)(layer6)

flatten_age = Flatten()(layer6)

output1 = Dense(8, name='output1', activation='softmax')(flatten_age)
output2 = Dense(1, name='output2', activation='sigmoid')(flatten_gender)

model = Model(inputs=img_input, outputs=[output1, output2])
model.compile(loss=['sparse_categorical_crossentropy', 'binary_crossentropy'], optimizer='adam')

print(model.summary())
return model

model = define_model()` Can someone help me

thisisdhruvagarwal on Jul 24, 2020

facing this issue with keras 2.8 and tf 2.8

ValueError: `class_weight` is only supported for Models with a single output.

alxbar75 on May 12, 2022

stiff facing this issue in tf 2.4+

abdulbasitds on Feb 1, 2022

@mmilosav working for me, however i am using keras proper (2.2.4 or 2.2.5) and not tf.keras

model.fit_generator(… class_weights={‘name’: {0: w1, 1: w2}}) where ‘name’ is also used for the relevant output layer and its loss (not sure which is important) in a multi output model

eyaler on Apr 5, 2020

Still an issue in 2.9

carlthome on Aug 24, 2022

I experience the same issue wth tensorflow 2.2.0 and 2.3.0 with a (non sequential) Keras model. I compile the model like this:

model = keras.models.Model( inputs=[inp1, inp2, inp3], outputs=[output] )

where output is: output = keras.layers.Dense(1, activation="sigmoid", name="y")(x)

It works perfectly with tf 2.0.1.

I use official python3 docker containers in all cases.

noise-field on Aug 4, 2020