ValueError in categorical_crossentropy loss shape

Question

I am building a multi-class CNN model but I am unable to compile the model due to loss shape error.

Both output layer and labels should have correct shapes; labels being (m, 1, 3) and final dense layer containing 3 perceptions with softmax activation
loss='categorical_crossentropy'

import numpy as np
import pandas as pd
from preprocess import DataLoader

import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Flatten, Conv3D, Dropout, MaxPooling3D
from tensorflow.keras.metrics import categorical_crossentropy
from tensorflow.keras import optimizers

target_width = 160
target_height = 192
target_depth = 192

num_classes = 3
batch_size = 4

data_loader = DataLoader(target_shape=(target_width, target_height, target_depth))
train, test = data_loader.Get_Data_List()

print("Train size: " + str(len(train)))
print("Test size: " + str(len(test)))

def custom_one_hot(labels):
  label_dict = {"stableAD":np.array([0,0,1]),
              "stableMCI":np.array([0,1,0]),
              "stableNL":np.array([1,0,0])}
  encoded_labels = []
  for label in labels:
    encoded_labels.append(label_dict[label].reshape(1,3))
  return np.asarray(encoded_labels)

def additional_data_prep(train, test):
  # Extract data from tuples
  train_labels, train_data = zip(*train)
  test_labels, test_data = zip(*test)
  X_train = np.asarray(train_data)
  X_test = np.asarray(test_data)
  y_train = custom_one_hot(train_labels)
  y_test = custom_one_hot(test_labels)
  return X_train, y_train, X_test, y_test

X, y, X_test, y_test = additional_data_prep(train, test)

X = np.expand_dims(X, axis=-1).reshape((X.shape[0],target_width,target_height,target_depth,1))
X_test = np.expand_dims(X_test, axis=-1).reshape((X_test.shape[0],target_width,target_height,target_depth,1))

model = Sequential()
model.add(Conv3D(24, kernel_size=(13, 11, 11), activation='relu', input_shape=(target_width,target_height,target_depth,1), padding='same', strides=4))
model.add(MaxPooling3D(pool_size=(3, 3, 3), strides=2))
model.add(Dropout(0.1))
model.add(Conv3D(48, kernel_size=(6, 5, 5), activation='relu', padding='same'))
model.add(MaxPooling3D(pool_size=(3, 3, 3), strides=2))
model.add(Dropout(0.1))
model.add(Conv3D(24, kernel_size=(4, 3, 3), activation='relu'))
model.add(MaxPooling3D(pool_size=(3, 3, 3), strides=2))
model.add(Dropout(0.1))
model.add(Conv3D(8, kernel_size=(2, 2, 2), activation='relu'))
model.add(MaxPooling3D(pool_size=(1, 1, 1), strides=2))
model.add(Dropout(0.1))
model.add(Flatten())
model.add(Dense(num_classes, activation='softmax'))

model.compile(loss='categorical_crossentropy',
              optimizer=optimizers.Adam(learning_rate=0.0015),
              metrics=['accuracy','categorical_crossentropy'])

model.fit(X, y, batch_size=batch_size, epochs=10, verbose=2, use_multiprocessing=True)  

model.evaluate(X_test, y_test, verbose=2, use_multiprocessing=True)

Results in this error message:

Traceback (most recent call last):
  File "train.py", line 70, in <module>
    model.fit(X, y, batch_size=batch_size, epochs=10, verbose=2, use_multiprocessing=True)
  File "/home/554282/.local/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training.py", line 819, in fit
    use_multiprocessing=use_multiprocessing)
  File "/home/554282/.local/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training_v2.py", line 235, in fit
    use_multiprocessing=use_multiprocessing)
  File "/home/554282/.local/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training_v2.py", line 593, in _process_training_inputs
    use_multiprocessing=use_multiprocessing)
  File "/home/554282/.local/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training_v2.py", line 646, in _process_inputs
    x, y, sample_weight=sample_weights)
  File "/home/554282/.local/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training.py", line 2383, in _standardize_user_data
    batch_size=batch_size)
  File "/home/554282/.local/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training.py", line 2489, in _standardize_tensors
    y, self._feed_loss_fns, feed_output_shapes)
  File "/home/554282/.local/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training_utils.py", line 810, in check_loss_and_target_compatibility
    ' while using as loss `' + loss_name + '`. '
ValueError: A target array with shape (8, 1, 3) was passed for an output of shape (None, 3) while using as loss `categorical_crossentropy`. This loss expects targets to have the same shape as the output.

vineet gundecha vineet gundecha · Accepted Answer · 2020-02-08T18:02:37

The custom_one_hot function returns a [M, 1, 3] array. You should reshape that to [M, 3] since the output of the CNN is [M, 3]. M here is the batch size.

ValueError in categorical_crossentropy loss shape

1 Answers