[FIXED] Python ConvNet Image Classifier - "ValueError" when fitting a model for a binary image classification

Issue

I am very new to deep learning and TensorFlow/Keras, so I'm having trouble understanding why I am throwing an error when trying to fit a model to classify images as either "dogs" or "cats." (image database can be found here: https://www.microsoft.com/en-us/download/details.aspx?id=54765). The model was written, saved, and opened in a separate module as I am learning and following a YouTube tutorial (https://www.youtube.com/watch?v=WvoLTXIjBYU). The first block of code involved creating and saving the model (with pickle), and the second block of code is the portion training the actual convolutional networks.

The image database was downloaded, saved to a file directory, and a model was written to train the classifier. The code is below:

import numpy as np
import matplotlib.pyplot as plt
import os
import cv2

DATADIR = "Pictures\\kagglecatsanddogs_3367a\\PetImages" 
#Workspace directory changed for posting
CATEGORIES = ["Dog", "Cat"]

#Iterate between all photos of dogs and cats
for category in CATEGORIES:
    path = os.path.join(DATADIR, category) #path to cats or dogs dir
    for img in os.listdir(path):
        img_array = cv2.imread(os.path.join(path, img), cv2.IMREAD_GRAYSCALE) #Converts to grayscale, does not need color in this specific instance)
        plt.imshow(img_array, cmap = "gray")
        break
    break

#Print image dimensions
print(img_array.shape)

#All the images are different-shaped photos, so they must be normalized
#Everything must be made the same shape
#Decide on the image size you want to go with
IMG_SIZE = 180
new_array = cv2.resize(img_array, (IMG_SIZE, IMG_SIZE))

training_data = []

def create_training_data(): #With goal of iterating through everything and building the dataset
    for category in CATEGORIES:
        path = os.path.join(DATADIR, category) #path to cats or dogs dir
        class_num = CATEGORIES.index(category)
        for img in os.listdir(path):
            try:
                img_array = cv2.imread(os.path.join(path, img), cv2.IMREAD_GRAYSCALE) #Converts to grayscale, does not need color in this specific instance)
                new_array = cv2.resize(img_array, (IMG_SIZE, IMG_SIZE))
                training_data.append([new_array, class_num])
            except Exception as e:
                pass

create_training_data()

print(len(training_data))

#Shuffle the data
import random
random.shuffle(training_data)

for sample in training_data[:10]:
    print(sample[1])

#Packs data into variables we will use
x = []
y = []

for features, label in training_data:
    x.append(features)
    y.append(label)
x = np.array(x).reshape(-1, IMG_SIZE, IMG_SIZE, 1)


#Model was saved with pickle
import pickle
pickle_out = open("x.pickle", "wb")
pickle.dump(x, pickle_out)
pickle_out.close()

pickle_out = open("y.pickle", "wb")
pickle.dump(y, pickle_out)
pickle_out.close()

The code was then opened in another Jupyter Notebook file and used to build the CNN:

#Import necessary packages
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Activation, Flatten, Conv2D, MaxPooling2D
import pickle

#Load models generated in previous tutorial
x = pickle.load(open("x.pickle", "rb"))
y = pickle.load(open("y.pickle", "rb"))

#Normalize the data
#255 is used due to RGB imagery
x = x/255

#Model building: First layer
model = Sequential()
#Convolutional network
model.add(Conv2D(64, (3,3), input_shape = x.shape[1:]))
model.add(Activation("relu"))
#Pooling
model.add(MaxPooling2D(pool_size = (2,2)))

#Model building: Second layer
#Convolutional network
model.add(Conv2D(64, (3,3), input_shape = x.shape[1:]))
model.add(Activation("relu"))
#Pooling
model.add(MaxPooling2D(pool_size = (2,2)))

#Final output layer
model.add(Flatten())
model.add(Dense(64))

model.add(Dense(1))
model.add(Activation('sigmoid'))

model.compile(loss= "binary_crossentropy",
             optimizer = "adam",
             metrics = ['accuracy'])

model.fit(x, y, batch_size = 32, epochs = 3, validation_split = 0.1)

The exception is then thrown:

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-6-bb5f154147cd> in <module>
     39              metrics = ['accuracy'])
     40 
---> 41 model.fit(x, y, batch_size = 32, epochs = 3, validation_split = 0.1)

~\AppData\Roaming\Python\Python36\site-packages\tensorflow\python\keras\engine\training.py in _method_wrapper(self, *args, **kwargs)
    106   def _method_wrapper(self, *args, **kwargs):
    107     if not self._in_multi_worker_mode():  # pylint: disable=protected-access
--> 108       return method(self, *args, **kwargs)
    109 
    110     # Running inside `run_distribute_coordinator` already.

~\AppData\Roaming\Python\Python36\site-packages\tensorflow\python\keras\engine\training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)
   1038       (x, y, sample_weight), validation_data = (
   1039           data_adapter.train_validation_split(
-> 1040               (x, y, sample_weight), validation_split=validation_split))
   1041 
   1042     if validation_data:

~\AppData\Roaming\Python\Python36\site-packages\tensorflow\python\keras\engine\data_adapter.py in train_validation_split(arrays, validation_split)
   1374     raise ValueError(
   1375         "`validation_split` is only supported for Tensors or NumPy "
-> 1376         "arrays, found following types in the input: {}".format(unsplitable))
   1377 
   1378   if all(t is None for t in flat_arrays):

ValueError: `validation_split` is only supported for Tensors or NumPy arrays, found following types in the input: [<class 'int'>, <class 'int'>, <class 'int'>, <class 'int'>, <class 'int'>, <class 'int'>, <class 'int'>, <class 'int'>, <class 'int'>, <class 'int'>, <class 'int'>, <class 'int'>, <class 'int'>, <class 'int'>

How can I resolve this error? It appears that the error is in the model.fit(x, y, batch_size = 32, epochs = 3, validation_split = 0.1) line, because when I run the code without this line, no exceptions are thrown. Thanks!

Solution

You should do transformation proccess for numpy array of y, not just X.

X = []
y = []

for features,label in training_data:
    X.append(features)
    y.append(label)

print(X[0].reshape(-1, IMG_SIZE, IMG_SIZE, 1))

X = np.array(X).reshape(-1, IMG_SIZE, IMG_SIZE, 1)
y = np.array(y)

Answered By - Gizem Uzun