python - python3 TensorFlow Check failed: new_num_elements == NumElements() (96 vs. 60000)

Collectives™ on Stack Overflow

Find centralized, trusted content and collaborate around the technologies you use most.
Learn more about Collectives
Teams
Q&A for work
Connect and share knowledge within a single location that is structured and easy to search.
Learn more about Teams
I'm coding up a basic Neural Network using TensorFlow(1.12.0) in Python(3.6.7).
Everything seems to work fine individually but I'm getting this error message when I run the model() .
F ./tensorflow/core/framework/tensor.h:663] Check failed: new_num_elements == NumElements() (96 vs. 60000)
Aborted
I haven't used the number 96 anywhere in my code as far as I can tell.
I've provided my code below:
model.py:
import numpy as np
import tensorflow as tf
from preprocessing import getDataset
from parameter import initializeParameters
from forward import forwardPropagation
from cost import computeCost
def model(numberOfIterations = 10000):
        Architecture:
                                        W1, b1                       W2, b2                      W3, b3                      W4, b4
        X(numberOfFeatures, numberOfImages) ---> L1(25, numberOfImages) ---> L2(25, numberOfImages) ---> L3(10, numberOfImages) ---> H(10,numberOFImages)
                                            relu                        relu                        relu                        sigmoid
        W1(25, numberOfFeatures)
        b1(25,1)
        W2(25, 25)
        b2(25, 1)
        W3(10, 25)
        b3(10, 1)
        W4(10, 10)
        b4(10, 1)
    # get all dataset information
    data = getDataset()
    (numberOfFeatures, numberOfImages) = data["X_train"].get_shape()
    # initalize parameters whilst breaking symmetry
    parameters = initializeParameters(numberOfFeatures, numberOfImages)
    # construct forward propagation graph
    (hypothesis, Z4) = forwardPropagation(data["X_train"], parameters)
    # define cost tensor
    cost = computeCost(Z4, data["Y_train"])
    # create optimizer
    optimizer = tf.train.AdamOptimizer().minimize(cost)
    # define session object
    with tf.Session() as sess:
        init = tf.global_variables_initializer()
        sess.run(init)
        # train network
        for iteration in range(numberOfIterations):
            sess.run(optimizer)
            if iteration % 10 == 0:
                print("After iteration", iteration, "cost =", sess.run(cost))
model(numberOfIterations = 50)
preprocessing.py:
import numpy as np
import tensorflow as tf
#import matplotlib.pyplot as plt
def getDataset(datasetInfo = True, exampleImage = False):
    (x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()
    numberOfImages_train = np.shape(x_train)[0]
    numberOfImages_test  = np.shape(x_test)[0]
    imageDimension = (np.shape(x_train)[1], np.shape(x_train)[2])
    if datasetInfo:
        print("Number of training data images:", numberOfImages_train)
        print("Number of testing data images:", numberOfImages_test)
        print("Image dimensions:", imageDimension)
#    if exampleImage:
#        randIndex = np.random.randint(0, numberOfImages)
#        plt.imshow(X_mat[:,:,:, randIndex])
    data = {
        "X_train": tf.convert_to_tensor(np.reshape(x_train, (numberOfImages_train, -1)).T, dtype = tf.float64),
       "Y_train": tf.convert_to_tensor(y_train.T),
        "X_test": tf.convert_to_tensor(np.reshape(x_test, (numberOfImages_test, -1)).T, dtype = tf.float64),
        "Y_test": tf.convert_to_tensor(y_test.T)
    return data
parameter.py:
import numpy as np
import tensorflow as tf
def initializeParameters(numberOfFeatures, numberOfImages):
    W1 = tf.Variable(np.random.randn(25, numberOfFeatures) )
    b1 = tf.Variable(np.zeros((25,1)))
    W2 = tf.Variable(np.random.randn(25, 25))
    b2 = tf.Variable(np.zeros((25,1)))
    W3 = tf.Variable(np.random.randn(10, 25))
    b3 = tf.Variable(np.zeros((10,1)))
    W4 = tf.Variable(np.random.randn(10, 10))
    b4 = tf.Variable(np.zeros((10,1)))
    parameters = {
        "W1": W1,
        "b1": b1,
        "W2": W2,
        "b2": b2,
        "W3": W3,
        "b3": b3,
        "W4": W4,
        "b4": b4
    return parameters
forward.py:
import numpy as np
import tensorflow as tf
def forwardPropagation(X, parameters):
    Z1 = tf.add( tf.matmul(parameters["W1"], X) , parameters["b1"])
    A1 = tf.nn.relu(Z1)
    Z2 = tf.add( tf.matmul(parameters["W2"],A1) , parameters["b2"])
    A2 = tf.nn.relu(Z2)
    Z3 = tf.add( tf.matmul(parameters["W3"],A2) , parameters["b3"])
    A3 = tf.nn.relu(Z3)
    Z4 = tf.add( tf.matmul(parameters["W4"],A3) , parameters["b4"])
    hypothesis = tf.sigmoid(Z4)
    return (hypothesis, Z4)
cost.py:
import numpy as np
import tensorflow as tf
def computeCost(hypothesis, labels):
    onehotlabels = tf.cast(tf.one_hot(labels, depth = 10, axis = 0), tf.float64)
    losses = tf.nn.sigmoid_cross_entropy_with_logits(labels = onehotlabels, logits = hypothesis)
    cost = tf.reduce_mean(losses)
    return cost
Full output:
Number of training data images: 60000
Number of testing data images: 10000
Image dimensions: (28, 28)
2018-12-03 12:35:50.912208: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2018-12-03 12:35:51.221523: F ./tensorflow/core/framework/tensor.h:663] Check failed: new_num_elements == NumElements() (96 vs. 60000)
Aborted
You are feeding  batch size of 60,000, which is very huge. I reproduced the error  and the error goes away when I limit number training images to 255. But more generally you can feed small batch at at time. Tensorflow has very rich classes and method to handle such kind of issues.
Make the following changes to your methods.
Return just numpy arrays from getDataset() method
def getDataset(datasetInfo = True, exampleImage = False):
    # body of the method
    data = {
        "X_train": np.reshape(x_train, (numberOfImages_train, -1)).astype(np.float64),
       "Y_train": y_train,
        "X_test": np.reshape(x_test, (numberOfImages_test, -1)).astype(np.float64),
        "Y_test": y_test
    return data
Inside model method make the following changes
# Just to match the shape of X_train returned from getDataset method
(numberOfImages , numberOfFeatures ) = data["X_train"].shape
# Create iterator that gives you batch size of sample for at each batch for both training and test cases
train_data =  tf.data.Dataset.from_tensor_slices((data["X_train"],data["Y_train"])).repeat().batch(BATCH_SIZE)
test_data =  tf.data.Dataset.from_tensor_slices((data["X_test"],data["Y_test"])).repeat().batch(BATCH_SIZE)
train_itr = train_data.make_one_shot_iterator()
x_train, y_train = train_itr.get_next()
x_train = tf.transpose(x_train)
Now feed these x_train and y_train for to build the network.
# initalize parameters whilst breaking symmetry
parameters = initializeParameters(numberOfFeatures, numberOfImages)
# construct forward propagation graph
(hypothesis, Z4) = forwardPropagation(x_train, parameters)
# define cost tensor
cost = computeCost(Z4, y_train)
I've provided the full code below for both getDataset and model methods
def getDataset(datasetInfo = True, exampleImage = False):
    (x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()
    numberOfImages_train = np.shape(x_train)[0]
    numberOfImages_test  = np.shape(x_test)[0]
    imageDimension = (np.shape(x_train)[1], np.shape(x_train)[2])
    if datasetInfo:
        print("Number of training data images:", numberOfImages_train)
        print("Number of testing data images:", numberOfImages_test)
        print("Image dimensions:", imageDimension)
#    if exampleImage:
#        randIndex = np.random.randint(0, numberOfImages)
#        plt.imshow(X_mat[:,:,:, randIndex])
    data = {
        "X_train": np.reshape(x_train, (numberOfImages_train, -1)).astype(np.float64),
       "Y_train": y_train,
        "X_test": np.reshape(x_test, (numberOfImages_test, -1)).astype(np.float64),
        "Y_test": y_test
    return data
def model(numberOfIterations = 10000, BATCH_SIZE=32):
        Architecture:
                                        W1, b1                       W2, b2                      W3, b3                      W4, b4
        X(numberOfFeatures, numberOfImages) ---> L1(25, numberOfImages) ---> L2(25, numberOfImages) ---> L3(10, numberOfImages) ---> H(10,numberOFImages)
                                            relu                        relu                        relu                        sigmoid
        W1(25, numberOfFeatures)
        b1(25,1)
        W2(25, 25)
        b2(25, 1)
        W3(10, 25)
        b3(10, 1)
        W4(10, 10)
        b4(10, 1)
    # get all dataset information
    data = getDataset()
    (numberOfImages , numberOfFeatures ) = data["X_train"].shape
    train_data =  tf.data.Dataset.from_tensor_slices((data["X_train"],data["Y_train"])).repeat().batch(BATCH_SIZE)
    test_data =  tf.data.Dataset.from_tensor_slices((data["X_test"],data["Y_test"])).repeat().batch(BATCH_SIZE)
    train_itr = train_data.make_one_shot_iterator()
    x_train, y_train = train_itr.get_next()
    x_train = tf.transpose(x_train)
    # initalize parameters whilst breaking symmetry
    parameters = initializeParameters(numberOfFeatures, numberOfImages)
    # construct forward propagation graph
    (hypothesis, Z4) = forwardPropagation(x_train, parameters)
    # define cost tensor
    cost = computeCost(Z4, y_train)
    # create optimizer
    optimizer = tf.train.AdamOptimizer().minimize(cost)
    # define session object
    with tf.Session() as sess:
        init = tf.global_variables_initializer()
        sess.run(init)
        # train network
        for iteration in range(numberOfIterations):
            sess.run(optimizer)
            if iteration % 10 == 0:
                print("After iteration", iteration, "cost =", sess.run(cost))
model(numberOfIterations = 50)
                I'm still getting some dimension mismatch errors. I don't quite understand what's happening in these lines: ______________________________  train_data =  tf.data.Dataset.from_tensor_slices((data["X_train"],data["Y_train"])).repeat().batch(BATCH_SIZE) test_data = tf.data.Dataset.from_tensor_slices((data["X_test"],data["Y_test"])).repeat().batch(BATCH_SIZE)  train_itr = train_data.make_one_shot_iterator() x_train, y_train = train_itr.get_next() x_train = tf.transpose(x_train) ________________________ Please explain
– Anirudh Ajith
                Dec 3, 2018 at 13:44
        Thanks for contributing an answer to Stack Overflow!
Please be sure to answer the question. Provide details and share your research!
But avoid …
Asking for help, clarification, or responding to other answers.
Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.