CODEWITHSUNDEEP
pythonkerasneural-networkmnist
Andrey Glazyrin
Andrey Glazyrin

Reputation: 29

My keras neural network does not predict handwritten numbers

I trained a feedforward neural network in Keras module, but there are some problems with it. The problem is the incorrect prediction of images with self-written digits. 

(X_train, y_train), (X_test, y_test) = mnist.load_data()
RESHAPED = 784
X_train = X_train.reshape(60000, RESHAPED)
X_test = X_test.reshape(10000, RESHAPED)
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
X_train /= 255
X_test /= 255
Y_train = np_utils.to_categorical(y_train, NB_CLASSES)
Y_test = np_utils.to_categorical(y_test, NB_CLASSES)
model = Sequential()
model.add(Dense(N_HIDDEN, input_shape=(RESHAPED,)))
model.add(Activation('relu'))
model.add(Dropout(DROPOUT))
model.add(Dense(N_HIDDEN))
model.add(Activation('relu'))
model.add(Dropout(DROPOUT))
model.add(Dense(NB_CLASSES))
model.add(Activation('softmax'))
model.summary()
model.compile(loss='categorical_crossentropy',
          optimizer=OPTIMIZER,
          metrics=['accuracy'])

history = model.fit(X_train, Y_train,
                batch_size=BATCH_SIZE, epochs=NB_EPOCH,
                verbose=VERBOSE, validation_split=VALIDATION_SPLIT)
score = model.evaluate(X_test, Y_test, verbose=VERBOSE) 
//output
....
Epoch 20/20
48000/48000 [==============================] - 2s 49us/step - loss: 0.0713 - 
acc: 0.9795 - val_loss: 0.1004 - val_acc: 0.9782
10000/10000 [==============================] - 1s 52us/step
Test score: 0.09572517980986121 
Test accuracy: 0.9781

Next, I upload my image, of dimension 28x28, which was self-written, for example - 2, and executed this script:

img_array = imageio.imread('2.png', as_gray=True)
predictions=model.predict(img_array.reshape(1,784))
print (np.argmax(predictions))
//output for example 3, but I expect - 2

I tried other pictures with different numbers, which also gave wrong predictions. What is wrong? Model shows-Test accuracy: 0.9781. Help me please)))

Upvotes: 0

Views: 442

Answers (2)

Mehdi Bahra
Mehdi Bahra

Reputation: 319

This is a common problem of data mismatch , in order to have a prefect accuracy on your own images , you need to make some preprocessing before , if you noticed one thing in the mnist dataset all images are white in black background , this is one of the modification you should make to your own image , for more information check this awesome medium article :

https://medium.com/@o.kroeger/tensorflow-mnist-and-your-own-handwritten-digits-4d1cd32bbab4

Upvotes: 0

tifi90
tifi90

Reputation: 413

You are using the MNIST Dataset. This set was originally created for the american post office. You'll have to deal with regional handwriting variation so make sure you have written american numbers.

On the other hand errors are normal. Make a bigger set of handwritten digits and make some tests.

Upvotes: 0

Related Questions