I am trying to use weightnorm for mnist. I get the following error.

[vishyML]

trafficstars

Traceback (most recent call last): File "C:\Users\vkswa\Downloads\weightnorm\cifar10_cnn.py", line 67, in validation_data=(x_test, y_test)) File "C:\Users\vkswa\AppData\Local\Programs\Python\Python36\lib\site-packages\keras\engine\training.py", line 1008, in fit self._make_train_function() File "C:\Users\vkswa\AppData\Local\Programs\Python\Python36\lib\site-packages\keras\engine\training.py", line 498, in _make_train_function loss=self.total_loss) TypeError: get_updates() missing 1 required positional argument: 'constraints'

Any suggestion will be helpful

[vishyML]

the cifar10.cnnpy was edited for minst as follows

'''Trains a simple convnet on the MNIST dataset. Gets to 99.25% test accuracy after 12 epochs (there is still a lot of margin for parameter tuning). 16 seconds per epoch on a GRID K520 GPU. '''

from future import print_function import keras from keras.datasets import mnist from keras.models import Sequential from keras.layers import Dense, Dropout, Flatten from keras.layers import Conv2D, MaxPooling2D from keras import backend as K

batch_size = 128 num_classes = 10 epochs = 12

input image dimensions

img_rows, img_cols = 28, 28

the data, split between train and test sets

(x_train, y_train), (x_test, y_test) = mnist.load_data()

if K.image_data_format() == 'channels_first': x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols) x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols) input_shape = (1, img_rows, img_cols) else: x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1) x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1) input_shape = (img_rows, img_cols, 1)

x_train = x_train.astype('float32') x_test = x_test.astype('float32') x_train /= 255 x_test /= 255 print('x_train shape:', x_train.shape) print(x_train.shape[0], 'train samples') print(x_test.shape[0], 'test samples')

convert class vectors to binary class matrices

y_train = keras.utils.to_categorical(y_train, num_classes) y_test = keras.utils.to_categorical(y_test, num_classes)

model = Sequential() model.add(Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=input_shape)) model.add(Conv2D(64, (3, 3), activation='relu')) model.add(MaxPooling2D(pool_size=(2, 2))) model.add(Dropout(0.25)) model.add(Flatten()) model.add(Dense(128, activation='relu')) model.add(Dropout(0.5)) model.add(Dense(num_classes, activation='softmax'))

from weightnorm import SGDWithWeightnorm sgd_wn = SGDWithWeightnorm(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True) model.compile(loss=keras.losses.categorical_crossentropy,optimizer=sgd_wn, metrics=['accuracy'])

model.fit(x_train, y_train, batch_size=batch_size, epochs=epochs, verbose=1, validation_data=(x_test, y_test)) score = model.evaluate(x_test, y_test, verbose=0) print('Test loss:', score[0]) print('Test accuracy:', score[1])

[mirfan899]

Same issue for me too. Code is two years old (2016) and Keras current version is 2.2.4

[vishyML]

I am currently using keras 2.2.2. Did it work for you when you upgraded to 2.2.4 ?

[mirfan899]

Use this repository it has latest implementation https://github.com/krasserm/weightnorm

[vishyML]

thanks. It works

On Sat, Dec 8, 2018 at 6:38 AM Muhammad Irfan [email protected] wrote:

Use this repository it has latest implementation https://github.com/krasserm/weightnorm

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/openai/weightnorm/issues/17#issuecomment-445456189, or mute the thread https://github.com/notifications/unsubscribe-auth/AeyM4lPBeMuDnN-o6AfwqcEkeMuC1iMtks5u27KsgaJpZM4Y8jWl .

[exowanderer]

PR #13 fixes this issue.

And TRAVIS says that there are no conflicts with the repo. Is @openai trying to keep this compatible with older versions of Keras? If so, why?