fcn benchmark

fcn_bench.py

from keras.models import Sequential
from keras.layers.core import Permute
from keras.layers.convolutional import Convolution2D
from keras.layers.core import Activation
import theano
import theano.tensor as T
import datetime
import numpy as np

now = datetime.datetime.now


if theano.config.floatX == 'float64':
    epsilon = 1.0e-9
else:
    epsilon = 1.0e-7


def categorical_crossentropy_2d(y_true, y_pred):
    y_pred = T.clip(y_pred, epsilon, 1.0 - epsilon)
    # scale preds so that the class probas of each sample sum to 1
    y_pred /= y_pred.sum(axis=-1, keepdims=True)
    cce = - (y_true * T.log(y_pred)).sum()
    return cce

# input data
np.random.seed(123456)
n_images = 10
s = (850, 649)
x = np.random.rand(n_images, 1, s[0], s[1]).astype('float32')
y = np.random.rand(n_images, s[0], s[1], 21).astype('float32')

layers = [
    Convolution2D(64, 3, 3, activation='relu', border_mode='same', input_shape=(1, s[0], s[1])),
    Convolution2D(64, 3, 3, activation='relu', border_mode='same'),
    Convolution2D(21, 3, 3, activation='relu', border_mode='same'),
    Permute((2, 3, 1)),
    Activation('softmax')
]
model = Sequential()
for l in layers:
    model.add(l)

# compile
t = now()
model.compile(optimizer='adagrad', loss=categorical_crossentropy_2d)
print('Compilation time %s' % (now() - t))

# train
t = now()
model.fit(x, y, batch_size=1, nb_epoch=1)
print('Training time for %d images (batch_size=1): %s' % (n_images, (now() - t)))
t = now()
model.fit(x, y, batch_size=n_images, nb_epoch=1)
print('Training time for %d images (batch_size=%s): %s' % (n_images, n_images, (now() - t)))

model.save_weights('w.h5', overwrite=True)

# predict
t = now()
model.predict(x)
print('Prediction time for %d images: %s' % (n_images, (now() - t)))

This code will not work properly with keras main branch code as @mmmikael has modified his code of softmax activation. Look at his softmax activation code here, add this softmax definition in your code and it will work as desired.