os.environ['ODIN'] = 'float32,gpu,%s,seed=12' % arg['backend']
from odin import backend as K
from odin import nnet as N
from odin import fuel, training
from six.moves import cPickle
# ===========================================================================
# Load data
# ===========================================================================
USE_MNIST_DATA = True if 'mnist' in arg['ds'].lower() else False
if USE_MNIST_DATA:
ds = fuel.load_mnist()
else:
ds = fuel.load_cifar10()
X = K.placeholder(shape=(None, ) + ds['X_train'].shape[1:], name='X')
y = K.placeholder(shape=(None, ), name='y', dtype='int32')
# ===========================================================================
# Build network
# ===========================================================================
ops = N.Sequence([
N.Dimshuffle((0, 1, 2, 'x')) if USE_MNIST_DATA else None,
N.BatchNorm(axes='auto'),
N.Conv(32, (3, 3), strides=(1, 1), pad='same', activation=K.relu),
N.Pool(pool_size=(2, 2), strides=None),
N.Conv(64, (3, 3), strides=(1, 1), pad='same', activation=K.relu),
N.Pool(pool_size=(2, 2), strides=None),
N.Flatten(outdim=2),
from __future__ import print_function, division, absolute_import
import os
os.environ['ODIN'] = 'float32,gpu,theano,seed=12082518'
import numpy as np
from odin import fuel as F, nnet as N, backend as K, training, utils
# ===========================================================================
# Load dataset
# ===========================================================================
ds = F.load_cifar10()
print(ds)
X_learn = ds['X_train'][:].astype('float32') / 255.
y_learn = ds['y_train']
X_test = ds['X_test'][:].astype('float32') / 255.
y_test = ds['y_test']
# ===========================================================================
# Create network
# ===========================================================================
X = K.placeholder(shape=(None, ) + X_learn.shape[1:], name='X')
y_true = K.placeholder(shape=(None, ), name='y_true', dtype='int32')
f = N.Sequence([
N.Dimshuffle(pattern=(0, 2, 3, 1)),
N.Conv(32, (3, 3), pad='same', stride=(1, 1), activation=K.relu),
N.Conv(32, (3, 3), pad='same', stride=(1, 1), activation=K.relu),
N.Pool(pool_size=(2, 2), ignore_border=True, strides=None, mode='max'),
N.Dropout(level=0.25),
import os
os.environ['ODIN'] = 'float32,gpu,theano,seed=12,cnmem=0.4'
from odin import backend as K
from odin import nnet as N
from odin import fuel, training
from odin.utils import get_modelpath, ArgController, stdio, get_logpath
from six.moves import cPickle
stdio(get_logpath('tmp.log'))
# ===========================================================================
# Load data
# ===========================================================================
ds = fuel.load_cifar10()
print(ds)
X_train = K.placeholder(shape=(None,) + ds['X_train'].shape[1:], name='X_train')
X_score = K.placeholder(shape=(None,) + ds['X_train'].shape[1:], name='X_score')
y = K.placeholder(shape=(None,), name='y', dtype='int32')
# ===========================================================================
# Build network
# ===========================================================================
ops = N.Sequence([
N.Flatten(outdim=2),
N.Dense(512, activation=K.relu),
N.Dense(256, activation=K.relu),
N.Dense(10, activation=K.softmax)
])