How to use the cortex.add_cost function in cortex
To help you get started, we’ve selected a few cortex examples, based on popular ways it is used in public projects.
Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.
rdevon / BGAN / cont_mnist.py View on Github 
def build_normal_GAN():
cortex.add_step('discriminator._cost', P='fake.P', X=0.,
name='fake_cost')
cortex.add_step('discriminator._cost', P='real.P', X=1.,
name='real_cost')
cortex.build()
cortex.add_cost(
lambda x, y: x + y, 'fake_cost.output', 'real_cost.output',
name='discriminator_cost')
m = 0
if m == 0:
cortex.add_cost(gen_cost, F='fake.P',
cells=['discriminator'],
name='generator_cost')
elif m == 1:
cortex.add_cost(alt_gen_cost, F='fake.P',
cells=['discriminator'],
name='generator_cost')
elif m == 2:
cortex.add_cost(
reweighted_MLE, G_samples='generator.output',
cells=['discriminator'], name='generator_cost')
else:
raise
cortex.add_stat('basic_stats', 'fake.P', name='fake_rate')
cortex.add_stat('basic_stats', 'real.P', name='real_rate')def build_normal_GAN():
'''
cortex.add_step('discriminator._cost', P='fake.P', X=0.,
name='fake_cost')
cortex.add_step('discriminator._cost', P='real.P', X=1.,
name='real_cost')
'''
cortex.build()
cortex.add_cost(
disc_cost, 'real.P', 'fake.P',
cells=['discriminator'],
name='discriminator_cost')
m = 2
if m == 0:
cortex.add_cost(gen_cost, F='fake.P',
cells=['discriminator'],
name='generator_cost')
elif m == 1:
cortex.add_cost(alt_gen_cost, F='fake.P',
cells=['discriminator'],
name='generator_cost')
elif m == 2:
cortex.add_cost(
reweighted_MLE, G_samples='generator.output',def build_normal_GAN():
cortex.add_step('discriminator._cost', P='fake.P', X=0.,
name='fake_cost')
cortex.add_step('discriminator._cost', P='real.P', X=1.,
name='real_cost')
cortex.build()
cortex.add_cost(
lambda x, y: x + y, 'fake_cost.output', 'real_cost.output',
name='discriminator_cost')
m = 2
if m == 0:
cortex.add_cost(gen_cost, F='fake.P',
cells=['discriminator'],
name='generator_cost')
elif m == 1:
cortex.add_cost(alt_gen_cost, F='fake.P',
cells=['discriminator'],
name='generator_cost')
elif m == 2:
cortex.add_cost(
reweighted_MLE, G_samples='generator.output',
cells=['discriminator', 'baseline'], name='generator_cost')def build_wasserstein_GAN():
cortex.build()
cortex.add_cost(wasserman_cost_d, 'real.output', 'fake.output',
name='discriminator_cost')
cortex.add_cost(wasserman_cost_g, 'fake.output',
name='generator_cost')
cortex.add_stat('basic_stats', 'data.input')cortex.add_cost(
lambda x, y: x + y, 'fake_cost.output', 'real_cost.output',
name='discriminator_cost')
m = 0
if m == 0:
cortex.add_cost(gen_cost, F='fake.P',
cells=['discriminator'],
name='generator_cost')
elif m == 1:
cortex.add_cost(alt_gen_cost, F='fake.P',
cells=['discriminator'],
name='generator_cost')
elif m == 2:
cortex.add_cost(
reweighted_MLE, G_samples='generator.output',
cells=['discriminator'], name='generator_cost')
else:
raise
cortex.add_stat('basic_stats', 'fake.P', name='fake_rate')
cortex.add_stat('basic_stats', 'real.P', name='real_rate')cortex.prepare_samples('noise', batch_size)
cortex.add_step('generator', 'noise.samples', constants=['noise.samples'])
cortex.prepare_samples('generator.P', n_posterior_samples)
cortex.add_step('discriminator', 'generator.samples', name='fake',
constants=['generator.samples'])
cortex.add_step('discriminator._cost', P='fake.P', X=0., name='fake_cost')
cortex.add_step('discriminator._cost', P='real.P', X=1., name='real_cost')
cortex.add_step('noise.grid2d', random_idx=True, name='noise_grid')
cortex.add_step('generator', 'noise_grid.output', name='gen_grid')
cortex.build()
#cortex.add_cost('l2_decay', 0.002, 'discriminator.mlp.weights')
cortex.add_cost('l2_decay', 0.002, 'generator.mlp.weights')
cortex.add_cost(lambda x, y: x + y, 'fake_cost.output', 'real_cost.output',
name='discriminator_cost')
cortex.add_cost(reweighted_MLE, G='generator.P',
G_samples='generator.samples',
cells=['generator', 'discriminator'],
name='generator_cost')
train_session = cortex.create_session()
cortex.build_session(test=test)
trainer = cortex.setup_trainer(
train_session,
optimizer='sgd',
epochs=3000,
learning_rate=0.01,'''
cortex.build()
cortex.add_cost(
disc_cost, 'real.P', 'fake.P',
cells=['discriminator'],
name='discriminator_cost')
m = 2
if m == 0:
cortex.add_cost(gen_cost, F='fake.P',
cells=['discriminator'],
name='generator_cost')
elif m == 1:
cortex.add_cost(alt_gen_cost, F='fake.P',
cells=['discriminator'],
name='generator_cost')
elif m == 2:
cortex.add_cost(
reweighted_MLE, G_samples='generator.output',
cells=['discriminator', 'baseline'], name='generator_cost')
else:
raise
cortex.add_stat('basic_stats', 'fake.P', name='fake_rate')
cortex.add_stat('basic_stats', 'real.P', name='real_rate')
cortex.add_step('discriminator._cost', P='real.P', X=1.,
name='real_cost')
cortex.build()
cortex.add_cost(
lambda x, y: x + y, 'fake_cost.output', 'real_cost.output',
name='discriminator_cost')
m = 2
if m == 0:
cortex.add_cost(gen_cost, F='fake.P',
cells=['discriminator'],
name='generator_cost')
elif m == 1:
cortex.add_cost(alt_gen_cost, F='fake.P',
cells=['discriminator'],
name='generator_cost')
elif m == 2:
cortex.add_cost(
reweighted_MLE, G_samples='generator.output',
cells=['discriminator', 'baseline'], name='generator_cost')
else:
raise
cortex.add_stat('basic_stats', 'fake.P', name='fake_rate')
cortex.add_stat('basic_stats', 'real.P', name='real_rate')
Popular cortex functions
- cortex.add_cost
- cortex.add_step
- cortex.app
- cortex.app.logger
- cortex.app.logger.warn
- cortex.app.route
- cortex.database.db
- cortex.database.db.get_surf
- cortex.lib
- cortex.lib.core
- cortex.lib.core.log
- cortex.lib.exceptions.UserException
- cortex.lib.systems
- cortex.lib.user
- cortex.lib.user.does_user_have_permission
- cortex.lib.user.does_user_have_system_permission
- cortex.lib.user.login_required
- cortex.options.config.get
- cortex.quickshow
- cortex.Volume