def test_model_get_outputs(backend_default, data):
(X_train, y_train), (X_test, y_test), nclass = load_mnist(path=data)
train_set = ArrayIterator(X_train[:backend_default.bsz * 3])
init_norm = Gaussian(loc=0.0, scale=0.1)
layers = [Affine(nout=20, init=init_norm, bias=init_norm, activation=Rectlin()),
Affine(nout=10, init=init_norm, activation=Logistic(shortcut=True))]
mlp = Model(layers=layers)
out_list = []
mlp.initialize(train_set)
for x, t in train_set:
x = mlp.fprop(x)
out_list.append(x.get().T.copy())
ref_output = np.vstack(out_list)
train_set.reset()
output = mlp.get_outputs(train_set)
assert np.allclose(output, ref_output)
def test_model_get_outputs(backend_default, data):
(X_train, y_train), (X_test, y_test), nclass = load_mnist(path=data)
train_set = ArrayIterator(X_train[:backend_default.bsz * 3])
init_norm = Gaussian(loc=0.0, scale=0.1)
layers = [
Affine(nout=20, init=init_norm, bias=init_norm, activation=Rectlin()),
Affine(nout=10, init=init_norm, activation=Logistic(shortcut=True))
]
mlp = Model(layers=layers)
out_list = []
mlp.initialize(train_set)
for x, t in train_set:
x = mlp.fprop(x)
out_list.append(x.get().T.copy())
ref_output = np.vstack(out_list)
train_set.reset()
output = mlp.get_outputs(train_set)
assert np.allclose(output, ref_output)
def main():
# setup the model and run for num_epochs saving the last state only
# this is at the top so that the be is generated
model = gen_model(args.backend)
# setup data iterators
(X_train, y_train), (X_test, y_test), nclass = load_mnist(path=args.data_dir)
NN = batch_size*5 # avoid partial mini batches
if args.backend == 'nervanacpu' or args.backend == 'cpu':
# limit data since cpu backend runs slower
train = ArrayIterator(X_train[:NN], y_train[:NN],
nclass=nclass, lshape=(1, 28, 28))
valid = ArrayIterator(X_test[:NN], y_test[:NN],
nclass=nclass, lshape=(1, 28, 28))
else:
train = ArrayIterator(X_train, y_train, nclass=nclass, lshape=(1, 28, 28))
valid = ArrayIterator(X_test, y_test, nclass=nclass, lshape=(1, 28, 28))
# serialization related
cost = GeneralizedCost(costfunc=CrossEntropyBinary())
opt_gdm = GradientDescentMomentum(learning_rate=0.1, momentum_coef=0.9)
checkpoint_model_path = os.path.join('./', 'test_oneshot.pkl')
checkpoint_schedule = 1 # save at every step
callbacks = Callbacks(model)
callbacks.add_callback(SerializeModelCallback(checkpoint_model_path,
checkpoint_schedule,
history=2))
# run the fit all the way through saving a checkpoint e
model.fit(train,
optimizer=opt_gdm,
num_epochs=num_epochs,
cost=cost,
callbacks=callbacks)
# setup model with same random seed run epoch by epoch
# serializing and deserializing at each step
model = gen_model(args.backend)
cost = GeneralizedCost(costfunc=CrossEntropyBinary())
opt_gdm = GradientDescentMomentum(learning_rate=0.1, momentum_coef=0.9)
# reset data iterators
train.reset()
valid.reset()
checkpoint_model_path = os.path.join('./', 'test_manyshot.pkl')
checkpoint_schedule = 1 # save at evey step
for epoch in range(num_epochs):
# _0 points to state at end of epoch 0
callbacks = Callbacks(model)
callbacks.add_callback(SerializeModelCallback(checkpoint_model_path,
checkpoint_schedule,
history=num_epochs))
model.fit(train,
optimizer=opt_gdm,
num_epochs=epoch+1,
cost=cost,
callbacks=callbacks)
# load saved file
prts = os.path.splitext(checkpoint_model_path)
fn = prts[0] + '_%d' % epoch + prts[1]
model.load_params(fn) # load the saved weights
# compare test_oneshot_<num_epochs>.pkl to test_manyshot_<num_epochs>.pkl
if not compare_model_pickles('test_oneshot_%d.pkl' % (num_epochs-1),
'test_manyshot_%d.pkl' % (num_epochs-1)):
print 'No Match'
sys.exit(1)
else:
print 'Match'
