def prepare_batch_norm_deeplift_model(self, axis):
self.input_layer = blobs.Input(num_dims=None, shape=(None,2,2,2))
if (self.keras_version <= 0.3):
std = self.std
epsilon = self.epsilon
else:
std = np.sqrt(self.std+self.epsilon)
epsilon = 0
self.batch_norm_layer = blobs.BatchNormalization(
gamma=self.gamma,
beta=self.beta,
axis=axis,
mean=self.mean,
std=std,
epsilon=epsilon)
self.batch_norm_layer.set_inputs(self.input_layer)
self.flatten_layer = blobs.Flatten()
self.flatten_layer.set_inputs(self.batch_norm_layer)
self.dense_layer = blobs.Dense(
W=np.ones((1,8)).T,
b=np.zeros(1),
dense_mxts_mode=DenseMxtsMode.Linear)
self.dense_layer.set_inputs(self.flatten_layer)
self.dense_layer.build_fwd_pass_vars()
self.dense_layer.set_scoring_mode(blobs.ScoringMode.OneAndZeros)
self.dense_layer.set_active()
self.dense_layer.update_task_index(0)
self.input_layer.update_mxts()
def batchnorm_conversion(layer, name, mxts_mode):
return [
blobs.BatchNormalization(name=name,
gamma=np.array(layer.gamma.get_value()),
beta=np.array(layer.beta.get_value()),
axis=layer.axis,
mean=np.array(layer.running_mean.get_value()),
std=np.array(layer.running_std.get_value()),
epsilon=layer.epsilon,
input_shape=layer.input_shape[1:])
]
def batchnorm_conversion(layer, name, verbose, **kwargs):
#note: the variable called "running_std" actually stores
#the variance...
gamma, beta, running_mean, running_var = layer.get_weights()
return [
blobs.BatchNormalization(name=name,
verbose=verbose,
gamma=np.array(gamma),
beta=np.array(beta),
axis=layer.axis,
mean=np.array(running_mean),
var=running_var,
epsilon=layer.epsilon)
]
def setUp(self):
self.input_layer = blobs.Input(num_dims=None, shape=(None, 4, 2))
self.mean = np.array([1, -1])
self.gamma = np.array([2, -2])
self.beta = np.array([1, -1])
self.std = np.array([1.99, 1.99])
self.epsilon = 0.01
self.batch_norm_layer = blobs.BatchNormalization(axis=-1,
gamma=self.gamma,
beta=self.beta,
mean=self.mean,
std=self.std,
epsilon=self.epsilon)
self.batch_norm_layer.set_inputs(self.input_layer)
self.batch_norm_layer.build_fwd_pass_vars()
self.inp = (np.arange(16).reshape((2, 4, 2)).astype("float32")) - 8.0
self.ref = np.zeros_like(self.inp) + 1.0
def test_relu_after_dense_batchnorm(self):
input_layer = blobs.Input(num_dims=None, shape=(None, 4))
dense_layer = blobs.Dense(W=np.random.random((4, 2)),
b=np.random.random((2, )),
dense_mxts_mode=DenseMxtsMode.Linear)
dense_layer.set_inputs(input_layer)
batch_norm = blobs.BatchNormalization(gamma=np.array([1.0, 1.0]),
beta=np.array([-0.5, 0.5]),
axis=-1,
mean=np.array([-0.5, 0.5]),
std=np.array([1.0, 1.0]),
epsilon=0.001)
batch_norm.set_inputs(dense_layer)
relu_after_bn = blobs.ReLU(
nonlinear_mxts_mode=NonlinearMxtsMode.DeepLIFT_GenomicsDefault)
relu_after_bn.set_inputs(batch_norm)
relu_after_bn.build_fwd_pass_vars()
self.assertEqual(relu_after_bn.nonlinear_mxts_mode,
NonlinearMxtsMode.RevealCancel)
def batchnorm_conversion(layer, name, verbose, **kwargs):
import keras
if (hasattr(keras,'__version__')):
keras_version = float(keras.__version__[0:3])
else:
keras_version = 0.2
if (keras_version <= 0.3):
std = np.array(layer.running_std.get_value())
epsilon = layer.epsilon
else:
std = np.sqrt(np.array(layer.running_std.get_value()+layer.epsilon))
epsilon = 0
return [blobs.BatchNormalization(
name=name,
verbose=verbose,
gamma=np.array(layer.gamma.get_value()),
beta=np.array(layer.beta.get_value()),
axis=layer.axis,
mean=np.array(layer.running_mean.get_value()),
std=std,
epsilon=epsilon)]
def test_relu_after_conv1d_batchnorm(self):
input_layer = blobs.Input(num_dims=None, shape=(None, 2, 2))
conv_layer = blobs.Conv1D(W=np.random.random((2, 2, 2)),
b=np.random.random((2, )),
conv_mxts_mode=ConvMxtsMode.Linear,
stride=1,
border_mode=PaddingMode.valid,
channels_come_last=True)
conv_layer.set_inputs(input_layer)
batch_norm = blobs.BatchNormalization(gamma=np.array([1.0, 1.0]),
beta=np.array([-0.5, 0.5]),
axis=-1,
mean=np.array([-0.5, 0.5]),
std=np.array([1.0, 1.0]),
epsilon=0.001)
batch_norm.set_inputs(conv_layer)
relu_after_bn = blobs.ReLU(
nonlinear_mxts_mode=NonlinearMxtsMode.DeepLIFT_GenomicsDefault)
relu_after_bn.set_inputs(batch_norm)
relu_after_bn.build_fwd_pass_vars()
self.assertEqual(relu_after_bn.nonlinear_mxts_mode,
NonlinearMxtsMode.Rescale)