def conv1d_conversion(config, name, verbose, nonlinear_mxts_mode,
conv_mxts_mode, **kwargs):
validate_keys(config, [
KerasKeys.weights, KerasKeys.activation, KerasKeys.filters,
KerasKeys.kernel_size, KerasKeys.padding, KerasKeys.strides
])
#nonlinear_mxts_mode only used for activation
converted_activation = activation_conversion(
config=config,
name=name,
verbose=verbose,
nonlinear_mxts_mode=nonlinear_mxts_mode)
to_return = [
layers.Conv1D(
name=("preact_" if len(converted_activation) > 0 else "") + name,
kernel=config[KerasKeys.weights][0],
bias=(config[KerasKeys.weights][1]
if len(config[KerasKeys.weights]) > 1 else np.zeros(
config[KerasKeys.weights][0].shape[-1])),
stride=config[KerasKeys.strides],
padding=config[KerasKeys.padding].upper(),
conv_mxts_mode=conv_mxts_mode)
]
to_return.extend(converted_activation)
return deeplift.util.connect_list_of_layers(to_return)
def test_fprop(self):
conv_layer = layers.Conv1D(kernel=self.conv_W, bias=self.conv_b,
stride=1,
padding=PaddingMode.valid,
conv_mxts_mode="Linear")
self.create_small_net_with_conv_layer(conv_layer,
outputs_per_channel=3)
func = compile_func([self.input_layer.get_activation_vars()],
self.conv_layer.get_activation_vars())
#input:
# [[[-8,-7,-6,-5],
# [-4,-3,-2,-1]],
# [[ 0, 1, 2, 3],
# [ 4, 5, 6, 7]]]
# W:
# [-2,-1
# 0, 1]
# 16+7+0+-3 = 20 - bias (1.0) = 19
# 0+-1+0+5 = 4 - bias (1.0) = 3
np.testing.assert_almost_equal(func(self.inp),
np.array(
[[[ 19, 17, 15],
[-19,-17,-15]],
[[ 3, 1,-1],
[-3,-1, 1]]]).transpose(0,2,1))
def test_relu_after_conv1d(self):
input_layer = layers.Input(batch_shape=(None,2,2))
conv_layer = layers.Conv1D(
kernel=np.random.random((2,2,2)).astype("float32"),
bias=np.random.random((2,)).astype("float32"),
conv_mxts_mode=ConvMxtsMode.Linear,
stride=1,
padding=PaddingMode.valid)
conv_layer.set_inputs(input_layer)
relu_after_conv = layers.ReLU(nonlinear_mxts_mode=
NonlinearMxtsMode.DeepLIFT_GenomicsDefault)
relu_after_conv.set_inputs(conv_layer)
relu_after_conv.build_fwd_pass_vars()
self.assertEqual(relu_after_conv.nonlinear_mxts_mode,
NonlinearMxtsMode.Rescale)
def test_dense_backprop_stride(self):
conv_layer = layers.Conv1D(kernel=self.conv_W, bias=self.conv_b,
stride=2,
padding=PaddingMode.valid,
conv_mxts_mode="Linear")
self.create_small_net_with_conv_layer(conv_layer,
outputs_per_channel=2)
self.dense_layer.update_task_index(task_index=0)
func = compile_func([self.input_layer.get_activation_vars(),
self.input_layer.get_reference_vars()],
self.input_layer.get_mxts())
np.testing.assert_almost_equal(
func([self.inp, np.zeros_like(self.inp)]),
np.array(
[[[ -4, -2, -4, -2],
[ 0, 2, 0, 2]],
[[ -4, -2, -4, -2],
[ 0, 2, 0, 2]]]).transpose(0,2,1))
def test_fprop_pos_and_neg_contribs(self):
conv_layer = layers.Conv1D(kernel=self.conv_W, bias=self.conv_b,
stride=1,
padding=PaddingMode.valid,
conv_mxts_mode="Linear")
self.create_small_net_with_conv_layer(conv_layer,
outputs_per_channel=3)
pos_contribs, neg_contribs = self.conv_layer.get_pos_and_neg_contribs()
func_pos = compile_func([self.input_layer.get_activation_vars(),
self.input_layer.get_reference_vars()],
pos_contribs)
func_neg = compile_func([self.input_layer.get_activation_vars(),
self.input_layer.get_reference_vars()],
neg_contribs)
#diff from ref:
# [[[-9,-8,-7,-6],
# [-5,-4,-3,-2]],
# [[-1, 0, 1, 2],
# [ 3, 4, 5, 6]]]
# W:
# [-2,-1
# 0, 1]
# 18+8 = 26, -4 = -4
# 0+-1+0+5 = 4 - bias (1.0) = 3
np.testing.assert_almost_equal(func_pos([self.inp,
np.ones_like(self.inp)]),
np.array(
[[[ 26, 23, 20],
[ 4, 3, 2]],
[[ 6, 5, 6],
[ 0, 1, 4]]]).transpose(0,2,1))
np.testing.assert_almost_equal(func_neg([self.inp,
np.ones_like(self.inp)]),
np.array(
[[[ -4, -3, -2],
[-26,-23,-20]],
[[ 0, -1, -4],
[ -6, -5, -6]]]).transpose(0,2,1))
def test_relu_after_conv1d_batchnorm(self):
input_layer = layers.Input(batch_shape=(None,2,2))
conv_layer = layers.Conv1D(
kernel=np.random.random((2,2,2)).astype("float32"),
bias=np.random.random((2,)).astype("float32"),
conv_mxts_mode=ConvMxtsMode.Linear,
stride=1,
padding=PaddingMode.valid)
conv_layer.set_inputs(input_layer)
batch_norm = layers.BatchNormalization(
gamma=np.array([1.0, 1.0]).astype("float32"),
beta=np.array([-0.5, 0.5]).astype("float32"),
axis=-1,
mean=np.array([-0.5, 0.5]).astype("float32"),
var=np.array([1.0, 1.0]).astype("float32"),
epsilon=0.001)
batch_norm.set_inputs(conv_layer)
relu_after_bn = layers.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)
