def convert_sequential_model(model,
num_dims=None,
mxts_mode=MxtsMode.DeepLIFT):
converted_layers = []
if (model.layers[0].input_shape is not None):
input_shape = model.layers[0].input_shape[1:]
num_dims_input = len(input_shape) + 1 #+1 for the batch axis
assert num_dims is None or num_dims_input==num_dims,\
"num_dims argument of "+str(num_dims)+" is incompatible with"\
+" the number of dims in layers[0].input_shape which is: "\
+str(model.layers[0].input_shape)
num_dims = num_dims_input
else:
input_shape = None
converted_layers.append(
blobs.Input_FixedDefault(default=0.0,
num_dims=num_dims,
shape=input_shape,
name="input"))
for layer_idx, layer in enumerate(model.layers):
conversion_function = layer_name_to_conversion_function[
layer.get_config()[KerasKeys.name]]
converted_layers.extend(
conversion_function(layer=layer,
name=str(layer_idx),
mxts_mode=mxts_mode))
connect_list_of_layers(converted_layers)
converted_layers[-1].build_fwd_pass_vars()
return models.SequentialModel(converted_layers)
def convert_sequential_model(
model_config,
nonlinear_mxts_mode=\
NonlinearMxtsMode.DeepLIFT_GenomicsDefault,
verbose=True,
dense_mxts_mode=DenseMxtsMode.Linear,
conv_mxts_mode=ConvMxtsMode.Linear,
maxpool_deeplift_mode=default_maxpool_deeplift_mode,
layer_overrides={},
custom_conversion_funcs={}):
if (verbose):
print("nonlinear_mxts_mode is set to: " + str(nonlinear_mxts_mode))
sys.stdout.flush()
converted_layers = []
batch_input_shape = model_config[0]['config'][KerasKeys.batch_input_shape]
converted_layers.append(
layers.core.Input(batch_shape=batch_input_shape, name="input"))
#converted_layers is actually mutated to be extended with the
#additional layers so the assignment is not strictly necessary,
#but whatever
converted_layers = sequential_container_conversion(
config=model_config,
name="",
verbose=verbose,
nonlinear_mxts_mode=nonlinear_mxts_mode,
dense_mxts_mode=dense_mxts_mode,
conv_mxts_mode=conv_mxts_mode,
maxpool_deeplift_mode=maxpool_deeplift_mode,
converted_layers=converted_layers,
layer_overrides=layer_overrides)
converted_layers[-1].build_fwd_pass_vars()
return models.SequentialModel(converted_layers)
def convert_sequential_model(
model,
num_dims=None,
nonlinear_mxts_mode=NonlinearMxtsMode.DeepLIFT,
verbose=True,
dense_mxts_mode=DenseMxtsMode.Linear,
maxpool_deeplift_mode=default_maxpool_deeplift_mode):
converted_layers = []
if (model.layers[0].input_shape is not None):
input_shape = model.layers[0].input_shape
assert input_shape[0] is None #batch axis
num_dims_input = len(input_shape)
assert num_dims is None or num_dims_input==num_dims,\
"num_dims argument of "+str(num_dims)+" is incompatible with"\
+" the number of dims in layers[0].input_shape which is: "\
+str(model.layers[0].input_shape)
num_dims = num_dims_input
else:
input_shape = None
converted_layers.append(
blobs.Input(num_dims=num_dims, shape=input_shape, name="input"))
#converted_layers is actually mutated to be extended with the
#additional layers so the assignment is not strictly necessary,
#but whatever
converted_layers = sequential_container_conversion(
layer=model,
name="",
verbose=verbose,
nonlinear_mxts_mode=nonlinear_mxts_mode,
dense_mxts_mode=dense_mxts_mode,
maxpool_deeplift_mode=maxpool_deeplift_mode,
converted_layers=converted_layers)
deeplift.util.connect_list_of_layers(converted_layers)
converted_layers[-1].build_fwd_pass_vars()
return models.SequentialModel(converted_layers)