Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[NNVM][FRONTEND][Keras] Support for reusing layers #1192

Merged
merged 5 commits into from
Jun 6, 2018
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
46 changes: 27 additions & 19 deletions nnvm/python/nnvm/frontend/keras.py
Original file line number Diff line number Diff line change
Expand Up @@ -152,8 +152,8 @@ def _convert_convolution(insym, keras_layer, symtab):
pass
# we insert a separate pad operator
elif keras_layer.padding == 'same':
in_h = keras_layer.input.shape[1].value
in_w = keras_layer.input.shape[2].value
in_h = keras_layer.input_shape[1]
in_w = keras_layer.input_shape[2]
pad_t, pad_b = _get_pad_pair(in_h, kernel_h, stride_h)
pad_l, pad_r = _get_pad_pair(in_w, kernel_w, stride_w)
insym = _sym.pad(data=insym, pad_width=((0, 0), (0, 0), (pad_t, pad_b), (pad_l, pad_r)))
Expand Down Expand Up @@ -192,8 +192,8 @@ def _convert_separable_convolution(insym, keras_layer, symtab):
pass
# we insert a separate pad operator
elif keras_layer.padding == 'same':
in_h = keras_layer.input.shape[1].value
in_w = keras_layer.input.shape[2].value
in_h = keras_layer.input_shape[1]
in_w = keras_layer.input_shape[2]
pad_t, pad_b = _get_pad_pair(in_h, kernel_h, stride_h)
pad_l, pad_r = _get_pad_pair(in_w, kernel_w, stride_w)
insym = _sym.pad(data=insym, pad_width=(
Expand Down Expand Up @@ -249,8 +249,8 @@ def _convert_pooling(insym, keras_layer, symtab):
pass
# we insert a separate pad operator
elif keras_layer.padding == 'same':
in_h = keras_layer.input.shape[1].value
in_w = keras_layer.input.shape[2].value
in_h = keras_layer.input_shape[1]
in_w = keras_layer.input_shape[2]
pad_t, pad_b = _get_pad_pair(in_h, pool_h, stride_h)
pad_l, pad_r = _get_pad_pair(in_w, pool_w, stride_w)
insym = _sym.pad(data=insym, pad_width=(
Expand Down Expand Up @@ -475,25 +475,33 @@ def from_keras(model):
symtab = SymbolTable()
for keras_layer in model.layers:
if isinstance(keras_layer, keras.engine.topology.InputLayer):
keras_layer.name = 'data'
symtab.get_var(keras_layer.name, must_contain=False)
else:
predecessors = []
inbound_nodes = keras_layer.inbound_nodes if hasattr(keras_layer, 'inbound_nodes') \
else keras_layer._inbound_nodes if hasattr(keras_layer, '_inbound_nodes') \
else None
if inbound_nodes is None:
raise TypeError("Unknown layer type or unsupported Keras version : {}"
.format(keras_layer))
for node in inbound_nodes:
for pred in node.inbound_layers:
predecessors.append(pred.name)
if len(predecessors) == 1:
insym = symtab.get_var(predecessors[0], must_contain=True)
else:
insym = [symtab.get_var(pred, must_contain=True) for pred in predecessors]
keras_op_to_nnvm(insym, keras_layer, keras_layer.name, symtab)

returns = [symtab.get_var(i.name, must_contain=False) for i in model.output_layers]
for my_idx, node in enumerate(inbound_nodes):
insym = []

# Since Keras allows creating multiple layers from the same name instance,
# we append node index to the symbol name to make it unique.
# The one exception is InputLayer. Changing input variable names after conversion
# would confuse users, so we should keep them as far as possible. Fortunately,
# they are named uniquely to input_1, input_2, input_3 ... by default.
for pred_idx, pred in zip(node.node_indices, node.inbound_layers):
if isinstance(pred, keras.engine.topology.InputLayer):
_sym = symtab.get_var(pred.name, must_contain=True)
else:
_sym = symtab.get_var(pred.name + ':' + str(pred_idx), must_contain=True)
insym.append(_sym)

if len(insym) == 1:
insym = insym[0]
keras_op_to_nnvm(insym, keras_layer, keras_layer.name + ':' + str(my_idx), symtab)

outsym = symtab.get_var(model.output_layers[0].name + ':0')
tvmparams = {k:tvm.nd.array(np.array(v, dtype=np.float32)) for k, v in symtab.params.items()}
return returns[0], tvmparams
return outsym, tvmparams
57 changes: 48 additions & 9 deletions nnvm/tests/python/frontend/keras/test_forward.py
Original file line number Diff line number Diff line change
Expand Up @@ -14,28 +14,31 @@


def verify_keras_frontend(keras_model):
in_shape = [dim.value if dim.value is not None else 1 for dim in keras_model.input_layers[0].input.shape]
in_shapes = []
for layer in keras_model.input_layers:
in_shapes.append(tuple(dim.value if dim.value is not None else 1 for dim in layer.input.shape))
out_shape = [dim.value if dim.value is not None else 1 for dim in keras_model.output_layers[0].output.shape]

def get_keras_output(x, dtype='float32'):
return keras_model.predict(x)
def get_keras_output(xs, dtype='float32'):
return keras_model.predict(xs)

def get_tvm_output(x, target, ctx, input_name='data', dtype='float32'):
def get_tvm_output(xs, target, ctx, dtype='float32'):
sym, params = nnvm.frontend.from_keras(keras_model)
shape_dict = {input_name : x.shape}
shape_dict = {name: x.shape for (name, x) in zip(keras_model.input_names, xs)}
with nnvm.compiler.build_config(opt_level=2):
graph, lib, params = nnvm.compiler.build(sym, target, shape_dict, params=params)
m = graph_runtime.create(graph, lib, ctx)
m.set_input(input_name, tvm.nd.array(x.astype(dtype)))
for name, x in zip(keras_model.input_names, xs):
m.set_input(name, tvm.nd.array(x.astype(dtype)))
m.set_input(**params)
m.run()
out = m.get_output(0, tvm.nd.empty(out_shape, dtype))
return out.asnumpy()

x = np.random.uniform(size=in_shape)
keras_out = get_keras_output(x)
xs = [np.random.uniform(size=shape) for shape in in_shapes]
keras_out = get_keras_output(xs)
for target, ctx in ctx_list():
tvm_out = get_tvm_output(x.transpose([0,3,1,2]), target, ctx)
tvm_out = get_tvm_output([x.transpose([0,3,1,2]) for x in xs], target, ctx)
np.testing.assert_allclose(keras_out, tvm_out, rtol=1e-5, atol=1e-5)


Expand Down Expand Up @@ -166,6 +169,39 @@ def test_forward_mobilenet():
verify_keras_frontend(keras_model)


def test_forward_multi_inputs():
data1 = keras.layers.Input(shape=(32,32,3))
data2 = keras.layers.Input(shape=(32,32,3))
x = keras.layers.Conv2D(8, (3, 3), padding="same")(data1)
y = keras.layers.Conv2D(8, (3, 3), padding="same")(data2)
z = keras.layers.add([x, y])
z = keras.layers.GlobalAveragePooling2D()(z)
keras_model = keras.models.Model([data1, data2], z)
verify_keras_frontend(keras_model)


def test_forward_reuse_layers():
# reuse conv2d
data = keras.layers.Input(shape=(32,32,3))
conv2d = keras.layers.Conv2D(8, (3, 3), padding="same")
x = conv2d(data)
y = conv2d(data)
z = keras.layers.add([x, y])
z = keras.layers.GlobalAveragePooling2D()(z)
keras_model = keras.models.Model(data, z)
verify_keras_frontend(keras_model)

# reuse add
data = keras.layers.Input(shape=(32,32,3))
x = keras.layers.Conv2D(8, (3, 3), padding="same")(data)
add = keras.layers.Add()
x = add([x, x])
x = add([x, x])
z = keras.layers.GlobalAveragePooling2D()(x)
keras_model = keras.models.Model(data, z)
verify_keras_frontend(keras_model)


if __name__ == '__main__':
test_forward_elemwise_add()
test_forward_softmax()
Expand All @@ -182,3 +218,6 @@ def test_forward_mobilenet():
test_forward_xception()
test_forward_resnet50()
test_forward_mobilenet()

test_forward_multi_inputs()
test_forward_reuse_layers()
6 changes: 3 additions & 3 deletions tutorials/nnvm/from_keras.py
Original file line number Diff line number Diff line change
Expand Up @@ -63,7 +63,7 @@ def download(url, path, overwrite=False):
# input preprocess
data = np.array(img)[np.newaxis, :].astype('float32')
data = preprocess_input(data).transpose([0, 3, 1, 2])
print('data', data.shape)
print('input_1', data.shape)

######################################################################
# Compile the model on NNVM
Expand All @@ -74,7 +74,7 @@ def download(url, path, overwrite=False):
sym, params = nnvm.frontend.from_keras(keras_resnet50)
# compile the model
target = 'cuda'
shape_dict = {'data': data.shape}
shape_dict = {'input_1': data.shape}
with nnvm.compiler.build_config(opt_level=2):
graph, lib, params = nnvm.compiler.build(sym, target, shape_dict, params=params)

Expand All @@ -86,7 +86,7 @@ def download(url, path, overwrite=False):
ctx = tvm.gpu(0)
m = graph_runtime.create(graph, lib, ctx)
# set inputs
m.set_input('data', tvm.nd.array(data.astype('float32')))
m.set_input('input_1', tvm.nd.array(data.astype('float32')))
m.set_input(**params)
# execute
m.run()
Expand Down