def convert(source_file,
target_file,
trim_unused_by_output="",
verbose=False,
compress_f16=False):
"""
Converts a ONNX model into a Barracuda model.
:param source_file: The ONNX Model
:param target_file: The name of the file the converted model will be saved to
:param trim_unused_by_output: The regexp to match output nodes to remain in the model. All other uconnected nodes will be removed.
:param verbose: If True, will display debug messages
:param compress_f16: If true, the float values will be converted to f16
:return:
"""
if (type(verbose) == bool):
args = Struct()
args.verbose = verbose
args.print_layers = verbose
args.print_source_json = verbose
args.print_barracuda_json = verbose
args.print_layer_links = verbose
args.print_patterns = verbose
args.print_tensors = verbose
else:
args = verbose
# Load ONNX model
print("Converting %s to %s" % (source_file, target_file))
i_model = onnx.load(source_file)
if args.print_source_json or args.verbose:
for layer in i_model.graph.node:
print(MessageToJson(layer) + ",")
# Convert
o_model = barracuda.Model()
o_model.layers, o_input_shapes, o_model.tensors, o_model.memories = \
process_model(i_model, args)
# Trim
if trim_unused_by_output:
o_model.layers = barracuda.trim(o_model.layers, trim_unused_by_output,
args.verbose)
# Find model inputs & outputs
all_inputs = {i for l in o_model.layers for i in l.inputs}
# Create load layers for constants
const_tensors = [i for i in all_inputs if i in o_model.tensors]
const_tensors += o_model.globals
for x in const_tensors:
shape = adapt_input_shape(o_model.tensors[x].dims) if hasattr(
o_model.tensors[x],
'dims') and len(o_model.tensors[x].dims) > 0 else [1, 1, 1, 1]
o_l = Struct(
type=255, # Load
class_name="Const",
name=x,
pads=[0, 0, 0, 0],
strides=[],
pool_size=[],
axis=-1,
alpha=1,
beta=0,
activation=0,
inputs=[],
tensors=[
Struct(name=x,
shape=shape,
data=np.reshape(get_tensor_data(o_model.tensors[x]),
shape).astype(np.float32))
])
o_model.layers.insert(0, o_l)
all_layers = {l.name for l in o_model.layers}
# global inputs - are inputs that are NOT connected to any layer in the network
# global outputs - are outputs that are NOT feeding any layer in the network
o_model.inputs = {
i: o_input_shapes[i]
for l in o_model.layers for i in l.inputs if i not in all_layers
}
o_model.outputs = [
l.name for l in o_model.layers if l.name not in all_inputs
]
# Compress
if compress_f16:
o_model = barracuda.compress(o_model)
# Summary
barracuda.summary(o_model,
print_layer_links=args.print_layer_links or args.verbose,
print_barracuda_json=args.print_barracuda_json
or args.verbose,
print_tensors=args.print_tensors or args.verbose)
# Write to file
barracuda.write(o_model, target_file)
print('DONE: wrote', target_file, 'file.')
def convert(source_file,
target_file,
trim_unused_by_output="",
verbose=False,
compress_f16=False):
"""
Converts a Keras model into a Barracuda model.
:param source_file: The Keras Model
:param target_file: The name of the file the converted model will be saved to
:param trim_unused_by_output: The regexp to match output nodes to remain in the model. All other uconnected nodes will be removed.
:param verbose: If True, will display debug messages
:param compress_f16: If true, the float values will be converted to f16
:return:
"""
if (type(verbose) == bool):
args = Struct()
args.verbose = verbose
args.print_layers = verbose
args.print_source_json = verbose
args.print_barracuda_json = verbose
args.print_layer_links = verbose
args.print_patterns = verbose
args.print_tensors = verbose
else:
args = verbose
if args.print_supported_ops:
barracuda.print_known_operations(known_classes, known_activations)
# Load Keras model
print("Converting %s to %s" % (source_file, target_file))
i_model = h5py.File(source_file, 'r')
configJSON = json.loads(i_model.attrs['model_config'].decode('utf-8'))
layers = configJSON['config']
model_tensors = i_model['model_weights']
if args.print_source_json or args.verbose:
pprint(configJSON)
# Convert
o_model = barracuda.Model()
o_model.layers, o_input_shapes, o_model.memories = \
process_model(layers, model_tensors, args)
# Gather patched model tensors
for l in o_model.layers:
for x in l.tensors:
o_model.tensors[x.name] = x
# Trim
if trim_unused_by_output:
o_model.layers = barracuda.trim(o_model.layers, trim_unused_by_output,
args.verbose)
# Find model inputs & outputs
all_layers = {l.name for l in o_model.layers}
all_inputs = {i for l in o_model.layers for i in l.inputs}
# global inputs - are inputs that are NOT connected to any layer in the network
# global outputs - are outputs that are NOT feeding any layer in the network
o_model.inputs = {
i: o_input_shapes[i]
for l in o_model.layers for i in l.inputs if i not in all_layers
}
o_model.outputs = [
l.name for l in o_model.layers if l.name not in all_inputs
]
# Compress
if compress_f16:
o_model = barracuda.compress(o_model)
# Summary
barracuda.summary(o_model,
print_layer_links=args.print_layer_links or args.verbose,
print_barracuda_json=args.print_barracuda_json
or args.verbose,
print_tensors=args.print_tensors or args.verbose)
# Write to file
barracuda.write(o_model, target_file)
print('DONE: wrote', target_file, 'file.')
def convert(source_file,
target_file,
trim_unused_by_output="",
verbose=False,
compress_f16=False):
"""
Converts a ONNX model into a Barracuda model.
:param source_file: The ONNX Model
:param target_file: The name of the file the converted model will be saved to
:param trim_unused_by_output: The regexp to match output nodes to remain in the model. All other uconnected nodes will be removed.
:param verbose: If True, will display debug messages
:param compress_f16: If true, the float values will be converted to f16
:return:
"""
if (type(verbose) == bool):
args = Struct()
args.verbose = verbose
args.print_layers = verbose
args.print_source_json = verbose
args.print_barracuda_json = verbose
args.print_layer_links = verbose
args.print_patterns = verbose
args.print_tensors = verbose
else:
args = verbose
if args.print_supported_ops:
barracuda.print_known_operations(known_classes, known_activations)
# Load ONNX model
print("Converting %s to %s" % (source_file, target_file))
i_model = onnx.load(source_file)
if args.print_source_json or args.verbose:
for layer in i_model.graph.node:
print(MessageToJson(layer) + ",")
# Convert
o_model = barracuda.Model()
o_model.layers, o_input_shapes, o_model.tensors, o_model.memories, o_model.globals = \
process_model(i_model, args)
# Trim
if trim_unused_by_output:
o_model.layers = barracuda.trim(o_model.layers, trim_unused_by_output,
args.verbose)
# Create load layers for constants
def dims_to_barracuda_shape(tensor):
if hasattr(tensor, 'dims') and len(tensor.dims) > 0:
return adapt_input_shape(tensor.dims)
return [1, 1, 1, 1]
barracuda.setup_constants(o_model,
lambda tensor: dims_to_barracuda_shape(tensor),
lambda tensor: get_tensor_data(tensor))
# Find model inputs & outputs
all_inputs = {i for l in o_model.layers for i in l.inputs}
all_layers = {l.name for l in o_model.layers}
# global inputs - are inputs that are NOT connected to any layer in the network
# global outputs - are outputs that are NOT feeding any layer in the network
o_model.inputs = {
i: o_input_shapes[i]
for l in o_model.layers for i in l.inputs if i not in all_layers
}
def is_output_layer(layer):
if layer.name in all_inputs: # Only layers that do not input to other layers can count as global output
return False
if layer.name in o_model.globals:
return False
return True
o_model.outputs = [l.name for l in o_model.layers if is_output_layer(l)]
# Compress
if compress_f16:
o_model = barracuda.compress(o_model)
# Sort model so that layer inputs are always ready upfront
o_model.layers = barracuda.sort(o_model.layers, o_model.inputs,
o_model.memories, args.verbose)
o_model.layers = barracuda.fuse(o_model.layers, args.verbose)
# Summary
barracuda.summary(o_model,
print_layer_links=args.print_layer_links or args.verbose,
print_barracuda_json=args.print_barracuda_json
or args.verbose,
print_tensors=args.print_tensors or args.verbose)
# Write to file
barracuda.write(o_model, target_file)
print('DONE: wrote', target_file, 'file.')