caffe2.python.onnx.backend.Caffe2Backend Class Reference

Inheritance diagram for caffe2.python.onnx.backend.Caffe2Backend:

Public Member Functions
def	dummy_name (cls)
def	run_node (cls, node, inputs, device='CPU', opset_version=_known_opset_version, outputs_info=None)
def	prepare_zip_archive (cls, file, device='CPU', kwargs)
def	prepare (cls, model, device='CPU', raw_values_dict=None, kwargs)
def	onnx_graph_to_caffe2_net (cls, model, device="CPU", opset_version=_known_opset_version)
def	supports_device (cls, device_str)
def	is_compatible (cls, model, device='CPU', kwargs)

Static Public Member Functions
def	optimize_onnx (input, init=False, predict=False)

Detailed Description

Definition at line 135 of file backend.py.

Member Function Documentation

def caffe2.python.onnx.backend.Caffe2Backend.prepare	(		cls,
			model,
			device = 'CPU',
			raw_values_dict = None,
			kwargs
	)

For Onnx Caffe2Backend, we require that init_graph don't initialize the actual input of the predict_graph,

for example, if "img" is the input blob for the predict_net, we require that in init_graph and in
initializer of the predict_graph, "img" is not initalized. We don't have a check for this, since
there is no way we can know which blob is the input of the predict_graph.

Definition at line 680 of file backend.py.

---

The documentation for this class was generated from the following file:

• caffe2/python/onnx/backend.py