Caffe2 - Python API
A deep learning, cross platform ML framework
Functions
predictor_py_utils Namespace Reference

Module caffe2.python.predictor.predictor_py_utils. More...

Functions

def create_predict_net (predictor_export_meta)
 
def create_predict_init_net (ws, predictor_export_meta)
 
def get_comp_name (string, name)
 
def GetPlan (meta_net_def, key)
 
def GetPlanOriginal (meta_net_def, key)
 
def GetBlobs (meta_net_def, key)
 
def GetNet (meta_net_def, key)
 
def GetNetOriginal (meta_net_def, key)
 
def GetApplicationSpecificInfo (meta_net_def, key)
 
def AddBlobs (meta_net_def, blob_name, blob_def)
 
def AddPlan (meta_net_def, plan_name, plan_def)
 
def AddNet (meta_net_def, net_name, net_def)
 

Detailed Description

Module caffe2.python.predictor.predictor_py_utils.

Function Documentation

◆ create_predict_init_net()

def predictor_py_utils.create_predict_init_net (   ws,
  predictor_export_meta 
)
Return an initialization net that zero-fill all the input and
output blobs, using the shapes from the provided workspace. This is
necessary as there is no shape inference functionality in Caffe2.

Definition at line 24 of file predictor_py_utils.py.

◆ create_predict_net()

def predictor_py_utils.create_predict_net (   predictor_export_meta)
Return the input prediction net.

Definition at line 11 of file predictor_py_utils.py.