Caffe2 - Python API
A deep learning, cross platform ML framework
Classes | Functions | Variables
torch._jit_internal Namespace Reference

Classes

class  BroadcastingListCls
 
class  DictCls
 
class  DictInstance
 
class  ListCls
 
class  ListInstance
 
class  TupleCls
 
class  TupleInstance
 

Functions

def createResolutionCallback (frames_up=0)
 
def weak_script (fn, _frames_up=0)
 
def weak_module (cls)
 
def weak_script_method (fn)
 
def boolean_dispatch (arg_name, arg_index, default, if_true, if_false, module_name, func_name)
 
def ignore (fn)
 
def is_tuple (ann)
 
def is_list (ann)
 
def is_dict (ann)
 

Variables

 compiled_weak_fns
 
 weak_script_methods
 
 weak_modules
 
 weak_types
 
 boolean_dispatched
 
 ignored_fns
 
 COMPILATION_PENDING
 
 COMPILED
 
 Tuple
 
 List
 
 Dict
 
 BroadcastingList1
 

Detailed Description

The weak_script annotation needs to be here instead of inside torch/jit/ so it
can be used in other places in torch/ (namely torch.nn) without running into
circular dependency problems

Function Documentation

def torch._jit_internal.boolean_dispatch (   arg_name,
  arg_index,
  default,
  if_true,
  if_false,
  module_name,
  func_name 
)
Dispatches to either of 2 weak script functions based on a boolean argument.
In TorchScript, the boolean argument must be constant so that the correct
function to use can be determined at compile time.

Definition at line 114 of file _jit_internal.py.

def torch._jit_internal.createResolutionCallback (   frames_up = 0)
Creates a function which, given a string variable name,
returns the value of the variable in the scope of the caller of
the function which called createResolutionCallback (by default).

This is used to enable access in-scope Python variables inside
TorchScript fragments.

frames_up is number of additional frames to go up on the stack.
The default value is 0, which correspond to the frame of the caller
of createResolutionCallback. Also for example, if frames_up is set
to 1, then the frame of the caller's caller of createResolutionCallback
will be taken.

For example, the following program prints 2::

    def bar():
        cb = createResolutionCallback(1)
        print(cb("foo"))

    def baz():
        foo = 2
        bar()

    baz()

Definition at line 35 of file _jit_internal.py.

def torch._jit_internal.weak_script (   fn,
  _frames_up = 0 
)
Marks a function as a weak script function. When used in a script function
or ScriptModule, the weak script function will be lazily compiled and
inlined in the graph. When not used in a script function, the weak script
annotation has no effect.

Definition at line 84 of file _jit_internal.py.