Unknown builtin op: aten::bool

jit
1

Which function can be used to replace tensor.bool()?

Traceback (most recent call last):
  File "/home/dai/scripts/mobileocr/detector/mobilenet_east_deploy_v2.py", line 311, in <module>
    script_module = torch.jit.script(net)
  File "/home/dai/py36env/lib/python3.6/site-packages/torch/jit/__init__.py", line 1203, in script
    return torch.jit.torch.jit._recursive.recursive_script(obj)
  File "/home/dai/py36env/lib/python3.6/site-packages/torch/jit/_recursive.py", line 173, in recursive_script
    return copy_to_script_module(mod, overload_stubs + stubs)
  File "/home/dai/py36env/lib/python3.6/site-packages/torch/jit/_recursive.py", line 95, in copy_to_script_module
    torch.jit._create_methods_from_stubs(script_module, stubs)
  File "/home/dai/py36env/lib/python3.6/site-packages/torch/jit/__init__.py", line 1423, in _create_methods_from_stubs
    self._c._create_methods(self, defs, rcbs, defaults)
  File "/home/dai/py36env/lib/python3.6/site-packages/torch/jit/_recursive.py", line 222, in try_compile_fn
    return torch.jit.script(fn, _rcb=rcb)
  File "/home/dai/py36env/lib/python3.6/site-packages/torch/jit/__init__.py", line 1226, in script
    fn = torch._C._jit_script_compile(qualified_name, ast, _rcb, get_default_args(obj))
  File "/home/dai/py36env/lib/python3.6/site-packages/torch/jit/_recursive.py", line 222, in try_compile_fn
    return torch.jit.script(fn, _rcb=rcb)
  File "/home/dai/py36env/lib/python3.6/site-packages/torch/jit/__init__.py", line 1226, in script
    fn = torch._C._jit_script_compile(qualified_name, ast, _rcb, get_default_args(obj))
  File "/home/dai/py36env/lib/python3.6/site-packages/torch/jit/_recursive.py", line 222, in try_compile_fn
    return torch.jit.script(fn, _rcb=rcb)
  File "/home/dai/py36env/lib/python3.6/site-packages/torch/jit/__init__.py", line 1226, in script
    fn = torch._C._jit_script_compile(qualified_name, ast, _rcb, get_default_args(obj))
RuntimeError: 
Unknown builtin op: aten::bool.
Here are some suggestions: 
	aten::Bool
	aten::roll

The original call is:
at /home/dai/scripts/mobileocr/detector/mobilenet_east_deploy_v2.py:291:88
def is_valid_poly_torch(res,score_shape,scale:int):
    # cnt = 0
    # for i in range(res.shape[1]):
    #     if res[0,i] < 0 or res[0,i] >= score_shape[1] * 4 or \
    #         res[1,i] < 0 or res[1,i] >= score_shape[0] * 4:
    #         cnt += 1
    # return True if cnt <= 1 else False
    print("res shape",res.shape)
    cnt = torch.sum(
        (res[:,0,:] < 0) + (res[:,0,:] >= score_shape[1] * scale) + (res[:,1,:] < 0) + (res[:,1,:] >= score_shape[0] * scale).bool(),
                                                                                        ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ <--- HERE
        dim = 1
    )
    print("cnt shape",cnt.shape)
    return cnt <= 1
2

This is likely a bug, can you open an issue on GitHub? Thanks!

3

Thank you for your replay, I opened an issue on Github:

1 Like