frozenleaves/pytorch
1
0
Fork 0
mirror of https://github.com/pytorch/pytorch.git synced 2025-10-20 21:14:14 +08:00
Code Issues Packages Projects Releases Wiki Activity

Resolve docstring errors in throughput_benchmark.py, weak.py, _traceback.py, file_baton.py, _contextlib.py, _device.py, cpp_backtrace.py, bundled_inputs.py, run_cpu.py, hooks.py, mobile_optimizer.py, _freeze.py, __init__.py, mkldnn.py, dlpack.py (#113311)

Browse Source 
Fixes #112633

Fixed errors relating to pydocstyle in the following files. The remaining errors are not covered in this issue. `torch/utils/dlpack.py` was not modified as the errors are relating to the function signature in the first line in the docstring which must be maintained as is for proper Sphinx interpretation.

```python
def from_dlpack(ext_tensor: Any) -> 'torch.Tensor':
    """from_dlpack(ext_tensor) -> Tensor
         .....
    """
```

pydocstyle torch/utils/_contextlib.py --count
before: 4
after: 0

pydocstyle torch/backends/mps/__init__.py --count
before: 8
after: 1

**remaining errors**
```
torch/backends/mps/__init__.py:1 at module level:
        D104: Missing docstring in public package
```

pydocstyle torch/backends/xeon/run_cpu.py --count
before: 13
after: 1

**remaining errors**
```
torch/backends/xeon/run_cpu.py:864 in public function `main`:
        D103: Missing docstring in public function
```

pydocstyle torch/backends/cpu/__init__.py --count
before: 2
after: 1

**remaining errors**
```
torch/backends/cpu/__init__.py:1 at module level:
        D104: Missing docstring in public package
```

pydocstyle torch/utils/cpp_backtrace.py --count
before: 4
after: 1

**remaining errors**
```
torch/utils/cpp_backtrace.py:1 at module level:
        D100: Missing docstring in public module
```

pydocstyle torch/utils/bundled_inputs.py --count
before: 8
after: 1

**remaining errors**
```
torch/utils/bundled_inputs.py:1 at module level:
        D100: Missing docstring in public module
```

pydocstyle torch/utils/file_baton.py --count
before: 8
after: 1

**remaining errors**
```
torch/utils/file_baton.py:1 at module level:
        D100: Missing docstring in public module
```

pydocstyle torch/utils/mobile_optimizer.py --count
before: 6
after: 1

**remaining errors**
```
torch/utils/mobile_optimizer.py:8 in public class `LintCode`:
        D101: Missing docstring in public class
```

pydocstyle torch/backends/opt_einsum/__init__.py --count
before: 7
after: 5

**remaining errors**
```
torch/backends/opt_einsum/__init__.py:1 at module level:
        D104: Missing docstring in public package
torch/backends/opt_einsum/__init__.py:67 in public function `set_flags`:
        D103: Missing docstring in public function
torch/backends/opt_einsum/__init__.py:77 in public function `flags`:
        D103: Missing docstring in public function
torch/backends/opt_einsum/__init__.py:93 in public class `OptEinsumModule`:
        D101: Missing docstring in public class
torch/backends/opt_einsum/__init__.py:94 in public method `__init__`:
        D107: Missing docstring in __init__
```

pydocstyle torch/utils/_device.py --count
before:  9
after: 6

**remaining errors**
```
torch/utils/_device.py:58 in public class `DeviceContext`:
        D101: Missing docstring in public class
torch/utils/_device.py:59 in public method `__init__`:
        D107: Missing docstring in __init__
torch/utils/_device.py:62 in public method `__enter__`:
        D105: Missing docstring in magic method
torch/utils/_device.py:68 in public method `__exit__`:
        D105: Missing docstring in magic method
torch/utils/_device.py:73 in public method `__torch_function__`:
        D105: Missing docstring in magic method
torch/utils/_device.py:80 in public function `device_decorator`:
        D103: Missing docstring in public function

```

pydocstyle torch/utils/_freeze.py --count
before: 15
after: 7

**remaining errors**
```
torch/utils/_freeze.py:77 in public function `indent_msg`:
        D103: Missing docstring in public function
torch/utils/_freeze.py:89 in public class `FrozenModule`:
        D101: Missing docstring in public class
torch/utils/_freeze.py:100 in public class `Freezer`:
        D101: Missing docstring in public class
torch/utils/_freeze.py:101 in public method `__init__`:
        D107: Missing docstring in __init__
torch/utils/_freeze.py:106 in public method `msg`:
        D102: Missing docstring in public method
torch/utils/_freeze.py:185 in public method `get_module_qualname`:
        D102: Missing docstring in public method
torch/utils/_freeze.py:206 in public method `compile_string`:
        D102: Missing docstring in public method

```

pydocstyle torch/utils/throughput_benchmark.py --count
before: 25
after: 8
**remaining errors**
```
torch/utils/throughput_benchmark.py:1 at module level:
        D100: Missing docstring in public module
torch/utils/throughput_benchmark.py:27 in public class `ExecutionStats`:
        D101: Missing docstring in public class
torch/utils/throughput_benchmark.py:28 in public method `__init__`:
        D107: Missing docstring in __init__
torch/utils/throughput_benchmark.py:33 in public method `latency_avg_ms`:
        D102: Missing docstring in public method
torch/utils/throughput_benchmark.py:37 in public method `num_iters`:
        D102: Missing docstring in public method
torch/utils/throughput_benchmark.py:46 in public method `total_time_seconds`:
        D102: Missing docstring in public method
torch/utils/throughput_benchmark.py:50 in public method `__str__`:
        D105: Missing docstring in magic method
torch/utils/throughput_benchmark.py:94 in public method `__init__`:
        D107: Missing docstring in __init__

```

pydocstyle torch/utils/hooks.py --count

before: 14
after: 11

**remaining errors**
```
torch/utils/hooks.py:1 at module level:
        D100: Missing docstring in public module
torch/utils/hooks.py:23 in public method `__init__`:
        D107: Missing docstring in __init__
torch/utils/hooks.py:34 in public method `remove`:
        D102: Missing docstring in public method
torch/utils/hooks.py:44 in public method `__getstate__`:
        D105: Missing docstring in magic method
torch/utils/hooks.py:50 in public method `__setstate__`:
        D105: Missing docstring in magic method
torch/utils/hooks.py:64 in public method `__enter__`:
        D105: Missing docstring in magic method
torch/utils/hooks.py:67 in public method `__exit__`:
        D105: Missing docstring in magic method
torch/utils/hooks.py:82 in public function `warn_if_has_hooks`:
        D103: Missing docstring in public function
torch/utils/hooks.py:103 in public method `__init__`:
        D107: Missing docstring in __init__
torch/utils/hooks.py:188 in public method `setup_input_hook`:
        D102: Missing docstring in public method
torch/utils/hooks.py:197 in public method `setup_output_hook`:
        D102: Missing docstring in public method
```

pydocstyle torch/utils/_traceback.py --count
before: 19
after: 14

**remaining errors**
```
torch/utils/_traceback.py:47 in public function `report_compile_source_on_error`:
        D103: Missing docstring in public function
torch/utils/_traceback.py:160 in public class `CapturedTraceback`:
        D101: Missing docstring in public class
torch/utils/_traceback.py:163 in public method `__init__`:
        D107: Missing docstring in __init__
torch/utils/_traceback.py:167 in public method `cleanup`:
        D102: Missing docstring in public method
torch/utils/_traceback.py:170 in public method `summary`:
        D102: Missing docstring in public method
torch/utils/_traceback.py:182 in public method `__getstate__`:
        D105: Missing docstring in magic method
torch/utils/_traceback.py:190 in public method `extract`:
        D205: 1 blank line required between summary line and description (found 0)
torch/utils/_traceback.py:190 in public method `extract`:
        D400: First line should end with a period (not 't')
torch/utils/_traceback.py:213 in public method `format`:
        D205: 1 blank line required between summary line and description (found 0)
torch/utils/_traceback.py:213 in public method `format`:
        D400: First line should end with a period (not 'f')
torch/utils/_traceback.py:213 in public method `format`:
        D401: First line should be in imperative mood (perhaps 'Format', not 'Formats')
torch/utils/_traceback.py:224 in public method `format_all`:
        D200: One-line docstring should fit on one line with quotes (found 3)
torch/utils/_traceback.py:247 in private function `_extract_symbolized_tb`:
        D205: 1 blank line required between summary line and description (found 0)
torch/utils/_traceback.py:247 in private function `_extract_symbolized_tb`:
        D400: First line should end with a period (not 'f')
```

pydocstyle torch/utils/mkldnn.py --count
before: 28
after: 26

**remaining errors**
```
torch/utils/mkldnn.py:1 at module level:
        D100: Missing docstring in public module
torch/utils/mkldnn.py:4 in public class `MkldnnLinear`:
        D101: Missing docstring in public class
torch/utils/mkldnn.py:5 in public method `__init__`:
        D107: Missing docstring in __init__
torch/utils/mkldnn.py:19 in public method `__getstate__`:
        D105: Missing docstring in magic method
torch/utils/mkldnn.py:23 in public method `__setstate__`:
        D105: Missing docstring in magic method
torch/utils/mkldnn.py:29 in public method `forward`:
        D102: Missing docstring in public method
torch/utils/mkldnn.py:75 in public class `MkldnnConv1d`:
        D101: Missing docstring in public class
torch/utils/mkldnn.py:76 in public method `__init__`:
        D107: Missing docstring in __init__
torch/utils/mkldnn.py:82 in public method `__setstate__`:
        D105: Missing docstring in magic method
torch/utils/mkldnn.py:88 in public class `MkldnnConv2d`:
        D101: Missing docstring in public class
torch/utils/mkldnn.py:89 in public method `__init__`:
        D107: Missing docstring in __init__
torch/utils/mkldnn.py:100 in public method `__setstate__`:
        D105: Missing docstring in magic method
torch/utils/mkldnn.py:110 in public class `MkldnnConv3d`:
        D101: Missing docstring in public class
torch/utils/mkldnn.py:111 in public method `__init__`:
        D107: Missing docstring in __init__
torch/utils/mkldnn.py:122 in public method `__setstate__`:
        D105: Missing docstring in magic method
torch/utils/mkldnn.py:133 in public class `MkldnnBatchNorm`:
        D101: Missing docstring in public class
torch/utils/mkldnn.py:136 in public method `__init__`:
        D107: Missing docstring in __init__
torch/utils/mkldnn.py:155 in public method `__getstate__`:
        D105: Missing docstring in magic method
torch/utils/mkldnn.py:163 in public method `__setstate__`:
        D105: Missing docstring in magic method
torch/utils/mkldnn.py:171 in public method `forward`:
        D102: Missing docstring in public method
torch/utils/mkldnn.py:184 in public class `MkldnnPrelu`:
        D101: Missing docstring in public class
torch/utils/mkldnn.py:185 in public method `__init__`:
        D107: Missing docstring in __init__
torch/utils/mkldnn.py:190 in public method `__getstate__`:
        D105: Missing docstring in magic method
torch/utils/mkldnn.py:194 in public method `__setstate__`:
        D105: Missing docstring in magic method
torch/utils/mkldnn.py:199 in public method `forward`:
        D102: Missing docstring in public method
torch/utils/mkldnn.py:205 in public function `to_mkldnn`:
        D103: Missing docstring in public function
```

pydocstyle torch/utils/weak.py --count
before: 32
after: 30

**remaining errors**
```
torch/utils/weak.py:1 at module level:
        D100: Missing docstring in public module
torch/utils/weak.py:42 in public class `WeakIdRef`:
        D101: Missing docstring in public class
torch/utils/weak.py:45 in public method `__init__`:
        D107: Missing docstring in __init__
torch/utils/weak.py:54 in public method `__call__`:
        D102: Missing docstring in public method
torch/utils/weak.py:61 in public method `__hash__`:
        D105: Missing docstring in magic method
torch/utils/weak.py:64 in public method `__eq__`:
        D105: Missing docstring in magic method
torch/utils/weak.py:84 in public class `WeakIdKeyDictionary`:
        D101: Missing docstring in public class
torch/utils/weak.py:87 in public method `__init__`:
        D107: Missing docstring in __init__
torch/utils/weak.py:131 in public method `__delitem__`:
        D105: Missing docstring in magic method
torch/utils/weak.py:135 in public method `__getitem__`:
        D105: Missing docstring in magic method
torch/utils/weak.py:138 in public method `__len__`:
        D105: Missing docstring in magic method
torch/utils/weak.py:145 in public method `__repr__`:
        D105: Missing docstring in magic method
torch/utils/weak.py:148 in public method `__setitem__`:
        D105: Missing docstring in magic method
torch/utils/weak.py:151 in public method `copy`:
        D102: Missing docstring in public method
torch/utils/weak.py:162 in public method `__deepcopy__`:
        D105: Missing docstring in magic method
torch/utils/weak.py:172 in public method `get`:
        D102: Missing docstring in public method
torch/utils/weak.py:175 in public method `__contains__`:
        D105: Missing docstring in magic method
torch/utils/weak.py:182 in public method `items`:
        D102: Missing docstring in public method
torch/utils/weak.py:189 in public method `keys`:
        D102: Missing docstring in public method
torch/utils/weak.py:198 in public method `values`:
        D102: Missing docstring in public method
torch/utils/weak.py:216 in public method `popitem`:
        D102: Missing docstring in public method
torch/utils/weak.py:224 in public method `pop`:
        D102: Missing docstring in public method
torch/utils/weak.py:228 in public method `setdefault`:
        D102: Missing docstring in public method
torch/utils/weak.py:231 in public method `update`:
        D102: Missing docstring in public method
torch/utils/weak.py:241 in public method `__ior__`:
        D105: Missing docstring in magic method
torch/utils/weak.py:245 in public method `__or__`:
        D105: Missing docstring in magic method
torch/utils/weak.py:252 in public method `__ror__`:
        D105: Missing docstring in magic method
torch/utils/weak.py:262 in public method `__eq__`:
        D105: Missing docstring in magic method
torch/utils/weak.py:276 in public method `__init__`:
        D107: Missing docstring in __init__
torch/utils/weak.py:280 in public method `__call__`:
        D102: Missing docstring in public method

```

@mikaylagawarecki @jbschlosser @svekars
Pull Request resolved: https://github.com/pytorch/pytorch/pull/113311
Approved by: https://github.com/ezyang
This commit is contained in:
zabboud
2023-11-15 17:40:04 +00:00
committed by PyTorch MergeBot
parent e100ff42fd
commit 7f9fafed53
16 changed files with 107 additions and 107 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
torch/backends/cpu/__init__.py
View File

@ -6,7 +6,7 @@ __all__ = [
def get_cpu_capability() -> str:
r"""Returns cpu capability as a string value.
r"""Return cpu capability as a string value.
Possible values:
- "DEFAULT"

16
torch/backends/mps/__init__.py
View File

@ -7,22 +7,24 @@ __all__ = ["is_built", "is_available", "is_macos13_or_newer"]
def is_built() -> bool:
r"""Returns whether PyTorch is built with MPS support. Note that this
doesn't necessarily mean MPS is available; just that if this PyTorch
binary were run a machine with working MPS drivers and devices, we
would be able to use it."""
r"""Return whether PyTorch is built with MPS support.
Note that this doesn't necessarily mean MPS is available; just that
if this PyTorch binary were run a machine with working MPS drivers
and devices, we would be able to use it.
"""
return torch._C._has_mps
@_lru_cache
def is_available() -> bool:
r"""Returns a bool indicating if MPS is currently available."""
r"""Return a bool indicating if MPS is currently available."""
return torch._C._mps_is_available()
@_lru_cache
def is_macos13_or_newer(minor: int = 0) -> bool:
r"""Returns a bool indicating whether MPS is running on MacOS 13 or newer."""
r"""Return a bool indicating whether MPS is running on MacOS 13 or newer."""
return torch._C._mps_is_on_macos_13_or_newer(minor)
@ -30,7 +32,7 @@ _lib = None
def _init():
r"""Register prims as implementation of var_mean and group_norm"""
r"""Register prims as implementation of var_mean and group_norm."""
global _lib
if is_built() is False or _lib is not None:
return

4
torch/backends/opt_einsum/__init__.py
View File

@ -14,12 +14,12 @@ except ImportError:
@_lru_cache
def is_available() -> bool:
r"""Returns a bool indicating if opt_einsum is currently available."""
r"""Return a bool indicating if opt_einsum is currently available."""
return _opt_einsum is not None
def get_opt_einsum() -> Any:
r"""Returns the opt_einsum package if opt_einsum is currently available, else None."""
r"""Return the opt_einsum package if opt_einsum is currently available, else None."""
return _opt_einsum

22
torch/backends/xeon/run_cpu.py
View File

@ -1,5 +1,6 @@
"""
This is a script for launching PyTorch inference on Intel(R) Xeon(R) Scalable Processors with optimal configurations.
Single instance inference, multi-instance inference are enabled.
Note: term "instance" here doesn't refer to a cloud instance. This script is executed as a single process. It invokes
@ -140,9 +141,7 @@ logger = logging.getLogger(__name__)
class _CPUinfo:
"""
Get CPU information, such as cores list and NUMA information.
"""
"""Get CPU information, such as cores list and NUMA information."""
def __init__(self, test_input=""):
self.cpuinfo = []
@ -229,7 +228,9 @@ class _CPUinfo:
def numa_aware_check(self, core_list):
"""
Check whether all cores in core_list are in the same NUMA node. cross NUMA will reduce performance.
Check whether all cores in core_list are in the same NUMA node.
Cross NUMA will reduce performance.
We strongly advice to not use cores on different nodes.
"""
cores_numa_map = self.logical_core_node_map
@ -254,9 +255,7 @@ instance. Alternatively, please use --skip-cross-node-cores knob.",
class _Launcher:
r"""
Class for launcher
"""
r"""Class for launcher."""
msg_lib_notfound = f"Unable to find the {{0}} library file lib{{1}}.so in $CONDA_PREFIX/lib or $VIRTUAL_ENV/lib \
or /.local/lib/ or /usr/local/lib/ or /usr/local/lib64/ or /usr/lib or /usr/lib64 or \
@ -266,9 +265,7 @@ or /.local/lib/ or /usr/local/lib/ or /usr/local/lib64/ or /usr/lib or /usr/lib6
self.cpuinfo = _CPUinfo()
def add_lib_preload(self, lib_type):
"""
Enable TCMalloc/JeMalloc/intel OpenMP
"""
"""Enable TCMalloc/JeMalloc/intel OpenMP."""
library_paths = []
if "CONDA_PREFIX" in os.environ:
library_paths.append(f"{os.environ['CONDA_PREFIX']}/lib")
@ -324,6 +321,7 @@ or /.local/lib/ or /usr/local/lib/ or /usr/local/lib64/ or /usr/lib or /usr/lib6
):
"""
Enable TCMalloc/JeMalloc with LD_PRELOAD and set configuration for JeMalloc.
By default, PTMalloc will be used for PyTorch, but TCMalloc and JeMalloc can get better
memory reuse and reduce page fault to improve performance.
"""
@ -405,6 +403,7 @@ Value applied: %s. Value ignored: %s",
):
"""
Set multi-thread configuration and enable Intel openMP and TCMalloc/JeMalloc.
By default, GNU openMP and PTMalloc are used in PyTorch. but Intel openMP and TCMalloc/JeMalloc are better alternatives
to get performance benefit.
"""
@ -816,7 +815,8 @@ def _add_kmp_iomp_params(parser):
def create_args(parser=None):
"""
Helper function parsing the command line options
Parse the command line options.
@retval ArgumentParser
"""
parser.add_argument(

8
torch/utils/_contextlib.py
View File

@ -68,8 +68,9 @@ def _wrap_generator(ctx_factory, func):
def context_decorator(ctx, func):
"""
Like contextlib.ContextDecorator, but:
Like contextlib.ContextDecorator.
But with the following differences:
1. Is done by wrapping, rather than inheritance, so it works with context
managers that are implemented from C and thus cannot easily inherit from
Python classes
@ -81,7 +82,6 @@ def context_decorator(ctx, func):
be a multi-shot context manager that can be directly invoked multiple times)
or a callable that produces a context manager.
"""
assert not (callable(ctx) and hasattr(ctx, '__enter__')), (
f"Passed in {ctx} is both callable and also a valid context manager "
"(has __enter__), making it ambiguous which interface to use. If you "
@ -118,7 +118,7 @@ def context_decorator(ctx, func):
class _DecoratorContextManager:
"""Allow a context manager to be used as a decorator"""
"""Allow a context manager to be used as a decorator."""
def __call__(self, orig_func: F) -> F:
if inspect.isclass(orig_func):
@ -144,7 +144,7 @@ class _DecoratorContextManager:
class _NoParamDecoratorContextManager(_DecoratorContextManager):
"""Allow a context manager to be used as a decorator without parentheses"""
"""Allow a context manager to be used as a decorator without parentheses."""
def __new__(cls, orig_func=None):
if orig_func is None:

8
torch/utils/_device.py
View File

@ -82,9 +82,9 @@ def device_decorator(device, func):
def set_device(device):
"""
Decorator which sets the default device inside of the wrapped
function. If you would like to use this as a context manager,
use device as a context manager directly, e.g.,
``with torch.device(device)``.
Set the default device inside of the wrapped function by decorating it with this function.
If you would like to use this as a context manager, use device as a
context manager directly, e.g., ``with torch.device(device)``.
"""
return lambda func: device_decorator(torch.device(device), func)

21
torch/utils/_freeze.py
View File

@ -117,8 +117,9 @@ class Freezer:
def write_bytecode(self, install_root):
"""
Write the `.c` files containing the frozen bytecode. Shard frozen
modules evenly across the files.
Write the `.c` files containing the frozen bytecode.
Shared frozen modules evenly across the files.
"""
bytecode_file_names = [
f"bytecode_{i}.c" for i in range(NUM_BYTECODE_FILES)
@ -132,10 +133,7 @@ class Freezer:
f.close()
def write_main(self, install_root, oss, symbol_name):
"""
Write the `main.c` file containing a table enumerating all the
frozen modules.
"""
"""Write the `main.c` file containing a table enumerating all the frozen modules."""
with open(os.path.join(install_root, "main.c"), "w") as outfp:
outfp.write(MAIN_INCLUDES)
for m in self.frozen_modules:
@ -150,9 +148,7 @@ class Freezer:
outfp.write(MAIN_SUFFIX)
def write_frozen(self, m: FrozenModule, outfp):
"""
Write a single frozen module's bytecode out to a C variable.
"""
"""Write a single frozen module's bytecode out to a C variable."""
outfp.write(f"unsigned char {m.c_name}[] = {{")
for i in range(0, len(m.bytecode), 16):
outfp.write("\n\t")
@ -161,7 +157,7 @@ class Freezer:
outfp.write("\n};\n")
def compile_path(self, path: Path, top_package_path: Path):
"""Generic entry point for compiling a Path object."""
"""Entry point for compiling a Path object."""
if path.is_dir():
self.compile_package(path, top_package_path)
else:
@ -220,8 +216,9 @@ class Freezer:
@indent_msg
def compile_file(self, path: Path, top_package_path: Path):
"""
Compile a Python source file to frozen bytecode. Append the result to
`self.frozen_modules`.
Compile a Python source file to frozen bytecode.
Append the result to `self.frozen_modules`.
"""
assert path.is_file()
if path.suffix != ".py":

14
torch/utils/_traceback.py
View File

@ -131,10 +131,7 @@ def report_compile_source_on_error():
raise exc.with_traceback(tb_next) # noqa: TRY200
def shorten_filename(fn, *, base=None):
"""
Shorten a source filepath, under the assumption that anything under torch/
directory is "obvious" and doesn't need to be shown to user.
"""
"""Shorten a source filepath, with the assumption that torch/ subdirectories don't need to be shown to user."""
if base is None:
base = os.path.dirname(os.path.dirname(__file__))
# Truncate torch/foo.py to foo.py
@ -147,8 +144,9 @@ def shorten_filename(fn, *, base=None):
def format_frame(frame, *, base=None, line=False):
"""
Format a FrameSummary in a short way, without printing full absolute path
or code. The idea is the result fits on a single line.
Format a FrameSummary in a short way, without printing full absolute path or code.
The idea is the result fits on a single line.
"""
extra_line = ""
if line:
@ -156,9 +154,7 @@ def format_frame(frame, *, base=None, line=False):
return f"{extra_line}{shorten_filename(frame.filename, base=base)}:{frame.lineno} in {frame.name}"
def format_traceback_short(tb):
"""
Format a TracebackType in a short way, printing only the inner-most frame.
"""
"""Format a TracebackType in a short way, printing only the inner-most frame."""
return format_frame(traceback.extract_tb(tb)[-1])
class CapturedTraceback:

29
torch/utils/bundled_inputs.py
View File

@ -11,25 +11,26 @@ T = TypeVar("T")
MAX_RAW_TENSOR_SIZE = 16
class InflatableArg(NamedTuple):
""" Helper type for bundled inputs.
"""Helper type for bundled inputs.
'value' is the compressed/deflated input that is stored in the model. Value
must be of the same type as the argument to the function that it is a deflated
input for.
'value' is the compressed/deflated input that is stored in the model. Value
must be of the same type as the argument to the function that it is a deflated
input for.
'fmt' is a formatable code string that is executed to inflate the compressed data into
the appropriate input. It can use 'value' as an input to the format str. It must result
in a value of the same type as 'value'.
'fmt' is a formatable code string that is executed to inflate the compressed data into
the appropriate input. It can use 'value' as an input to the format str. It must result
in a value of the same type as 'value'.
'fmt_fn' is a formatable function code string that is executed to inflate the compressed
data into the appropriate input. It must result in a value of the same type as 'value'.
The function name should be the formatable part of the string.
'fmt_fn' is a formatable function code string that is executed to inflate the compressed
data into the appropriate input. It must result in a value of the same type as 'value'.
The function name should be the formatable part of the string.
Note: Only top level InflatableArgs can be inflated. i.e. you cannot place
an inflatable arg inside of some other structure. You should instead create
an inflatable arg such that the fmt code string returns the full structure
of your input.
"""
value: Any
fmt: str = "{}"
fmt_fn: str = ""
@ -42,8 +43,9 @@ def bundle_inputs(
*,
_receive_inflate_expr: Optional[List[str]] = None,
) -> torch.jit.ScriptModule:
"""Creates and returns a copy of the specified model with inputs attached. The original model is
not mutated or changed in any way.
"""Create and return a copy of the specified model with inputs attached.
The original model is not mutated or changed in any way.
Models with bundled inputs can be invoked in a uniform manner by
benchmarking and code coverage tools.
@ -129,7 +131,7 @@ def augment_model_with_bundled_inputs(
info: Optional[List[str]] = None, # Optional argument to provide info about forward or its inputs
skip_size_check=False,
) -> None:
""" Add bundled sample inputs to a model for the forward function.
"""Add bundled sample inputs to a model for the forward function.
Models with bundled inputs can be invoked in a uniform manner by
benchmarking and code coverage tools.
@ -159,7 +161,6 @@ def augment_model_with_bundled_inputs(
- `inputs` is a list of inputs of form List[Tuple[Any, ...]]. A list of tuples where the elements
of each tuple are the args that make up one input.
"""
if not isinstance(model, torch.jit.ScriptModule):
raise Exception("Only ScriptModule is supported.")

4
torch/utils/cpp_backtrace.py
View File

@ -2,10 +2,10 @@ from torch._C import _get_cpp_backtrace
def get_cpp_backtrace(frames_to_skip=0, maximum_number_of_frames=64) -> str:
r"""
Returns a string containing the C++ stack trace of the current thread.
Return a string containing the C++ stack trace of the current thread.
Args:
frames_to_skip (int): the number of frames to skip from the top of the stack
maximum_number_of_frames (int): the maximum number of frames to return
"""
return _get_cpp_backtrace(frames_to_skip, maximum_number_of_frames)

20
torch/utils/file_baton.py
View File

@ -3,28 +3,28 @@ import time
class FileBaton:
'''A primitive, file-based synchronization utility.'''
"""A primitive, file-based synchronization utility."""
def __init__(self, lock_file_path, wait_seconds=0.1):
'''
Creates a new :class:`FileBaton`.
"""
Create a new :class:`FileBaton`.
Args:
lock_file_path: The path to the file used for locking.
wait_seconds: The seconds to periodically sleep (spin) when
calling ``wait()``.
'''
"""
self.lock_file_path = lock_file_path
self.wait_seconds = wait_seconds
self.fd = None
def try_acquire(self):
'''
Tries to atomically create a file under exclusive access.
"""
Try to atomically create a file under exclusive access.
Returns:
True if the file could be created, else False.
'''
"""
try:
self.fd = os.open(self.lock_file_path, os.O_CREAT | os.O_EXCL)
return True
@ -32,17 +32,17 @@ class FileBaton:
return False
def wait(self):
'''
"""
Periodically sleeps for a certain amount until the baton is released.
The amount of time slept depends on the ``wait_seconds`` parameter
passed to the constructor.
'''
"""
while os.path.exists(self.lock_file_path):
time.sleep(self.wait_seconds)
def release(self):
'''Releases the baton and removes its file.'''
"""Release the baton and removes its file."""
if self.fd is not None:
os.close(self.fd)

4
torch/utils/hooks.py
View File

@ -70,7 +70,8 @@ class RemovableHandle:
def unserializable_hook(f):
"""
Decorator which marks a function as an unserializable hook.
Mark a function as an unserializable hook with this decorator.
This suppresses warnings that would otherwise arise if you attempt
to serialize a tensor that has a hook.
"""
@ -91,6 +92,7 @@ def warn_if_has_hooks(tensor):
class BackwardHook:
"""
A wrapper class to implement nn.Module backward hooks.
It handles:
- Ignoring non-Tensor inputs and replacing them by None before calling the user hook
- Generating the proper Node to capture a set of Tensor's gradients

3
torch/utils/mkldnn.py
View File

@ -34,7 +34,8 @@ class MkldnnLinear(torch.jit.ScriptModule):
class _MkldnnConvNd(torch.jit.ScriptModule):
"""Common base of MkldnnConv1d and MkldnnConv2d"""
"""Common base of MkldnnConv1d and MkldnnConv2d."""
__constants__ = ['stride', 'padding', 'dilation', 'groups']
def __init__(self, dense_module):

10
torch/utils/mobile_optimizer.py
View File

@ -1,6 +1,4 @@
"""
This module contains utility method for mobile model optimization and lint.
"""
"""This module contains utility method for mobile model optimization and lint."""
import torch
from enum import Enum
@ -19,6 +17,8 @@ def optimize_for_mobile(
preserved_methods: Optional[List[AnyStr]] = None,
backend: str = 'CPU') -> torch.jit.RecursiveScriptModule:
"""
Optimize a torch script module for mobile deployment.
Args:
script_module: An instance of torch script module with type of ScriptModule.
optimization_blocklist: A set with type of MobileOptimizerType. When set is not passed,
@ -77,8 +77,10 @@ def optimize_for_mobile(
def generate_mobile_module_lints(script_module: torch.jit.ScriptModule):
"""
Generate a list of lints for a given torch script module.
Args:
script_module: An instance of torch script module with type of ScriptModule
script_module: An instance of torch script module with type of ScriptModule.
Returns:
lint_map: A list of dictionary that contains modules lints

44
torch/utils/throughput_benchmark.py
View File

@ -3,7 +3,7 @@ import torch._C
def format_time(time_us=None, time_ms=None, time_s=None):
'''Defines how to format time'''
"""Define time formatting."""
assert sum([time_us is not None, time_ms is not None, time_s is not None]) == 1
US_IN_SECOND = 1e6
@ -39,9 +39,7 @@ class ExecutionStats:
@property
def iters_per_second(self):
'''
Returns total number of iterations per second across all calling threads
'''
"""Return total number of iterations per second across all calling threads."""
return self.num_iters / self.total_time_seconds
@property
@ -59,13 +57,14 @@ class ExecutionStats:
class ThroughputBenchmark:
'''
This class is a wrapper around a c++ component throughput_benchmark::ThroughputBenchmark
responsible for executing a PyTorch module (nn.Module or ScriptModule)
under an inference server like load. It can emulate multiple calling threads
to a single module provided. In the future we plan to enhance this component
to support inter and intra-op parallelism as well as multiple models
running in a single process.
"""
This class is a wrapper around a c++ component throughput_benchmark::ThroughputBenchmark.
This wrapper on the throughput_benchmark::ThroughputBenchmark component is responsible
for executing a PyTorch module (nn.Module or ScriptModule) under an inference
server like load. It can emulate multiple calling threads to a single module
provided. In the future we plan to enhance this component to support inter and
intra-op parallelism as well as multiple models running in a single process.
Please note that even though nn.Module is supported, it might incur an overhead
from the need to hold GIL every time we execute Python code or pass around
@ -90,8 +89,7 @@ class ThroughputBenchmark:
... )
>>> print("Avg latency (ms): {}".format(stats.latency_avg_ms))
>>> print("Number of iterations: {}".format(stats.num_iters))
'''
"""
def __init__(self, module):
if isinstance(module, torch.jit.ScriptModule):
@ -100,21 +98,23 @@ class ThroughputBenchmark:
self._benchmark = torch._C.ThroughputBenchmark(module)
def run_once(self, *args, **kwargs):
'''
"""
Given input id (input_idx) run benchmark once and return prediction.
This is useful for testing that benchmark actually runs the module you
want it to run. input_idx here is an index into inputs array populated
by calling add_input() method.
'''
"""
return self._benchmark.run_once(*args, **kwargs)
def add_input(self, *args, **kwargs):
'''
Store a single input to a module into the benchmark memory and keep it
there. During the benchmark execution every thread is going to pick up a
"""
Store a single input to a module into the benchmark memory and keep it there.
During the benchmark execution every thread is going to pick up a
random input from the all the inputs ever supplied to the benchmark via
this function.
'''
"""
self._benchmark.add_input(*args, **kwargs)
def benchmark(
@ -123,7 +123,9 @@ class ThroughputBenchmark:
num_warmup_iters=10,
num_iters=100,
profiler_output_path=""):
'''
"""
Run a benchmark on the module.
Args:
num_warmup_iters (int): Warmup iters are used to make sure we run a module
a few times before actually measuring things. This way we avoid cold
@ -147,7 +149,7 @@ class ThroughputBenchmark:
It currently has two fields:
- num_iters - number of actual iterations the benchmark have made
- avg_latency_ms - average time it took to infer on one input example in milliseconds
'''
"""
config = torch._C.BenchmarkConfig()
config.num_calling_threads = num_calling_threads
config.num_warmup_iters = num_warmup_iters

5
torch/utils/weak.py
View File

@ -269,10 +269,7 @@ WeakTensorKeyDictionary = WeakIdKeyDictionary
class TensorWeakRef:
"""
Wrapper around a weak ref of a Tensor that handles the _fix_weakref() call required
when unwrapping a Tensor weakref.
"""
"""Wrapper around a weak ref of a Tensor that handles the _fix_weakref() call required when unwrapping a Tensor weakref."""
ref: WeakRef[Tensor]