|
|
|
#!/usr/bin/env python
|
|
|
|
# -*- encoding: utf-8 -*-
|
|
|
|
|
|
|
|
import inspect
|
|
|
|
|
|
|
|
from colossalai.legacy.registry import *
|
|
|
|
|
|
|
|
|
|
|
|
def build_from_config(module, config: dict):
|
|
|
|
"""Returns an object of :class:`module` constructed from `config`.
|
|
|
|
|
|
|
|
Args:
|
|
|
|
module: A python or user-defined class
|
|
|
|
config: A python dict containing information used in the construction of the return object
|
|
|
|
|
|
|
|
Returns: An ``object`` of interest
|
|
|
|
|
|
|
|
Raises:
|
|
|
|
AssertionError: Raises an AssertionError if `module` is not a class
|
|
|
|
|
|
|
|
"""
|
|
|
|
assert inspect.isclass(module), "module must be a class"
|
|
|
|
return module(**config)
|
|
|
|
|
|
|
|
|
|
|
|
def build_from_registry(config, registry: Registry):
|
|
|
|
r"""Returns an object constructed from `config`, the type of the object
|
|
|
|
is specified by `registry`.
|
|
|
|
|
|
|
|
Note:
|
|
|
|
the `config` is used to construct the return object such as `LAYERS`, `OPTIMIZERS`
|
|
|
|
and other support types in `registry`. The `config` should contain
|
|
|
|
all required parameters of corresponding object. The details of support
|
|
|
|
types in `registry` and the `mod_type` in `config` could be found in
|
|
|
|
`registry <https://github.com/hpcaitech/ColossalAI/blob/main/colossalai/registry/__init__.py>`_.
|
|
|
|
|
|
|
|
Args:
|
|
|
|
config (dict or :class:`colossalai.context.colossalai.context.Config`): information
|
|
|
|
used in the construction of the return object.
|
|
|
|
registry (:class:`Registry`): A registry specifying the type of the return object
|
|
|
|
|
|
|
|
Returns:
|
|
|
|
A Python object specified by `registry`.
|
|
|
|
|
|
|
|
Raises:
|
|
|
|
Exception: Raises an Exception if an error occurred when building from registry.
|
|
|
|
"""
|
|
|
|
config_ = config.copy() # keep the original config untouched
|
|
|
|
assert isinstance(registry, Registry), f"Expected type Registry but got {type(registry)}"
|
|
|
|
|
|
|
|
mod_type = config_.pop("type")
|
|
|
|
assert registry.has(mod_type), f"{mod_type} is not found in registry {registry.name}"
|
|
|
|
try:
|
|
|
|
obj = registry.get_module(mod_type)(**config_)
|
|
|
|
except Exception as e:
|
|
|
|
print(f"An error occurred when building {mod_type} from registry {registry.name}", flush=True)
|
|
|
|
raise e
|
|
|
|
|
|
|
|
return obj
|
|
|
|
|
|
|
|
|
|
|
|
def build_gradient_handler(config, model, optimizer):
|
|
|
|
"""Returns a gradient handler object of :class:`BaseGradientHandler` constructed from `config`,
|
|
|
|
`model` and `optimizer`.
|
|
|
|
|
|
|
|
Args:
|
|
|
|
config (dict or :class:`colossalai.context.Config`): A python dict or
|
|
|
|
a :class:`colossalai.context.Config` object containing information
|
|
|
|
used in the construction of the ``GRADIENT_HANDLER``.
|
|
|
|
model (:class:`nn.Module`): A model containing parameters for the gradient handler
|
|
|
|
optimizer (:class:`torch.optim.Optimizer`): An optimizer object containing parameters for the gradient handler
|
|
|
|
|
|
|
|
Returns:
|
|
|
|
An object of :class:`colossalai.legacy.engine.BaseGradientHandler`
|
|
|
|
"""
|
|
|
|
config_ = config.copy()
|
|
|
|
config_["model"] = model
|
|
|
|
config_["optimizer"] = optimizer
|
Develop/experiments (#59)
* Add gradient accumulation, fix lr scheduler
* fix FP16 optimizer and adapted torch amp with tensor parallel (#18)
* fixed bugs in compatibility between torch amp and tensor parallel and performed some minor fixes
* fixed trainer
* Revert "fixed trainer"
This reverts commit 2e0b0b76990e8d4e337add483d878c0f61cf5097.
* improved consistency between trainer, engine and schedule (#23)
Co-authored-by: 1SAA <c2h214748@gmail.com>
* Split conv2d, class token, positional embedding in 2d, Fix random number in ddp
Fix convergence in cifar10, Imagenet1000
* Integrate 1d tensor parallel in Colossal-AI (#39)
* fixed 1D and 2D convergence (#38)
* optimized 2D operations
* fixed 1D ViT convergence problem
* Feature/ddp (#49)
* remove redundancy func in setup (#19) (#20)
* use env to control the language of doc (#24) (#25)
* Support TP-compatible Torch AMP and Update trainer API (#27)
* Add gradient accumulation, fix lr scheduler
* fix FP16 optimizer and adapted torch amp with tensor parallel (#18)
* fixed bugs in compatibility between torch amp and tensor parallel and performed some minor fixes
* fixed trainer
* Revert "fixed trainer"
This reverts commit 2e0b0b76990e8d4e337add483d878c0f61cf5097.
* improved consistency between trainer, engine and schedule (#23)
Co-authored-by: 1SAA <c2h214748@gmail.com>
Co-authored-by: 1SAA <c2h214748@gmail.com>
Co-authored-by: ver217 <lhx0217@gmail.com>
* add an example of ViT-B/16 and remove w_norm clipping in LAMB (#29)
* add explanation for ViT example (#35) (#36)
* support torch ddp
* fix loss accumulation
* add log for ddp
* change seed
* modify timing hook
Co-authored-by: Frank Lee <somerlee.9@gmail.com>
Co-authored-by: 1SAA <c2h214748@gmail.com>
Co-authored-by: binmakeswell <binmakeswell@gmail.com>
* Feature/pipeline (#40)
* remove redundancy func in setup (#19) (#20)
* use env to control the language of doc (#24) (#25)
* Support TP-compatible Torch AMP and Update trainer API (#27)
* Add gradient accumulation, fix lr scheduler
* fix FP16 optimizer and adapted torch amp with tensor parallel (#18)
* fixed bugs in compatibility between torch amp and tensor parallel and performed some minor fixes
* fixed trainer
* Revert "fixed trainer"
This reverts commit 2e0b0b76990e8d4e337add483d878c0f61cf5097.
* improved consistency between trainer, engine and schedule (#23)
Co-authored-by: 1SAA <c2h214748@gmail.com>
Co-authored-by: 1SAA <c2h214748@gmail.com>
Co-authored-by: ver217 <lhx0217@gmail.com>
* add an example of ViT-B/16 and remove w_norm clipping in LAMB (#29)
* add explanation for ViT example (#35) (#36)
* optimize communication of pipeline parallel
* fix grad clip for pipeline
Co-authored-by: Frank Lee <somerlee.9@gmail.com>
Co-authored-by: 1SAA <c2h214748@gmail.com>
Co-authored-by: binmakeswell <binmakeswell@gmail.com>
* optimized 3d layer to fix slow computation ; tested imagenet performance with 3d; reworked lr_scheduler config definition; fixed launch args; fixed some printing issues; simplified apis of 3d layers (#51)
* Update 2.5d layer code to get a similar accuracy on imagenet-1k dataset
* update api for better usability (#58)
update api for better usability
Co-authored-by: 1SAA <c2h214748@gmail.com>
Co-authored-by: ver217 <lhx0217@gmail.com>
Co-authored-by: puck_WCR <46049915+WANG-CR@users.noreply.github.com>
Co-authored-by: binmakeswell <binmakeswell@gmail.com>
Co-authored-by: アマデウス <kurisusnowdeng@users.noreply.github.com>
Co-authored-by: BoxiangW <45734921+BoxiangW@users.noreply.github.com>
3 years ago
|
|
|
return build_from_registry(config_, GRADIENT_HANDLER)
|