Add PTQ and exporting function
1. Add Post-Training Quantization
1.1 Abstract some functions from QAT to Quantization class
1.2 Add Post-Training Quantization by extending Quantization class
1.3 Add observers for PTQ
1.4 Add unittest for PTQ
2. Add exporting function for QAT and PTQ

* 为split增加取值范围维度的判断

* 为glu的axis进行取值判断并添加单测

* 完善glu的单测

* fix glu

* add upsample 0d test

* update api references

* update api references

* update api reference

* alpha_dropout supports zero_dim

* add test

* [Divide by 0 Error] add normalize check

* [Divide by 0 Error] normalize check migrate to c++

* fix cross_entropy

* update

* add input dimension check for max_unpool2d/max_unpool3d

* add unittest

* paddle.nn.functional.softmax
* paddle.nn.functional.log_softmax
* paddle.nn.functional.gumbel_softmax
* paddle.nn.functional.prelu

remove fluid.initializer.UniformInitializer, ConstantInitializer, NormalInitializer, TruncatedNormalInitializer, XavierInitializer, BilinearInitializer, MSRAInitializer, NumpyArrayInitializer and calculate_gain.. (#49498)

* move UniformInitializer and ConstantInitializer

* more modify

* circular import resolved

* another circular import resolved?

* more circular import 2

* circular import 3

* change import paddle in metric.py

* BuildStrategy import from fluid

* modify the framework import path in common.py

* change rnn.py import, from static to original framework

* change import static in the nn folder

* default_main_program should import from common_ops_import

* add import paddle in param_attr.py

* use core not paddle module for using VarDesc

* another old uniform

* mistake that use Uniform instead of UniformInitializer

* modify UniformInitializer doc

* move fluid.NormalInitializer to nn.initializer.NormalInitializer

* remove import of Normal in fluid.layers.nn.py

* remove more import of old Normal

* remove more import of old Normal

* sample code modify and tests modify import

* is_listen_failed passing arg should be log file

* problem solved

* a mistake solved

* comments resoleved and remove paddle.fluid.initializer.TruncatedNormalInitializer

* remove paddle.fluid.initializer.XavierInitializer and paddle.fluid.initializer.MSRAInitializer

* remove paddle.fluid.initializer.BilinearInitializer NumpyArrayInitializer and set_global_initializer

* change fluid to static

* change static to fluid to avoid circular import in distributed_strategy.py

* fix example code and test_initializer

* ValueType

* sample code fix

* change set_global_initializer back to fluid

* put paddle.static.BuildStrategy.ReduceStrategy into the fuction to avoid circular import

* remove calculate_gain, delete BilinearInitializer and revert set_global_initializer

* change the time of using UniformInitializer, ConstantInitializer, NormalInitializer, TruncatedNormalInitializer, XavierInitializer, MSRAInitializer, NumpyArrayInitializer as few as possible

* fix argument incampatible

* fix more arg incompatible

* fix test_prelu_op_xpu.py Constant

* fix inaccurate doc

* more doc fix: default value

* add clip_grad_norm_ api.

* fix docs and some details according to the comments.

* fix code style.

* fix no_grad problem, and fix doc.

* fix code style.

* fix doc and remove type information

* support 0d tensor for interpolate

* support 0d tensor for interpolate

* add xpu unittest for interp

* update unittest for interpolate

* fix coverage

* fix code style

* fix for coverage

* fix coverage

* add dimension check for interpolate

* modify dimension check for interpolate

* add unittest to size check for interpolate

* fix incorrect shape check for interpolate

* split size check and add unittests

* [Eager] polish some apis logic

* polish api logic

* [PHI] rrelu add yaml

* polish

* polish

* [Eager] polish some api logic

* fix split

* revover

* Add tools for quantization-aware training
1. Expose an API named paddle.quantization.QAT
2. Define a wrapper class to insert quanters into model for QAT
3. Add some functions in QuantConfig for QAT
4. Add unittest for QAT

* Add QuantedConv2D and QuantedLinear for QAT

* Add paddle.nn.quant.qat to setup.py

* fix nll_loss

* fix nll_loss

* update

* update

* update

* fix

* [Zero-Dim] support input 0D Tensor for maximum,minimum,allclose,sigmoid_focal_loss

* [Zero-Dim] add backward test for sigmoid_focal_loss with 0-D input Tensor

* [Eager] polish several ops

* rm useless code

* remove fluid.save_dygraph and fluid.load_dygraph use paddle.save and paddle.load instead

* move Sequential to paddle.nn

* modify convert_call_func.py Sequential reference

* remove related unitests

* remove fluid.dynamic.Sequntial

* test remove conver_call_func

* fix conflicts

* fix typro

* fix unitests

* fix sample_code

* fix unitest

* fix __init__

* check weight shape of conv1d_transpose

* add unittest case

* 1219

* temporarily change the num_diff_files limit, test=document_fix

* Revert "temporarily change the num_diff_files limit, test=document_fix"

This reverts commit 8e70f00ef468d2dad0e38b3da06295ed62990d20.

* for codestyle

* remove duplicate license

* `static mode` -> `static graph mode`

* Update hybrid_parallel_inference.py

* Update layer_function_generator.py

* Update manipulation.py

* reset
Co-authored-by: NLigoml <39876205+Ligoml@users.noreply.github.com>
Co-authored-by: NSigureMo <sigure.qaq@gmail.com>

* rm legacy

* clear in_legacy

* fix tracer

* rm legacy nn part2

* rm _non_static_mode

* modify

* modify unpool test

* modify unpool test

* modify loss

* keep legacy for layer_norm