b84d4ae31c
Fix bug of Model.save ( #27815 )
...
* fix model bugs, inputs can be InputSpec instance
* correct error message
4 years ago
f3e2580cf0
Fix the param of swish ( #27824 )
4 years ago
070ac9590c
Add double grad in Squeeze and Unsqueeze ( #27810 )
...
* Add double grad in Squeeze and Unsqueeze
* Add double grad in Squeeze and Unsqueeze
4 years ago
d4359b0f39
add the kunlun kernel for the paddle 2.0
...
Add xpu kernel for KUNLUN core:
* accuracy op
* sign op
* scale op
* sum op
Add default atol in xpu unittest.
4 years ago
4676f03cbb
fix summary ( #27820 )
4 years ago
840d54de9b
add XPU support for shape op and reshape op ( #27804 )
4 years ago
0a1862d1d2
fleet combine amp dgc recompute meta optimizer ( #27643 )
4 years ago
8fabb1c32f
Add test attribute in channelwise_quant op, test=develop ( #27742 )
...
* Add test attribute in channelwise_quant op, test=develop
4 years ago
81d3992c47
Fix docker build error ( #27735 )
4 years ago
9b49f02441
Polish jit.save/load design & remove paddle.SaveLoadConfig ( #27623 )
...
* replace config by kwargs
* change save path form dir to prefix
* fix failed unittests
* revert unittest name change
* polish en docs
* add more tests for coverage
4 years ago
74d3a55072
Add Swish and ThresholdedReLU for API 2.0 ( #27758 )
4 years ago
ad99e638fd
add double grad op for matmul ( #27776 )
...
* add matmul doublegrad op
* fix compile errors
* modify code according to review
* delete float16
4 years ago
c425cf1822
[API 2.0]Update 2.0 api from fluid to paddle ( #27802 )
4 years ago
bf187c7577
Polish the documentation and examples of paddle.static.nn.fc. ( #27768 )
...
* Reimplement paddle.static.nn.fc, mainly change the parameters and English documentation.
* Polish the documentation format.
4 years ago
0025e0d87b
refine APIs: brelu, hardsigmoid, hardswish, maxout ( #27658 )
4 years ago
5098891fdf
add softmax xpu kernel ( #27700 )
4 years ago
65c06141b6
disable_fuse_all_reduce ( #27746 )
...
* disable_fuse_all_reduce
* fix test
* fix ut
4 years ago
f6ad2375be
fix pool3d bug, test=develop ( #27718 )
...
* fix pool3d bug, test=develop
* fix unitest, test=develop
* fix test and fix pool2d bug, test=develop
4 years ago
0d27591642
save operator version infomation to program desc, test=develop ( #27668 )
4 years ago
00d401ec1a
Add api of constant in paddle.nn.initializer ( #27786 )
...
* Add api of constant in paddle.nn.initializer
* Add api of constant in paddle.nn.initializer
* Add api of constant in paddle.nn.initializer
* Add api of constant in paddle.nn.initializer
* Add api of constant in paddle.nn.initializer
* Add api of constant in paddle.nn.initializer
* Add api of constant in paddle.nn.initializer
4 years ago
c4b1faa469
modified sample code of add_position_encoding to use paddle.randn, test=document_fix ( #27679 )
4 years ago
d3b98f0d84
Fix dynamic parallel train mode for hapi ( #27787 )
...
* fix dynamic parallel for hapi
* fix code style
4 years ago
b53970ee36
Fix cross, cumsum op docs test=document_fix
...
Fix cross, cumsum op docs
4 years ago
c52b6bbfa9
add alias for RNN APIs from paddle.nn.layer.rnn explicitly ( #27784 )
4 years ago
836ee3b0c8
Polish the english documentation and example of paddle.nn.Linear and paddle.nn.functional.linear ( #27759 )
4 years ago
061240b34a
remove beam_search and beam_search_decode api in paddle.nn ( #27660 )
4 years ago
395cb561aa
refine logsumexp error message and docs ( #27713 )
4 years ago
606611d351
[oneDNN] GRU BF16 kernel ( #27731 )
4 years ago
baddedfdf1
fix ut test=develop ( #27760 )
4 years ago
6da552a22f
Update initializer examples of Bilinear ( #27709 )
4 years ago
7ecbc465c1
reimplement paddle.nn.functional.sigmoid_focal_loss ( #27748 )
...
* reimplement paddle.nn.functional.sigmoid_focal_loss. test=develop
* fix reduction error message. test=develop
* fix exp. test=develop
* reset the shape of logit. test=develop
* delete disable_static in example. test=develop
4 years ago
994438b109
change clip grad api, test=develop ( #27767 )
4 years ago
d84eb9b33f
keep network mode unchange when use summary api ( #27754 )
...
* keep summary mode unchange
* add no grad decorator
4 years ago
b9c7c66ea5
add type promotion ( #27756 )
4 years ago
9089841b6e
Fix bilateral inference shape bug ( #26822 )
...
* fix bilateral bug
4 years ago
6076d0a5df
modify doc for bilinear_tensor_product, test=develop ( #27613 )
4 years ago
bcc34724c2
polish api code & example ( #27696 )
4 years ago
c826bcb2ec
modify doc for ParameterList and LayerList ( #27609 )
...
* modify doc for ParameterList and LayerList, test=develop
* add empty line after code-block, test=develop
4 years ago
aaa3ee65e4
modify doc for unique_name.guard unique_name.generate unique_name.switch, test=develop ( #27605 )
4 years ago
7ca66f1e06
modify Sequential doc, test=develop ( #27608 )
4 years ago
7698e19928
modify doc for paddle.nn.Layer ( #27624 )
...
* modify doc for Layer, test=develop
* modify doc for Layer2, test=develop
* set dtype default value to float32, test=develop
* add example code for paddle.nn.Layer, test=develop
* set create_parameter and create_variable dtype default value to None, test=develop
* modify some example code, tet=develop
* refine, test=develop
* del no ues code, test=develop
* modify doc, example code, args, test=develop
* modify doc, test=develop
4 years ago
7793fd2877
add huber_loss to fix ci, test=develop ( #27766 )
4 years ago
de60c54938
fix doc and example code of huber_loss and npair_loss ( #27678 )
...
* fix huber_loss ans npair_loss doc and example code, test=document_fix
* remove disable_static in example code, test=document_fix
* remove huber_loss and refine npair_loss example code, test=document_fix
* remove huber_loss in functional/__init__.py, test=document_fix
4 years ago
9f3fb95b34
[Dy2stat] Add Simnet Test for V2 APIs ( #27460 )
...
Add Simnet Test for V2 APIs.
We used tool from https://www.paddlepaddle.org.cn/documentation/docs/zh/2.0-beta/guides/migration_cn.html#paddle1-xpaddle2-0beta to do v1.x to v2 transformation.
This PR pulled changes from #27430 , please DO NOT merge before #27430 is merged
4 years ago
a90711c7a2
Add avx512 core instructions check 2 ( #27750 )
...
* Add test skip from cmake
* Remove print
4 years ago
966447e338
Added support for quantization of fusion_gru ( #27518 )
4 years ago
0cd4907eba
Add avx512 core instructions check ( #27732 )
...
* Add avx instructions check
* Small fix
* Change function name
* Change uint to unsigned int
4 years ago
9cd86487cc
Fix api for ErrorClipByValue, code demo of clip_by_norm. test=develop ( #27654 )
...
* Fix ErrorClipByValue api and demo code of clip_by_value. test=develop
Co-authored-by: tianshuo78520a <707759223@qq.com>
4 years ago
54c368db1e
[API 2.0: doc] fix doc of nonzero ( #27685 )
...
* test=develop, update example
4 years ago
69a3339aaa
Move dygraph amp api to paddle-2.0 ( #27681 )
...
* move dygraph amp api to paddle
* refine code and add unit test
4 years ago
a0f1dba37f
Add visualdl callback function ( #27565 )
...
* add visualdl callback
4 years ago
9b3ef5979d
add categorical class ( #27695 )
...
* add multinomial cpu kernel
* fix C++ notype error
* fix windows ci array len error
* let array len be const
* change array to vector
* add cuda kernrl with num_distribution is 1, and not support replacement=False
* add multinomial python api
* support num_distribution different multinomial distributions
* add categorical class
* fix test_distribution enable_static error
* add unittest for different setting of Categorical
* optimize format
* little change
* little change
* add raise error if shape not match, optimize format
* fix windows CI dtype error in concat
* little changes
* little changes2
* change values type to int64
* change values type to int64
* change values type to int64
4 years ago
4d3eefbb95
Modify the docs for Transformer's APIs. test=document_fix ( #27729 )
4 years ago
ab85a8910d
[Dy2stat] Add Resnet Test for V2 APIs ( #27459 )
...
* Add test_resnet_v2.py test=develop
4 years ago
488152a6d0
[API 2.0]Update 2.0 api from fluid to paddle. ( #27598 )
4 years ago
7f9b198d59
Romove grid_sampler and refine example code ( #27649 )
...
* refine grid_sample and temporal_shift
4 years ago
a01bc6b31d
【paddle.fleet】fleet support non_distributed training in dygraph mode ( #27714 )
...
* fleet support non_distributed training in dygraph mode; test=develop
4 years ago
e496640bf4
fix bmm enforce equal batch ( #27694 )
4 years ago
742cbe6660
[bug fix] avoiding multiple initialization of gloo for fleet in dygraph mode ( #27706 )
...
* add double grad for expand, test=develop
4 years ago
a12071ab8a
add type check for initializer and regularizer in ParamAttr ( #27720 )
4 years ago
f373269df0
update histogram op for performance optimization, test=develop ( #24912 )
4 years ago
4d5ddbf106
add xpu test ( #27622 )
...
* add xpu test
* notest;add kunlun_test
* notest;add kunlun_test
* notest;test=kunlun
* notest;test=kunlun
* notest;test=kunlun
* notest;test=kunlun
* test=kunlun
4 years ago
d15cbe70b2
Remove Input requirement in dygraph for Model ( #27557 )
...
* remove input requirment in dygraph Model
* correct unittest
* upadte save inference model in dygraph without input
* fix unittets for test_model.py
* solve conflicts
* solve conflicts
* delete http.log
* fix test_model.py bug, correct initialization of MyModel
* fix unittests bugs
* set paddle manual seed for unittest
* fix Model bugs, because inputs can be list or dict when it is provided.
* add random seed for test_export_deploy_model
* delete redundant codes, because calls
* Code optimization, error information optimization
4 years ago
3a8bef1d41
[Dynamic-to-Static] Refine 2.0rc assign: paddle.nn.functional.assign ( #27650 )
4 years ago
295e87e428
fix dice_loss, log_loss doc and example code test=document_fix ( #27702 )
...
* update 2.0 API for dice_loss and log_loss test=document_fix
4 years ago
8d68dd4785
Fix test_se_resnet unittest ( #27715 )
...
* fix test_se_resnet unittest
* fix test_se_resnet unittest
* add comments for decresing test_se_resnet precision
4 years ago
4d79304c09
update samples of print and clip api, test=develop ( #27670 )
4 years ago
e262cb6293
fix the scatternd/scatterndadd ( #27634 )
...
* fix the scatternd/scatterndadd
* fix the doc of scatter
* replace rank with ndim
4 years ago
28f83f0519
[Dy2stat] Add Ptb Lm Test for V2 APIs ( #27461 )
...
As the title
4 years ago
b77d9f268e
migrate code example and doc ( #27627 )
...
* migrate code example and doc
4 years ago
7cd2c13f1b
add multinomial op ( #27219 )
...
* add multinomial cpu kernel
* fix C++ notype error
* fix windows ci array len error
* let array len be const
* change array to vector
* add cuda kernrl with num_distribution is 1, and not support replacement=False
* add multinomial python api
* support num_distribution different multinomial distributions
* add multinomial python api unittest
* change output dtype to int64
* fix coverage prob
* optimize format
* fix dtype of output error, should be int64_t
4 years ago
7c69e36131
add pip new requirements to windows ( #27697 )
...
* add pip new requirements to windows
* Increase the conditions that restrict system installation
4 years ago
53803202cc
add rename var in block ( #27705 )
4 years ago
719309a80f
add note of large offset of trace test=document_fix ( #27693 )
4 years ago
cefb49ab44
fix docs ( #27637 )
4 years ago
90eb5541d8
fix the precision problem of test_distribution ( #27524 )
...
* increase tolerance
* increase the difference between low and high
* change tolerance of Normal log_prob method
* change probs tolerance to 1e-4
* change tolerance of Normal kl method
4 years ago
29d5937aaa
fix batch_norm doublegrad, test=develop ( #27703 )
4 years ago
42d175385d
Add support for (de/re)quantization with shift ( #27481 )
4 years ago
8da2b16d1a
fix reg ( #27647 )
...
* fix reg
* fix code example and doc
* remove disable_static
* fix doc
* fix l2decay
4 years ago
cc780b1977
test=develop, optimize geo communicator ( #26857 )
...
* test=develop, optimize geo communicator
4 years ago
5132f5129d
terminate http server used by gloo for fleet after init ( #27698 )
4 years ago
8a4f85feb9
Add unittests and OP version registry for quant_conv2d_dequant_fuse_pass ( #27689 )
4 years ago
dec53a9c79
Remove DataParallel.scale_loss & apply_collective_grads ( #27603 )
...
* remove data parallel scale loss & apply collective_grads
* move apply in minimize
* fix failed unittests
4 years ago
7b46fb0f14
fix generate_proposals and affine grid error info ( #27636 )
4 years ago
6d9ae66096
delete ExponentialMovingAverage in paddle/optimizer ( #27683 )
4 years ago
199da9689c
Polish api Program/CompiledProgram/ParallelEnv doc & code example ( #27656 )
...
* polish Program api doc & example
* polish CompiledProgram api doc & example
* polish ParallelEnv api doc & examples
* polish details, test=document_fix
* polish program doc details, test=document_fix
* polish details, test=document_fix
* fix note format error, test=document_fix
* add lost example, test=document_fix
* fix lost example, test=document_fix
4 years ago
b14ecb8632
Polish api BuildStrategy/ExecutionStrategy doc & code example ( #27662 )
...
* polish BuildStrategy api doc & example
* polish ExecutionStrategy api doc & example
* polish details
4 years ago
cc2fc93804
[Dy2stat] Refine Dy2stat APIs to 2.0rc ( #27430 )
...
Refine Dy2stat APIs to 2.0rc
After discussion, we accepted 3 key points from reviewers:
1. In 2.0rc we changed dygraph_to_static folder to dy2static
2. Keep the three files: convert_call_func.py, convert_operators.py, variable_trans_func.py
3. Remove convert_operators path when users import convert_xxx.
After this PR, users can import convert_xxx APIs by:
`import paddle.jit.dy2static.convert_xxx`
The file structure will be:
```
jit
dy2static
convert_operators.py
convert_func_call.py
variable_trans_func.py
```
Detail changed API in files:
In python/paddle/jit/dygraph_to_static/convert_call_func.py:
from ...fluid.dygraph.dygraph_to_static.convert_call_func import convert_call #DEFINE_ALIAS
In python/paddle/jit/dygraph_to_static/convert_operators.py:
from ...fluid.dygraph.dygraph_to_static.convert_operators import cast_bool_if_necessary #DEFINE_ALIAS
from ...fluid.dygraph.dygraph_to_static.convert_operators import convert_assert #DEFINE_ALIAS
from ...fluid.dygraph.dygraph_to_static.convert_operators import convert_ifelse #DEFINE_ALIAS
from ...fluid.dygraph.dygraph_to_static.convert_operators import convert_len #DEFINE_ALIAS
from ...fluid.dygraph.dygraph_to_static.convert_operators import convert_logical_and #DEFINE_ALIAS
from ...fluid.dygraph.dygraph_to_static.convert_operators import convert_logical_not #DEFINE_ALIAS
from ...fluid.dygraph.dygraph_to_static.convert_operators import convert_logical_or #DEFINE_ALIAS
from ...fluid.dygraph.dygraph_to_static.convert_operators import convert_print #DEFINE_ALIAS
from ...fluid.dygraph.dygraph_to_static.convert_operators import convert_var_dtype #DEFINE_ALIAS
from ...fluid.dygraph.dygraph_to_static.convert_operators import convert_var_shape #DEFINE_ALIAS
from ...fluid.dygraph.dygraph_to_static.convert_operators import convert_while_loop #DEFINE_ALIAS
In python/paddle/jit/dygraph_to_static/variable_trans_func.py:
from ...fluid.dygraph.dygraph_to_static.variable_trans_func import create_fill_constant_node #DEFINE_ALIAS
from ...fluid.dygraph.dygraph_to_static.variable_trans_func import create_static_variable_gast_node #DEFINE_ALIAS
from ...fluid.dygraph.dygraph_to_static.variable_trans_func import data_layer_not_check #DEFINE_ALIAS
from ...fluid.dygraph.dygraph_to_static.variable_trans_func import to_static_variable #DEFINE_ALIAS
from ...fluid.dygraph.dygraph_to_static.variable_trans_func import to_static_variable_gast_node #DEFINE_ALIAS
4 years ago
3baf561a90
reduce epoch ( #27661 )
4 years ago
6363a3362b
add paddle.enable_static() && random.seed(xx) to test_activation_op ( #27585 )
...
* add paddle.enable_static() to some testcase
* add seed to random in test_activation_op
* update a randomseed
* update a randomseed
4 years ago
6871e57b30
fix in_dynamic_mode of paddle,test=document_fix ( #27671 )
4 years ago
abb32bbccd
[Dy2stat] Fix lstm bug ( #27631 )
...
This PR fixed two bugs when converting LSTM in dy2stat:
is_unsupported has a condition can trigger Python syntax error
LSTM API's implementation in _rnn_static_graph doesn't include parameter initialization, which can cause dy2stat error.
4 years ago
b7b1ae865e
update mv op docs ( #27559 )
4 years ago
bbc2add703
Initialize gloo for low level collective apis ( #27672 )
...
* add gloo initializer, test=develop
4 years ago
b7107c65a6
[Dy2stat] Fix test_yolov3 to Run Correctly on Win/Mac ( #27666 )
...
We decreased the batch size on CPU so that it can run correctly on Win/Mac machine, this may cause the delta to be larger. So I set larger delta value.
4 years ago
6ad72106f9
[API 2.0] Fix api 'is_empty' ( #27593 )
...
* fix is_empty api and code example; test=develop
4 years ago
ee13a2ab88
Add transformer generate square subsequent mask api ( #27651 )
...
* add transformer generate square subsequent mask api
* add dtype for input, update doc, use -np.inf
* add dtype for input, update doc, use -np.inf
4 years ago
3ccee08285
numpy -> paddle in conv & conv_transpose ( #27669 )
...
* numpy -> paddle in conv. test=develop
4 years ago
ca2892019a
Add label smooth to functional package ( #27642 )
4 years ago
0ecf441af1
Add support for mkldnn ops types selection with FLAGS in dygraph ( #27482 )
...
* Add support for mkldnn ops types selection with FLAGS in dygraph
* use regex to match DNNL verbose
* python3 encoding fix
4 years ago
e7b476c15d
disable ut test_parallel_executor_fetch_isolated_var,test=document_fix ( #27641 )
4 years ago
c29aa8c40e
fix reshape doc, remove reverse api ( #27592 )
4 years ago
1539a23822
Fix bugs in hdfs download ( #27344 )
...
* set default value to strategy in distributed_optimizer test=develop
4 years ago
07b01b0e90
[doc] Change docs of WeightNormParamAttr to dygraph model ( #27571 )
...
* Change docs of WeightNormParamAttr to dygraph model, test=develop, test=document_fix
4 years ago
c7e0a8bebf
Remove inplace argument when calling nn.reshape() ( #27376 )
...
* remove inplace argument
* fix sample code
* fix sample code
4 years ago
26b6169106
Refine initializer to support not passing block in dygraph mode ( #27612 )
...
* support not passing block
* fix NumpyArrayInitializer
* add unit test
4 years ago
0873644cfe
Remove alias for `l2_normalize` ( #27616 )
...
functionality provided by `normalize`
4 years ago
e1f8617ee2
bugfix: RNN does not initialize the state for the cell correctly ( #27644 )
...
1. fix a bug that paddle.nn.RNN does not initialize the state for the cell correctly;
2. add unittest for paddle.nn.RNN and paddle.nn.BiRNN
4 years ago
5e4f01f5ef
modified sample code of add_position_encoding to 2.0 ( #27561 )
...
* modified sample code of add_position_encoding to 2.0, test=document_fix
* use core.op in add_position_encoding API.
* add test for add_position_encoding in dygraph mode
4 years ago
a4c25b2f34
use paddle.is_compile_with_cuda ( #27586 )
...
* modify doc
4 years ago
780140599f
【paddle.distributed.fleet】add data_generator in distributed.fleet.dataset ( #27345 )
4 years ago
eb37ee2a26
modify docs of program API, test=document_fix ( #27600 )
4 years ago
36c0410223
Revert "Initialize gloo for low level collective apis ( #27356 )", test=document_fix ( #27665 )
4 years ago
aed0080181
Remove NLTK requirements to avoid dependency security alert from Github Dependabot. ( #27628 )
...
Remove NLTK requirements to avoid dependency security alert from Github Dependabot
4 years ago
ae6e40a7fd
Add unittests and OP version registry for tensorrt_subgraph_pass ( #27544 )
...
* add unittests and op version register for tensorrt_subgraph_pass
* rename to test_trt_subgraph_pass.py
* fix softmax converter diff when padding dim=1
4 years ago
6822307745
test=develop, rm netifaces ( #27581 )
...
* test=develop, rm netifaces
4 years ago
c68a0313a5
add paddle.fluid._cuda_synchronize ( #27595 )
...
* add paddle.fluid._cuda_synchronize, test=develop
* fix bug about core_avx core_noavx, test=develop
* delete CPUPlace and XPUPlace, test=develop
4 years ago
516d84b22a
fix tests warpctc ( #27639 )
4 years ago
074a71bd25
Support assignment to a Variable in dynamic mode but not deal with backward. ( #27471 )
...
* Support assignment to a Variable in dynamic mode. Note: not deal with backward.
* Rewrite VarBase __setitem__ for high-performance.
* try to test 3 means to do __setitem__ and test the performance of 3 means.
* Retain the means of the highest performance: C++ code and don't trace op.
4 years ago
fa73e4a284
Initialize gloo for low level collective apis ( #27356 )
...
* add gloo initializer, test=develop
4 years ago
bf99bc4a62
update name_scope example code ( #27594 )
...
* update name_scope example code
test=document_fix
* refine name_scope doc
test=document_fix
4 years ago
5641ea2bf6
Remove optimizer which in fleet, test=develop ( #27606 )
4 years ago
68df20d2f2
fix pad2d example code ( #27615 )
...
* fix example code
* rename var to tensor
* remove static
* fix return type
4 years ago
7c5162400f
[API 2.0]Migrate api example for gradients/append_backward/program_guard ( #27570 )
...
* modify sample code
* variable -> tensor
* migrate program_guard sample code
* refine error message
* migrate program_guard
* refine comment style
* fix indent
4 years ago
4e8f18ab25
Get final strategy ( #27602 )
...
* add get final strategy for user to print final strategy
4 years ago
d01f626944
update mv op according PR#27024 ( #27474 )
4 years ago
d1c2a3bc6f
disable ut test_warpctc_op,test=document_fix ( #27632 )
4 years ago
6e41143ffe
remove paddle.metrics.cos_sim api ( #27569 )
...
* fix api alias
* remove cos_sim
4 years ago
96daa2594e
Fix padding in conv1d op ( #27590 )
4 years ago
1501a80f74
add support to float64 input of warpctc op. ( #27399 )
...
* add float64 input to ctc_loss
* modified error message of warpctc
* update repo and tag of warpctc
* add test for warpctc with float64 input
* modified warpctc.cmake to make sure build always
* resolved sample code bug of warpctc
* add core.ops in warpctc dygraph
* fix a bug of test
4 years ago
3f170dd83d
[API 2.0] Fix example code of api 'switch_case' and add/delete alias ( #27578 )
...
* Fix example code of api `fluid.layers.switch_case` to use api2.0
* delete `paddle.nn.switch_case` alias and add `paddle.static.nn.switch_case`
4 years ago
c5b6e44b4a
fix cholesky of test_math_op_patch_var_base ( #27591 )
4 years ago
9b7ebf1099
[API 2.0] Fix example code of api 'case' and add/delete alias ( #27577 )
...
* Fix example code of api fluid.layers.case
* delete paddle.nn.case alias and add paddle.static.nn.case
4 years ago
6b727e08b1
support elementwise add, activation, matmul on Baidu Kunlun ( #27143 )
...
* support elementwise add, activation, matmul on Baidu Kunlun
* test=kunlun
* minor
* test=kunlun
* reconstuct the xpu directory
* test=kunlun
* minor
* test=kunlun
* minor
* test=kunlun
* minor
* test=kunlun
* minor
* test=kunlun
* minor
* test=kunlun
4 years ago
d37b3774fd
register log double grad kernel for cpu and cuda
...
register log double grad kernel for cpu and cuda
4 years ago
162b4d6c13
remove to_variable from 2.0 ( #27528 )
4 years ago
0e101c4f6f
Fix test dist fleet heter ctr ( #27513 )
...
* fix test_dist_fleet_heter_ctr & peformance update
4 years ago
42065ba37a
fix activate_nn_grad, test=develop ( #27555 )
4 years ago
b9d739a7ea
fix pool bug, test=develop ( #27537 )
...
* fix pool bug, test=develop
* fix coverage,test=develop
* fix bug, test=develop
4 years ago
86fa043205
init test=develop ( #27554 )
4 years ago
ecfdfc9c58
fix guard place set error ( #27573 )
4 years ago
b0ee1405f7
Add conv2d bfloat16 support ( #27325 )
4 years ago
b38e4f2840
Refine vision models ( #27476 )
...
* refine vision models
4 years ago
0b4bb023a7
Add static mode check on data() ( #27495 )
...
* add static check on data()
* follow comments
* fix ut
4 years ago
6f69a4cb05
add xpu in heter mode ( #27000 )
...
* add xpu in heter mode
test=develop
* BOOST_CONST_GET; PADDLE_THROW
test=develop
* code style
test=develop
* code style
test=develop
* code style
test=develop
* refine
test=develop
* refine
test=develop
* refine
test=develop
* refine code
test=develop
4 years ago
8daccc9ea7
Fix batch norm double grad compute ( #27549 )
...
* fix bn double grad, test=develop
* update, test=develop
4 years ago
c143326df5
try to fix test_paddle_save_load unknown timeout ( #27536 )
...
* try to fix paddle save load test
* open paddle save load
* replace dataloader
* remove dataloader
4 years ago
6fc74bbaf6
add fp16 for matmul ( #27523 )
...
* add fp16 for matmul
4 years ago
fab4e6d08f
add abs support double grad
...
add abs support double grad for the api 2.0
4 years ago
77a36f8997
[buf fix]:fix some unittests error ( #27540 )
...
* [buf fix]:fix unittest test_activation_op error
* split long-time unittests to smaller ones
* rename some unittests
4 years ago
6e16a0997c
fix unittest_group_norm_op_v2, test=develop ( #27486 )
...
* fix unittest_group_norm_op_v2, test=develop
* fix unittest_group_norm_op_v2, test=develop
4 years ago
dd04b160d9
fix test imperative se resnext failed ( #27538 )
4 years ago
e550fc02ae
fleet2.0 add fp16 grad compression ( #27480 )
4 years ago
c5c13473c6
Add compatibility check for four mkldnn pass ( #27364 )
...
* Add pass compatibility check for four mkldnn pass, test=develop
4 years ago
41a7ce8347
fix random failure of test_buffer_sahred_memory_reuse_pass ( #27551 )
4 years ago
8473ee9dae
make places of DataLoader optional. ( #27432 )
...
* make places of DataLoader optional. test=develop
4 years ago
3d5522146e
register seq_concat_fc_fuse pass. ( #27479 )
4 years ago
32ad4f90a4
【paddle.fleet】 Usages Change: from fleet.util() to fleet.util ( #27468 )
...
* test=develop, bug fix
4 years ago
273f58a3c5
Decrease Random Failure Probability for test_parallel_executor_mnist, test=develop ( #27498 )
...
As the title, decrease random failure probability for test_parallel_executor_mnist
The old code set larger delta when comparing reduce and all reduce, but didn't set all. I added it.
On my linux machine, I run 100 times, no failure occurs. In addition, we only saw this random failure on CI two times since I worked. I thought it was rare and I just increased the delta.
4 years ago
59c049995e
change test main process wait time ( #27516 )
4 years ago
b6ecf35627
disable test_paddle_save_load,test=document_fix ( #27534 )
4 years ago
081fb2f963
Remove dependency on nltk for paddle __init__. ( #27388 )
...
* Remove dependency on nltk for paddle __init__.
test=develop
* Remove nltk.movie_reivew sentiment dataset to remove dependency on nltk.
test=develop
4 years ago
f2c97b6da5
replace dataset with fake data ( #27519 )
4 years ago
78a27a2b0d
Reproduce summary api ( #27367 )
...
* reproduce summary api
4 years ago
fc9d80bc9e
[Dy2Stat]rename StaticLayer into StaticFunction ( #27487 )
...
* rename StaticLayer
* rename
4 years ago
5c8fdb5926
Fix GradientClipByGlobalNorm dtype bug ( #27437 )
...
* fix dtype of gradientclipbyglobalnorm
* fix dtype bug of GradientClipbyGlobalnorm
4 years ago
c0caf0e45f
fix ut for static graph ( #27506 )
4 years ago
66951ab2ea
modified timeout value for 4 ut ( #27462 )
4 years ago
bb84f0e646
Add new paddle.save/load APIs ( #27331 )
...
* init commit of new save/load
* fix failed unittests
* fix save_load_v2 unittest failed
* fix failed unittest & polish doc
* add tests for coverage
* add more tests & move static apis
* fix example code error
* polish emample code
* fix detail example code problem
4 years ago
19a58b3d5d
disable ut test_vision_models and test_pretrained_model,test=document_fix ( #27502 )
4 years ago
1e1ae5c54d
Make the Bind Method of Tensor more automatic ( #27270 )
...
* Makes the Bind Method more intelligent
* Makes the Bind Method more intelligent
* fix unittest
* fix unittest
* fix conflict
4 years ago
5508c78744
Fix bug: The calculation result of Diag_v2 Op under large size input is wrong ( #27447 )
...
The calculation result of Diag_v2 Op under large size input is wrong
4 years ago
bc5f0246a8
large scale kv speedup ( #26510 )
...
* rename communicator meet->BatchesCounter
* fix parame recv for sparse
* geo sparse init from pserver
* optimize init from pserver
* add large scale optimizer fuse(SGD/ADAM)
* rectification init_worker and exe.run startup program
4 years ago
d7b7dcd10e
fix cmake dependencies of test_recognize_digits, test=develop ( #27475 )
4 years ago
43240a1b81
[doc] Add example for cache and buffered ( #26819 )
...
* Add example for cache and buffered, test=develop, test=document_fix
4 years ago
906e7f921e
add fuse_bn_act op ( #27230 )
...
* add fused_bn_add_relu op
4 years ago
5034d181f3
update for 2.0 inference api. ( #27473 )
4 years ago
0721767ba9
fix server_num bug;test=develop ( #27442 )
4 years ago
76fb95fe76
avoid data transform for linspace OP ( #27444 )
4 years ago
827ac36faa
Use dygraph mode by default ( #27443 )
...
* default open dygraph mode
* fix CI-Mac
* fix Mac-CI other unittest file
* fix CI-Py3
* fix test_communicator_geo and test_buffer_shared_memory_reuse_pass
* add enable_static to fix CI-Py3
* add enable_static to fix CI-coverage
* delete try except
4 years ago
0a862fd356
refine the precious of linspace Op using half way ( #27452 )
4 years ago
905e2346ac
add endpoints log;test=develop ( #27439 )
4 years ago
7ba6279a25
[Dy2stat] Refine error msg of @to_static if not in imperative mode ( #27371 )
...
* refine error mesg
4 years ago
18f2ea66bd
remove paddle.readers API ( #26727 )
...
* remove paddle.readers API. test=develop
4 years ago
f4c750d721
Add the cpu version of segment sum mean max min op
...
Add the cpu version of segment sum mean max min op
4 years ago
3fe176df35
Fix test_gast_with_compatibility.py due to the problem of gast in python3.8 ( #27433 )
...
test=develop
4 years ago
13a4c74efd
add mv op(c++, python, unit test) ( #27024 )
4 years ago
f11a53ee76
Optimize argsort Op performance on GPU
...
* argsort op acceleration on GPU when the input size is equal to the length of the ‘axis’ dimension
4 years ago
1d3b27cae8
add double grad compute for batch norm ( #27296 )
...
* add double grad compute for batch norm,test=develop
* fix unittest, test=develop
* remove unuse tensor,test=develop
* add format,test=develop
* update, test=develop
4 years ago
4bd7aa2566
use paddle.get_default_dtype in vision datasets. test=develop ( #27426 )
4 years ago
fc61efd736
fix port env bug(int);test=develop ( #27405 )
4 years ago
e217e965a9
fix pool bug ( #27366 )
4 years ago
d93661942e
fix bug sequececonv_eltadd_relu_fuse_pass ( #27404 )
...
* fix bug sequececonv_eltadd_relu_fuse_pass, output error when sequence_conv's padding_start > 0
* fix seqconv_eltadd_relu_fuse_pass unitest error
4 years ago
aba759ba16
[Feature] Enhance inplace addto strategy for gradient accumulation in static graph ( #27112 )
...
* support use add instead of sum to do gradient accumulation
* add inplace addto pass
* add grad_add op and inplace addto pass
* remove debug code
* code refine
* fix bug when sereral sum ops inserts at same op_idx
* fix Flags type
* add addto attribute for conv3d
* fix ut
* code clean
* fix type
4 years ago
669efb98de
Fix bug: shapes of Topk outputs are wrong when the parameter k is Tensor
...
Fix bug: shapes of Topk outputs are wrong when the parameter k is Tensor
4 years ago
39546aa2f3
Add pass compatible and unit test. ( #27377 )
4 years ago
02606d45ef
Quant op dev ( #25932 )
...
* Finished ChannelWiseQuantDequantAbsMaxOp and Passed unittests.
* Finished channel-wise quantize strategy in imperative quantization.
* Added Cuda code of ChannelWiseQuantDequantMaxAbsOP
Add Cuda code of ChannelWiseQuantDequantMaxAbsOp
* Add quant_axis for channel_wise quant.
* fixed a bug in unnitests, which will not trigger axis = 1 case and cannot meet the coverage rate requirement.
* Added some assert infomation and fixed some coding style mistakes.
4 years ago
aa7835efee
Correct the error in decorator.py ( #27409 )
...
test=develop
4 years ago
f3b4a64add
fix CIFAR MNIST UCIHousing dataset. test=develop ( #27368 )
...
* fix CIFAR & MNIST dataset. test=develop
4 years ago
f936adbd2d
fix adam ( #27343 )
...
* fix adam
* rmsprop support double
4 years ago
d6b54de467
【paddle.fleet】Fix/role maker api fix ( #27326 )
...
* fix fleet util and gloo
* fix worker endpoints
* fix
* fix UT
* fix gloo
* fix gloo
* update gloo
* update gloo
* update gloo
* update gloo
* update gloo
* fix gloo wrapper for hdfs
* add file gloo and UT
* fix UT
* fix UT
* fix UT
* hide public method of RoleMaker
* fix UT
* GPU fleetrun support gloo
* parameterserver fleetrun support gloo
* add UT
* add UT
* fix UT
* fix get server endpoint
* fix get server endpoint
* fix UT
* hide public method of rolemaker
* hide public method of rolemaker
* hide public method of rolemaker
* Update test_fleet_rolemaker_new.py
* hide public method of rolemaker
* hide public method of rolemaker
4 years ago
99626502f7
【paddle.fleet】gloo and util ( #27213 )
...
* fix worker endpoints
* fix gloo wrapper for hdfs
* GPU fleetrun support gloo
* parameterserver fleetrun support gloo
* fix get server endpoint
4 years ago
4c5cfdea1b
fix paddle.nn.Transformer api ( #27391 )
4 years ago
fd7ab4e63c
register pass compatibility ( #27357 )
...
* pass compatibility
* add compatibility registry
* add unittests for different padding
* add assert
* drop errmsg
4 years ago
7e6dfcf9b2
Add 3 pass version check ( #27283 )
4 years ago
03b0e0c42b
Remove dependences of cv2 ( #27286 )
...
* rm dependence of cv2
4 years ago
fef94eac4e
fix cross_entropy bug of the axis parameter in log_softmax ( #27311 )
4 years ago
d28162b97f
Remove save_quantized_model in ImperativeQuantAware. ( #27240 )
4 years ago
ac82baa80d
[Dy2Stat-log] Add feature also_to_stdout and optimize log messages ( #27285 )
...
* Add env value to log to stdout; 2.Add logger name
* Optimize log messages in dygraph-to-static
* Replace logging.warn and warnings.warn with logging_utils.warn
4 years ago
3c11717988
add op version checker to ir passes ( #27329 )
4 years ago
515efe4240
add empty_like op (python, and unit test), use c++ implementation of empty op, ( #27287 )
...
and optimize the c++ implmentation of empty op as PR#26659 reviews,
and add bool for shape op.
4 years ago
f36b9a7f79
【Fleet2.0 Util】 add documents ( #26698 )
...
* test=develop, util documents
4 years ago
bcb4a583aa
Replace the 'spawn' start method with 'fork' start method for multiprocessing, on MacOS with python>=3.8 ( #27317 )
...
* Replace the 'spawn' start method with 'fork' start method for multiprocessing, on MacOs when python>=3.8
test=develop
4 years ago
63203c4abc
enhance reduce op which can reduce tensor with arbitrary rank
...
enhance reduce op which can reduce tensor with arbitrary rank
4 years ago
69279207eb
Update hapi.model._save_inference_model by using new features of dy2stat in 2.0-beta API ( #27272 )
...
* update model.save_inference_model
* update doc for _save_inference_model, delete useless class in unittests
* make users not be able to set model._inputs be None
* update usage of Model class in unittests
* fix bugs of _verify_spec
* fix bugs of _verify_spec
* add unittest to increase coverage rate
* delete http.log
* update doc for save, remove requirments and limitations for using
* update doc for class Model
4 years ago
f0a5eef58f
cancel three disable ut ( #27359 )
4 years ago
25902b2c12
del exclusive ut which name with test_dist_ ( #27316 )
4 years ago
9ee77b1f41
Fix elementwise_floordiv op ( #27352 )
...
* fix floordiv
4 years ago
7d7f0fad7f
python for windows not install netifaces ( #27355 )
4 years ago
9bea834ed4
Refine the unittest to support py38 ( #27208 )
...
* Refine the unittest to support py38
test=develop
4 years ago
a7fadce82f
fix dll load bug on windows from python3.8 ( #27324 )
4 years ago
d4b4357bc0
[Dy2stat] Change the Global Switch Name of ProgramTranslator for API 2.0 ( #27203 )
...
Change ProgramTranslator.enable_declarative to ProgramTranslator.enable_to_static to meet API 2.0
4 years ago
8d05c00c67
fix paddle.fleet en-doc for apis in dynamic mode ( #27354 )
...
* fix fleet dynamic-mode en-doc;test=develop
4 years ago
746a8ded29
fix comment of adaptive lsgd ( #27362 )
4 years ago
bf8e030eed
modify test_imperative_using_non_zero_gpu from use two gpus to one gpu ( #27348 )
...
* add op_function_generator.exe retry in windows, test=develop
* modify test_imperative_using_non_zero_gpu from use two gpus to one gpu, test=develop
4 years ago
189e10f1dd
Remove unnecessary requirements ( #27341 )
...
* remove objgraph
* remove graphviz
* fix ut
4 years ago
11bcf0e21c
Cleanup redundant code files ( #27319 )
4 years ago
54b81fa32c
add adaptivelsgd in meta_optimizer ( #27289 )
...
* add adaptivelsgd
* Todo fix the code to avoid the conflict.
4 years ago
34091533c9
Fix bug in continuous apply, test=develop ( #27337 )
4 years ago
c23f09fea6
Support load state_dict from save_params/persistables ( #27298 )
...
* support load state_dict from save_params/persistables
* remove failed unittest
* add load eof check & unittest
* remove eof check
4 years ago
c67c391682
refine fleet dataset class api ( #27133 )
4 years ago
c296618c94
fix error message in broadcast/allreduce/gather ( #27302 )
...
* fix error message
4 years ago
950301bfa1
Add input_spec & output_spec for TranslatedLayer ( #27284 )
...
* add input_spec & output_spec for translated_layer
* update error message
4 years ago
18fc927562
add regularizer api ( #27292 )
4 years ago
8fe1c2d1c2
move three ut to execute only at night ( #27314 )
4 years ago
ef6dd6b8e6
fix the test_fleet_lars_meta_optimizer ut. ( #27291 )
4 years ago
389a9a7e0e
fix ports conflict when use paddlecloud to launch analogue multi-nodes ( #26191 )
...
* fix ports conflict when launching multi-nodes in paddlecloud;test=develop
* add DISTRIBUTED_TRAINER_ENDPOINTS env for cloud;test=develop
4 years ago
9dedafa0df
fix strategy, test=develop ( #27323 )
...
* fix strategy, test=develop
* fix can_apply
4 years ago
c8e54c5e42
Disable unit-test test_fleet_rolemaker_new
4 years ago
47fdc60ecc
Optimize slice trt plugin ( #26970 )
...
* optimize slice TRT plugin
This patch removes unnecessary barrier for data transfer of needed offset,
so data transfer can be overlap with GPU kernel execution.
This patch also fixes incorrect name of slice plugin. That is, replaces
"layernorm" with "slice"
test=develop
* add serialize/deserialize to slice plugin
* add static shape slice trt plugin
* fix slice trt op convertor dynamic shape bug
* fix format by clang-format
* fix pylint format error
* fix problems commented by peiyang
Co-authored-by: Ryan Jeng <rjeng@nvidia.com>
4 years ago
f827665ae6
[Pass Compatible] Bind python compatible. ( #27262 )
4 years ago
e6e2e53782
Optimize error report ( #27254 )
...
* optimize errror report
* add test case for pad op converter
* fix some spelling mistake commented by peiyang
4 years ago
ee1ed42c99
change sequence length attribute to input ( #27193 )
...
* replace sequence length attr to input
4 years ago
2d8281d5ad
Remove the cache in post_traning_quantization, test=develop ( #26450 )
...
* Remove the cache in post_traning_quantization, test=develop
4 years ago
6947a58a1f
disable three unittests,test=document_fix ( #27299 )
4 years ago
ac9afa024b
paddle.nn.functional.logsigmoid -> log_sigmoid ( #27277 )
4 years ago
bc3e9ba1c6
check the validation of parameters for expand and tile apis ( #26816 )
...
* bug fix, test=develop
4 years ago
a685435962
fix conv depthwise bug ( #27278 )
...
Fix conv deepwise bug when in_channels=1.
4 years ago
d4f03dfb71
fix for tuple,test=develop ( #27190 )
4 years ago
9166307315
add check for sparse parameters with weight_decay ( #27141 )
...
* add check for sparse parameters with weight_decay
* move sparse check to adam.py
4 years ago
LiuChiachi
hong19860320
TeslaZhao
Jack Zhou
LielinJiang
mapingshuo
WangXi
cc
tianshuo78520a
Chen Weihang
wangxinxin08
Wilber
Yiqun Liu
zhupengyang
Leo Chen
Double_V
石晓伟
zhulei
Li Fuchen
LutaoChu
Feiyu Chan
liu zhengxi
Jacek Czaja
gongweibao
FlyingQianMM
Qi Li
wanghuancoder
huangjun12
Huihuang Zheng
joanna.wozna.intel
Wojciech Uss
ysh329
123malin
pangyoki
xiemoyuan
danleifeng
yaoxuefeng
lilong12
hutuxian
liym27
lijianshe02
Peihan
ShenLiang
Bai Yifan
iducn
ceci3
littletomatodonkey
Pei Yang
yukavio
MRXLT
Shang Zhizhou
Zhou Wei
furnace
Kaipeng Deng
whs
arlesniak
YUNSHEN XIE
Qinghe JING
Yang Zhang
Zhang Ting
Zeyu Chen
Tao Luo
Aurelius84
Dong Daxiang
QingshuChen
Chengmo
Thunderbrook
Zhong Hui
zhang wenhui
Guo Sheng
tangwei12
wangchaochaohu
guofei
huangxu96
haozech
chajchaj
Zhen Wang
Yibing Liu
chalsliu
GaoWei8
xiaoting