[DO NOT MERGE] detect model test for dynamic shape by luotao1 · Pull Request #18331 · PaddlePaddle/Paddle

luotao1 · 2019-06-25T16:10:43Z

only for test

luotao1 · 2019-06-25T16:11:21Z

paddle/fluid/inference/tests/api/analyzer_detect_tester.cc

+  std::string shape_line;
+  std::ifstream infer_file(FLAGS_infer_shape);
+
+  int iteration = FLAGS_test_all_data ? 1000 : 1;


You could change the sample numbers yourself.

luotao1 · 2019-06-27T08:15:18Z

@LeoZhao-Intel

LeoZhao-Intel · 2019-06-27T08:35:08Z

paddle/fluid/inference/tests/api/analyzer_detect_tester.cc

+        elapsed_time += run_timer.toc();
+      });
+      threads[0].join();
+      threads.clear();


this place, the clear method should be same with input_slots_all.

* add dependecy of collective_helper * test=develop fix dependecy of collective_helper

Fix dygraph show style for FluidDoc.

test=develop

* add cuda_is_available test=develop * Fix api.spec test=develop * fix api doc test=develop

* test=develop, add some comments for Program.clone * test=develop, add API.spec * test=develop, refine comments * refine Program doc and clone doc * test=develop, refine doc

* add_elementwise_add_inplace_test,test=develop * rename file, test=develop

* change nproc 8

1. some key generation method is not aligned with PR#17965 2. enlarge ptr lifetime to avoid memory release if SetBlob fails otherwise it will get core dump. test=develop

#18390) * add MultiSlotStringDataGenerator for speedup of string based user input data

* test=develop * test=develop

test=develop

* fix py-cpuinfo mac random fail * differentiate version on windows

change url of pslib.tar.gz

fix data feed ptr runtime error, pipeline trainer will core in some cases, so set it nullptr as default value.

* update api format test=develop * update API.spec test=develop

replace mnist dataset url

* Fix bug in quantize kernel which cause crash in vgg16/19 model test=develop * refine the code to reduce verbose code; test=develop * remove useless code; test=develop

* Int8: Fix Pooling output scale test=develop * Update scales quantization for certain operators These include: concat, transpose, pool and reshape. test=develop * Move concat minimum scale finding to quantizer test=develop

* fix mac ci random fail * use platform instead

update README.md with latest release & install version

update README_cn.md with latest version

…18371) * modify roi_perspective_transform_op to output mask and transform matrix * modify comment * modify comment * modify API.spec * update API.spec * remove no use header, test=develop * resolve conflict

* add not_been_used_vars to no_grad_set test=develop

make fleet support mpi job submit directly.

* fix the api.spec file does not get the class comment problem * cat new.spec * check api.spec * test=develop

1. Since allreduce op has 4 reduce types, We split these four reduce types into four ops 2. We also refined the collective op code, e.g. we separated the collective op kernel into CPUKernel and CUDAKernel, and remove the device specified DeviceContext parameter in template as we already knew the target DeviceContext 3. We remove the newly added Collective op role to reduce the complexity of program and graph analysis

test=develop

…d() (#18453) * rename mkldnn set/get_cur_thread_id() to set/get_cur_mkldnn_session_id() test=develop * update session id definition and adjust logic for default behavior test=develop * reset logic in mkldnn reuse as most of cases work in default. test=develop

… luotao1-detect_model

CLAassistant · 2019-07-03T04:32:59Z

All committers have signed the CLA.

detect model test for dynamic shape

76db898

luotao1 commented Jun 25, 2019

View reviewed changes

luotao1 and others added 5 commits June 26, 2019 19:17

load input data one by one

6a97049

each iteration use new threads

1a47373

Merge branch 'develop' into detect_model

c0419de

Remove all the code, API and doc of MKL-DNN INT8v1 (#18347)

19da59e

fix input_slot_all memory leak

6adb535

LeoZhao-Intel reviewed Jun 27, 2019

View reviewed changes

add dependecy of collective_helper (#18365)

9931bc6

* add dependecy of collective_helper * test=develop fix dependecy of collective_helper

luotao1 mentioned this pull request Jun 27, 2019

[DO NOT MERGE] detect model test2 for dynamic shape #18372

Closed

junjun315 and others added 19 commits June 27, 2019 19:07

Fix dygraph show style (#18297)

fd6631e

Fix dygraph show style for FluidDoc.

Call the test_slim_int8_* tests through absolute path (#18386)

8ed819d

test=develop

Add is_compiled_with_cuda (#18356)

871cc15

* add cuda_is_available test=develop * Fix api.spec test=develop * fix api doc test=develop

test=develop, fix multigpu hang on latest docker (#18379)

af874a1

Fix/program doc (#17908)

43f64a1

* test=develop, add some comments for Program.clone * test=develop, add API.spec * test=develop, refine comments * refine Program doc and clone doc * test=develop, refine doc

Add a unittest to inplace elementwise_add (#18385)

f564100

* add_elementwise_add_inplace_test,test=develop * rename file, test=develop

Fix mac build nproc command not found (#18362)

052b044

* change nproc 8

Fix potential mkldnn concat/pool/conv kernel issues (#18393)

681d355

1. some key generation method is not aligned with PR#17965 2. enlarge ptr lifetime to avoid memory release if SetBlob fails otherwise it will get core dump. test=develop

add MultiSlotStringDataGenerator for speedup of string based user inp… (

e83f902

#18390) * add MultiSlotStringDataGenerator for speedup of string based user input data

fix ci document_preview job error (#18399)

b963079

* test=develop * test=develop

init custom black white list (#18377)

2b4ef50

test=develop

fix py-cpuinfo mac random fail (#18383)

ce7a024

* fix py-cpuinfo mac random fail * differentiate version on windows

update pslib library path (#18415)

ef81ff7

change url of pslib.tar.gz

fix data feed ptr error (#18419)

93a2b31

fix data feed ptr runtime error, pipeline trainer will core in some cases, so set it nullptr as default value.

update api format (#18413)

8a39e5c

* update api format test=develop * update API.spec test=develop

test=develop (#18426)

92ecb30

add "import paddle.fluid as fluid" to examples lack of it

47e2ef3

replace mnist dataset url, test=develop (#18429)

dd3f9d1

replace mnist dataset url

Fix bug in quantize kernel which cause crash in vgg16/19 model (#17964)

4bc2987

* Fix bug in quantize kernel which cause crash in vgg16/19 model test=develop * refine the code to reduce verbose code; test=develop * remove useless code; test=develop

Sand3r- and others added 15 commits July 1, 2019 17:12

Fix Pooling output scale (#18186)

7023a86

* Int8: Fix Pooling output scale test=develop * Update scales quantization for certain operators These include: concat, transpose, pool and reshape. test=develop * Move concat minimum scale finding to quantizer test=develop

fix mac ci random fail (#18430)

a3bc804

* fix mac ci random fail * use platform instead

Update README.md with latest version

2246f7c

update README.md with latest release & install version

update README_cn.md with latest version

99659a9

update README_cn.md with latest version

Make roi_perspective_transform op return mask and transform matrix (#…

449c7a9

…18371) * modify roi_perspective_transform_op to output mask and transform matrix * modify comment * modify comment * modify API.spec * update API.spec * remove no use header, test=develop * resolve conflict

Add find_no_grad_vars in backward.py (#17942)

e0d8c6a

* add not_been_used_vars to no_grad_set test=develop

make fleet support mpi job submit directly (#18441)

357311f

make fleet support mpi job submit directly.

fix the api.spec file does not get the class comment problem (#18439)

85b49d8

* fix the api.spec file does not get the class comment problem * cat new.spec * check api.spec * test=develop

remove unused AnalysisPredictor::SetMkldnnThreadID() (#18444)

3123d18

test=develop

fix load attr error. test=develop (#18447)

823ab5e

add friendly error msg to py_reader (#18316)

41ab76e

Merge branch 'detect_model' of https://github.com/luotao1/Paddle into…

d30fe34

… luotao1-detect_model

add bert test for transfer_scope_cache

510d442

luotao1 closed this Jul 3, 2019

luotao1 deleted the detect_model branch July 3, 2019 04:34

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[DO NOT MERGE] detect model test for dynamic shape#18331

[DO NOT MERGE] detect model test for dynamic shape#18331
luotao1 wants to merge 41 commits intoPaddlePaddle:developfrom
luotao1:detect_model

luotao1 commented Jun 25, 2019

Uh oh!

luotao1 Jun 25, 2019

Uh oh!

luotao1 commented Jun 27, 2019

Uh oh!

LeoZhao-Intel Jun 27, 2019

Uh oh!

CLAassistant commented Jul 3, 2019 •

edited

Loading

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

20 participants

Conversation

luotao1 commented Jun 25, 2019

Uh oh!

luotao1 Jun 25, 2019

Choose a reason for hiding this comment

Uh oh!

luotao1 commented Jun 27, 2019

Uh oh!

LeoZhao-Intel Jun 27, 2019

Choose a reason for hiding this comment

Uh oh!

CLAassistant commented Jul 3, 2019 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

20 participants

CLAassistant commented Jul 3, 2019 •

edited

Loading