[Feature] Add `DerivedMutable` & `MutableValue` #215

wutongshenqiu · 2022-08-01T07:14:11Z

Motivation

Add DerivedMutable and MutableValue.

Modification

Add DerivedMutable
Add MutableValue
Fix mmcls import error

codecov · 2022-08-01T07:37:08Z

Codecov Report

Merging #215 (dff284e) into dev-1.x (696191e) will decrease coverage by 0.04%.
The diff coverage is 0.00%.

@@            Coverage Diff             @@
##           dev-1.x    #215      +/-   ##
==========================================
- Coverage     0.67%   0.63%   -0.05%     
==========================================
  Files          120     124       +4     
  Lines         4318    4597     +279     
  Branches       676     720      +44     
==========================================
  Hits            29      29              
- Misses        4284    4563     +279     
  Partials         5       5

Flag	Coverage Δ
unittests	`0.63% <0.00%> (-0.05%)`	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
mmrazor/models/mutables/__init__.py	`0.00% <0.00%> (ø)`
mmrazor/models/mutables/derived_mutable.py	`0.00% <0.00%> (ø)`
...models/mutables/mutable_channel/mutable_channel.py	`0.00% <0.00%> (ø)`
...tables/mutable_channel/one_shot_mutable_channel.py	`0.00% <0.00%> (ø)`
...ables/mutable_channel/slimmable_mutable_channel.py	`0.00% <0.00%> (ø)`
mmrazor/models/mutables/mutable_value/__init__.py	`0.00% <0.00%> (ø)`
...zor/models/mutables/mutable_value/mutable_value.py	`0.00% <0.00%> (ø)`
mmrazor/models/utils/__init__.py	`0.00% <0.00%> (ø)`
mmrazor/models/utils/make_divisible.py	`0.00% <0.00%> (ø)`
mmrazor/structures/subnet/fix_subnet.py	`0.00% <0.00%> (ø)`

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.

sunnyxiaohu · 2022-08-02T02:13:58Z

mmrazor/models/mutables/derived_mutable.py

+        return self.mask_fn()
+
+    # TODO
+    # should be __str__? but can not provide info when debug


We could provide the link_path from DerivedMutable to Source mutables.

Provide attribute source_mutables to trace source mutables of derived mutable

mmrazor/engine/runner/mixins.py

mmrazor/models/mutators/channel_mutator/channel_mutator.py

mmrazor/engine/runner/autoslim_val_loop.py

mmrazor/models/mutators/channel_mutator/slimmable_channel_mutator.py

sunnyxiaohu · 2022-08-09T02:49:41Z

mmrazor/models/mutables/derived_mutable.py

+from typing import Any, Callable, Dict, Optional, Protocol, Set, Union
+
+import torch
+from mmcls.models.utils import make_divisible


The main modules(e.g., mutators / mutables) of mmrazor should not depends on other downstream repos expect mmcv and mmengine.

Add make_divisible in mmrazor.models.utils

sunnyxiaohu · 2022-08-09T03:13:55Z

mmrazor/models/mutables/derived_mutable.py

+class DerivedMethodMixin:
+    """A mixin that provides some useful method to derive mutable."""
+
+    def derive_same_mutable(self: MutableProtocol) -> 'DerivedMutable':


typo? ‘DerivedMutable’ -> DerivedMutable

The reason for using str here is that class DeriveMutable is defined after DerivedMethodMixin. To directly use DerivedMutable for type hint, the version of python should >= 3.7. More details can be found at this link

mmrazor/models/mutables/derived_mutable.py

sunnyxiaohu · 2022-08-09T03:53:48Z

mmrazor/models/mutables/mutable_channel/one_shot_mutable_channel.py

+        return self * other
+
+    def __mul__(self, other) -> DerivedMutable:
+        if isinstance(other, int):


When other is not an instance of int, can we handle these logics in derived_mutable.py uniformly?

A uniformly definition in DerivedMutable or DerivedMutableMixin might be tricky, as it is difficult to determine the type of multiplication of the two and whether the operations should be the same for different types

sunnyxiaohu · 2022-08-09T04:10:15Z

mmrazor/models/mutables/mutable_channel/one_shot_mutable_channel.py

+
+        return dict(
+            current_choice=self.current_choice,
+            origin_channels=self.num_channels)


What's the purpose of origin_channels?

It will not be used except just for exporting more content to the subnet config, would it be better to remove it?

I suggest that we only dump necessary infomation, which decides subnet.

sunnyxiaohu · 2022-08-09T06:15:12Z

mmrazor/models/mutables/derived_mutable.py

+
+    # TODO
+    # has no effect
+    def fix_chosen(self, chosen: Dict) -> None:


Raise Error for fix_chosen and dump_chosen, when called, as DerivedMutable dose not have its own search_space.
Meanwhile, the DerivedMutable should be excluded when export_fix_subnet and load_fix_subnet to imporove human readability.

Add warnings when calling fix_chosen or dump_chosen and add an optional argument dump_derived_mutable for function export_fix_subnet to indicate whether export derived mutable or not.

sunnyxiaohu · 2022-08-09T06:29:34Z

tests/test_models/test_mutables/test_derived_mutable.py

+            _ = DerivedMutable(
+                choice_fn=lambda x: x, source_mutables=[mc_derived1])
+
+        def dict_closure_fn(x, y):


Add a UT for the case when there are source_mutables and/or derived_mutables in the closure function.

I am not sure can this UT meet the requirement.

sunnyxiaohu · 2022-08-09T06:34:53Z

tests/test_models/test_mutables/test_derived_mutable.py

+        with pytest.raises(RuntimeError):
+            derived_mutable.fix_chosen({})
+
+    def test_source_mutables(self) -> None:


Add a UT when the link path is longer than 1. For example,
A is a source mutable, B is a source mutable, C is derived from A, D is derived from C and B. Will D changes along with A and B? How about it's source mutables?

Add test_nested_mutables

* fix mmcls get classes * resolve comment * resolve comment

* bump version to v0.4.0 * [Enhancement] Make rewriter more powerful (open-mmlab#150) * Finish function tests * lint * resolve comments * Fix tests * docstring & fix * Complement informations * lint * Add example * Fix version * Remove todo Co-authored-by: RunningLeon <mnsheng@yeah.net> * Torchscript support (open-mmlab#159) * support torchscript * add nms * add torchscript configs and update deploy process and dump-info * typescript -> torchscript * add torchscript custom extension support * add ts custom ops again * support mmseg unet * [WIP] add optimizer for torchscript (open-mmlab#119) * add passes * add python api * Torchscript optimizer python api (open-mmlab#121) * add passes * add python api * use python api instead of executable * Merge Master, update optimizer (open-mmlab#151) * [Feature] add yolox ncnn (open-mmlab#29) * add yolox ncnn * add ncnn android performance of yolox * add ut * fix lint * fix None bugs for ncnn * test codecov * test codecov * add device * fix yapf * remove if-else for img shape * use channelshuffle optimize * change benchmark after channelshuffle * fix yapf * fix yapf * fuse continuous reshape * fix static shape deploy * fix code * drop pad * only static shape * fix static * fix docstring * Added mask overlay to output image, changed fprintf info messages to … (open-mmlab#55) * Added mask overlay to output image, changed fprintf info messages to stdout * Improved box filtering (filter area/score), make sure roi coordinates stay within bounds * clang-format * Support UNet in mmseg (open-mmlab#77) * Repeatdataset in train has no CLASSES & PALETTE * update result for unet * update docstring for mmdet * remove ppl for unet in docs * fix ort wrap about input type (open-mmlab#81) * Fix memleak (open-mmlab#86) * delete [] * fix build error when enble MMDEPLOY_ACTIVE_LEVEL * fix lint * [Doc] Nano benchmark and tutorial (open-mmlab#71) * add cls benchmark * add nano zh-cn benchmark and en tutorial * add device row * add doc path to index.rst * fix typo * [Fix] fix missing deploy_core (open-mmlab#80) * fix missing deploy_core * mv flag to demo * target link * [Docs] Fix links in Chinese doc (open-mmlab#84) * Fix docs in Chinese link * Fix links * Delete symbolic link and add links to html * delete files * Fix link * [Feature] Add docker files (open-mmlab#67) * add gpu and cpu dockerfile * fix lint * fix cpu docker and remove redundant * use pip instead * add build arg and readme * fix grammar * update readme * add chinese doc for dockerfile and add docker build to build.md * grammar * refine dockerfiles * add FAQs * update Dpplcv_DIR for SDK building * remove mmcls * add sdk demos * fix typo and lint * update FAQs * [Fix]fix check_env (open-mmlab#101) * fix check_env * update * Replace convert_syncbatchnorm in mmseg (open-mmlab#93) * replace convert_syncbatchnorm with revert_sync_batchnorm from mmcv * change logger * [Doc] Update FAQ for TensorRT (open-mmlab#96) * update FAQ * comment * [Docs]: Update doc for openvino installation (open-mmlab#102) * fix docs * fix docs * fix docs * fix mmcv version * fix docs * rm blank line * simplify non batch nms (open-mmlab#99) * [Enhacement] Allow test.py to save evaluation results (open-mmlab#108) * Add log file * Delete debug code * Rename logger * resolve comments * [Enhancement] Support mmocr v0.4+ (open-mmlab#115) * support mmocr v0.4+ * 0.4.0 -> 0.4.1 * fix onnxruntime wrapper for gpu inference (open-mmlab#123) * fix ncnn wrapper for ort-gpu * resolve comment * fix lint * Fix typo (open-mmlab#132) * lock mmcls version (open-mmlab#131) * [Enhancement] upgrade isort in pre-commit config (open-mmlab#141) * [Enhancement] upgrade isort in pre-commit config by refering to mmflow pr open-mmlab#87 * fix lint * remove .isort.cfg and put its known_third_party to setup.cfg * Fix ci for mmocr (open-mmlab#144) * fix mmocr unittests * remove useless * lock mmdet maximum version to 2.20 * pip install -U numpy * Fix capture_output (open-mmlab#125) Co-authored-by: hanrui1sensetime <83800577+hanrui1sensetime@users.noreply.github.com> Co-authored-by: Johannes L <tehkillerbee@users.noreply.github.com> Co-authored-by: RunningLeon <mnsheng@yeah.net> Co-authored-by: VVsssssk <88368822+VVsssssk@users.noreply.github.com> Co-authored-by: lvhan028 <lvhan_028@163.com> Co-authored-by: AllentDan <41138331+AllentDan@users.noreply.github.com> Co-authored-by: Yifan Zhou <singlezombie@163.com> Co-authored-by: 杨培文 (Yang Peiwen) <915505626@qq.com> Co-authored-by: Semyon Bevzyuk <semen.bevzuk@gmail.com> * configs for all tasks * use torchvision roi align * remote unnecessary code * fix ut * fix ut * export * det dynamic * det dynamic * add ut * fix ut * add ut and docs * fix ut * skip torchscript ut if no ops available * add torchscript option to build.md * update benchmark and resolve comments * resolve conflicts * rename configs * fix mrcnn cuda test * remove useless * add version requirements to docs and comments to codes * enable empty image exporting for torchscript and accelerate ORT inference for MRCNN * rebase * update example for torchscript.md * update FAQs for torchscript.md * resolve comments * only use torchvision roi_align for torchscript * fix ut * use torchvision roi align when pool model is avg * resolve comments Co-authored-by: grimoire <streetyao@live.com> Co-authored-by: grimoire <yaoqian@sensetime.com> Co-authored-by: hanrui1sensetime <83800577+hanrui1sensetime@users.noreply.github.com> Co-authored-by: Johannes L <tehkillerbee@users.noreply.github.com> Co-authored-by: RunningLeon <mnsheng@yeah.net> Co-authored-by: VVsssssk <88368822+VVsssssk@users.noreply.github.com> Co-authored-by: lvhan028 <lvhan_028@163.com> Co-authored-by: Yifan Zhou <singlezombie@163.com> Co-authored-by: 杨培文 (Yang Peiwen) <915505626@qq.com> Co-authored-by: Semyon Bevzyuk <semen.bevzuk@gmail.com> * Update supported mmseg models (open-mmlab#181) * fix ocrnet cascade decoder * update mmseg support models * update mmseg configs * support emanet and icnet * set max K of TopK for tensorrt * update supported models for mmseg in docs * add test for emamodule * add configs and update docs * Update docs * update benchmark * [Features]Support mmdet3d (open-mmlab#103) * add mmdet3d code * add code * update code * [log]This commit finish pointpillar export and evaluate on onnxruntime.The model is sample with nvidia repo model * add tensorrt config * fix config * update * support for tensorrt * add config * fix config` * fix apis about torch2onnx * update * mmdet3d deploy version1.0 * map is ok * fix code * version1.0 * fix code * fix visual * fix bug * tensorrt support success * add docstring * add docs * fix docs * fix comments * fix comment * fix comment * fix openvino wrapper * add unit test * fix device about cpu * fix comment * fix show_result * fix lint * fix requirments * remove ci about det3d * fix ut * add ut data * support for new version pointpillars * fix comment * fix support_list * fix comments * fix config name * [Enhancement] Update pad logic in detection heads (open-mmlab#168) * pad with register * fix lint Co-authored-by: AllentDan <dongchunyu@sensetime.com> * [Enhancement] Additional arguments support for OpenVINO Model Optimizer (open-mmlab#178) * Add mo args. * [Docs]: update docs and argument descriptions (open-mmlab#196) * bump version to v0.4.0 * update docs and argument descriptions * revert version change * fix unnecessary change of config for dynamic exportation (open-mmlab#199) * fix mmcls get classes (open-mmlab#215) * fix mmcls get classes * resolve comment * resolve comment * Add ModelOptimizerOptions. * Fix merge bugs. * Update mmpose.md (open-mmlab#224) * [Dostring]add example in apis docstring (open-mmlab#214) * add example in apis docstring * add backend example in docstring * rm blank line * Fixed get_mo_options_from_cfg args * fix l2norm test Co-authored-by: RunningLeon <mnsheng@yeah.net> Co-authored-by: Haofan Wang <frankmiracle@outlook.com> Co-authored-by: VVsssssk <88368822+VVsssssk@users.noreply.github.com> Co-authored-by: grimoire <yaoqian@sensetime.com> * [Enhancement] Switch to statically typed Value::Any (open-mmlab#209) * replace std::any with StaticAny * fix __compare_typeid * remove fallback id support * constraint on traits::TypeId<T>::value * fix includes * [Enhancement] TensorRT DCN support (open-mmlab#205) * add tensorrt dcn support * fix lint * remove roi_align plugin for ORT (open-mmlab#258) * remove roi_align plugin * remove ut * skip single_roi_extractor UT for ORT in CI * move align to symbolic and update docs * recover UT * resolve comments * [Enhancement]: Support fcn_unet deployment with dynamic shape (open-mmlab#251) * support mmseg fcn+unet dynamic shape * add test * fix ci * fix units * resolve comments * [Enhancement] fix-cmake-relocatable (open-mmlab#223) * require user to specify xxx_dir * fix line ending * fix end-of-file-fixer * try to fix ld cudart cublas * add ENV var search * fix CMAKE_CUDA_COMPILER * cpu, cuda should all work well * remove commented code * fix ncnn example find ncnn package (open-mmlab#282) * table format is wrong (open-mmlab#283) * update pre-commit (open-mmlab#284) * update pre-commit * fix clang-format * fix mmseg config (open-mmlab#281) * fix mmseg config * fix mmpose evaluate outputs * fix lint * update pre-commit config * fix lint * Revert "update pre-commit config" This reverts commit c3fd71611f0b79dfa9ad73fc0f4555c1b3563665. * miss code symbol (open-mmlab#296) * refactor cmake build (open-mmlab#295) * add-mmpose-sdk (open-mmlab#259) * Torchscript support (open-mmlab#159) * support torchscript * add nms * add torchscript configs and update deploy process and dump-info * typescript -> torchscript * add torchscript custom extension support * add ts custom ops again * support mmseg unet * [WIP] add optimizer for torchscript (open-mmlab#119) * add passes * add python api * Torchscript optimizer python api (open-mmlab#121) * add passes * add python api * use python api instead of executable * Merge Master, update optimizer (open-mmlab#151) * [Feature] add yolox ncnn (open-mmlab#29) * add yolox ncnn * add ncnn android performance of yolox * add ut * fix lint * fix None bugs for ncnn * test codecov * test codecov * add device * fix yapf * remove if-else for img shape * use channelshuffle optimize * change benchmark after channelshuffle * fix yapf * fix yapf * fuse continuous reshape * fix static shape deploy * fix code * drop pad * only static shape * fix static * fix docstring * Added mask overlay to output image, changed fprintf info messages to … (open-mmlab#55) * Added mask overlay to output image, changed fprintf info messages to stdout * Improved box filtering (filter area/score), make sure roi coordinates stay within bounds * clang-format * Support UNet in mmseg (open-mmlab#77) * Repeatdataset in train has no CLASSES & PALETTE * update result for unet * update docstring for mmdet * remove ppl for unet in docs * fix ort wrap about input type (open-mmlab#81) * Fix memleak (open-mmlab#86) * delete [] * fix build error when enble MMDEPLOY_ACTIVE_LEVEL * fix lint * [Doc] Nano benchmark and tutorial (open-mmlab#71) * add cls benchmark * add nano zh-cn benchmark and en tutorial * add device row * add doc path to index.rst * fix typo * [Fix] fix missing deploy_core (open-mmlab#80) * fix missing deploy_core * mv flag to demo * target link * [Docs] Fix links in Chinese doc (open-mmlab#84) * Fix docs in Chinese link * Fix links * Delete symbolic link and add links to html * delete files * Fix link * [Feature] Add docker files (open-mmlab#67) * add gpu and cpu dockerfile * fix lint * fix cpu docker and remove redundant * use pip instead * add build arg and readme * fix grammar * update readme * add chinese doc for dockerfile and add docker build to build.md * grammar * refine dockerfiles * add FAQs * update Dpplcv_DIR for SDK building * remove mmcls * add sdk demos * fix typo and lint * update FAQs * [Fix]fix check_env (open-mmlab#101) * fix check_env * update * Replace convert_syncbatchnorm in mmseg (open-mmlab#93) * replace convert_syncbatchnorm with revert_sync_batchnorm from mmcv * change logger * [Doc] Update FAQ for TensorRT (open-mmlab#96) * update FAQ * comment * [Docs]: Update doc for openvino installation (open-mmlab#102) * fix docs * fix docs * fix docs * fix mmcv version * fix docs * rm blank line * simplify non batch nms (open-mmlab#99) * [Enhacement] Allow test.py to save evaluation results (open-mmlab#108) * Add log file * Delete debug code * Rename logger * resolve comments * [Enhancement] Support mmocr v0.4+ (open-mmlab#115) * support mmocr v0.4+ * 0.4.0 -> 0.4.1 * fix onnxruntime wrapper for gpu inference (open-mmlab#123) * fix ncnn wrapper for ort-gpu * resolve comment * fix lint * Fix typo (open-mmlab#132) * lock mmcls version (open-mmlab#131) * [Enhancement] upgrade isort in pre-commit config (open-mmlab#141) * [Enhancement] upgrade isort in pre-commit config by refering to mmflow pr open-mmlab#87 * fix lint * remove .isort.cfg and put its known_third_party to setup.cfg * Fix ci for mmocr (open-mmlab#144) * fix mmocr unittests * remove useless * lock mmdet maximum version to 2.20 * pip install -U numpy * Fix capture_output (open-mmlab#125) Co-authored-by: hanrui1sensetime <83800577+hanrui1sensetime@users.noreply.github.com> Co-authored-by: Johannes L <tehkillerbee@users.noreply.github.com> Co-authored-by: RunningLeon <mnsheng@yeah.net> Co-authored-by: VVsssssk <88368822+VVsssssk@users.noreply.github.com> Co-authored-by: lvhan028 <lvhan_028@163.com> Co-authored-by: AllentDan <41138331+AllentDan@users.noreply.github.com> Co-authored-by: Yifan Zhou <singlezombie@163.com> Co-authored-by: 杨培文 (Yang Peiwen) <915505626@qq.com> Co-authored-by: Semyon Bevzyuk <semen.bevzuk@gmail.com> * configs for all tasks * use torchvision roi align * remote unnecessary code * fix ut * fix ut * export * det dynamic * det dynamic * add ut * fix ut * add ut and docs * fix ut * skip torchscript ut if no ops available * add torchscript option to build.md * update benchmark and resolve comments * resolve conflicts * rename configs * fix mrcnn cuda test * remove useless * add version requirements to docs and comments to codes * enable empty image exporting for torchscript and accelerate ORT inference for MRCNN * rebase * update example for torchscript.md * update FAQs for torchscript.md * resolve comments * only use torchvision roi_align for torchscript * fix ut * use torchvision roi align when pool model is avg * resolve comments Co-authored-by: grimoire <streetyao@live.com> Co-authored-by: grimoire <yaoqian@sensetime.com> Co-authored-by: hanrui1sensetime <83800577+hanrui1sensetime@users.noreply.github.com> Co-authored-by: Johannes L <tehkillerbee@users.noreply.github.com> Co-authored-by: RunningLeon <mnsheng@yeah.net> Co-authored-by: VVsssssk <88368822+VVsssssk@users.noreply.github.com> Co-authored-by: lvhan028 <lvhan_028@163.com> Co-authored-by: Yifan Zhou <singlezombie@163.com> Co-authored-by: 杨培文 (Yang Peiwen) <915505626@qq.com> Co-authored-by: Semyon Bevzyuk <semen.bevzuk@gmail.com> * Update supported mmseg models (open-mmlab#181) * fix ocrnet cascade decoder * update mmseg support models * update mmseg configs * support emanet and icnet * set max K of TopK for tensorrt * update supported models for mmseg in docs * add test for emamodule * add configs and update docs * Update docs * update benchmark * [Features]Support mmdet3d (open-mmlab#103) * add mmdet3d code * add code * update code * [log]This commit finish pointpillar export and evaluate on onnxruntime.The model is sample with nvidia repo model * add tensorrt config * fix config * update * support for tensorrt * add config * fix config` * fix apis about torch2onnx * update * mmdet3d deploy version1.0 * map is ok * fix code * version1.0 * fix code * fix visual * fix bug * tensorrt support success * add docstring * add docs * fix docs * fix comments * fix comment * fix comment * fix openvino wrapper * add unit test * fix device about cpu * fix comment * fix show_result * fix lint * fix requirments * remove ci about det3d * fix ut * add ut data * support for new version pointpillars * fix comment * fix support_list * fix comments * fix config name * [Enhancement] Additional arguments support for OpenVINO Model Optimizer (open-mmlab#178) * Add mo args. * [Docs]: update docs and argument descriptions (open-mmlab#196) * bump version to v0.4.0 * update docs and argument descriptions * revert version change * fix unnecessary change of config for dynamic exportation (open-mmlab#199) * fix mmcls get classes (open-mmlab#215) * fix mmcls get classes * resolve comment * resolve comment * Add ModelOptimizerOptions. * Fix merge bugs. * Update mmpose.md (open-mmlab#224) * [Dostring]add example in apis docstring (open-mmlab#214) * add example in apis docstring * add backend example in docstring * rm blank line * Fixed get_mo_options_from_cfg args * fix l2norm test Co-authored-by: RunningLeon <mnsheng@yeah.net> Co-authored-by: Haofan Wang <frankmiracle@outlook.com> Co-authored-by: VVsssssk <88368822+VVsssssk@users.noreply.github.com> Co-authored-by: grimoire <yaoqian@sensetime.com> * add-mmpose-codebase * fix ci * fix img_shape after TopDownAffine * rename TopDown module -> XheadDecode & implement regression decode * align keypoints_from_heatmap * remove hardcode keypoint_head, need refactor, current only support topdown config * add mmpose python api * update mmpose-python code * can't clip fake box * fix rebase error * fix rebase error * link mspn decoder to base decoder * fix ci * compile with gcc7.5 * remove no use code * fix * fix prompt * remove unnecessary cv::parallel_for_ * rewrite TopdownHeatmapMultiStageHead.inference_model * add comment * add more detail docstring why use _cs2xyxy in sdk backend * fix Registry name * remove no use param & add comment of output result Co-authored-by: AllentDan <41138331+AllentDan@users.noreply.github.com> Co-authored-by: grimoire <streetyao@live.com> Co-authored-by: grimoire <yaoqian@sensetime.com> Co-authored-by: hanrui1sensetime <83800577+hanrui1sensetime@users.noreply.github.com> Co-authored-by: Johannes L <tehkillerbee@users.noreply.github.com> Co-authored-by: RunningLeon <mnsheng@yeah.net> Co-authored-by: VVsssssk <88368822+VVsssssk@users.noreply.github.com> Co-authored-by: lvhan028 <lvhan_028@163.com> Co-authored-by: Yifan Zhou <singlezombie@163.com> Co-authored-by: 杨培文 (Yang Peiwen) <915505626@qq.com> Co-authored-by: Semyon Bevzyuk <semen.bevzuk@gmail.com> Co-authored-by: Haofan Wang <frankmiracle@outlook.com> * update faq about WinError 1455 (open-mmlab#297) * update faq about WinError 1455 * Update faq.md * Update faq.md * fix ci Co-authored-by: chenxin2 <chenxin2@sensetime.com> * [Feature]Support centerpoint (open-mmlab#252) * bump version to v0.4.0 * [Enhancement] Make rewriter more powerful (open-mmlab#150) * Finish function tests * lint * resolve comments * Fix tests * docstring & fix * Complement informations * lint * Add example * Fix version * Remove todo Co-authored-by: RunningLeon <mnsheng@yeah.net> * Torchscript support (open-mmlab#159) * support torchscript * add nms * add torchscript configs and update deploy process and dump-info * typescript -> torchscript * add torchscript custom extension support * add ts custom ops again * support mmseg unet * [WIP] add optimizer for torchscript (open-mmlab#119) * add passes * add python api * Torchscript optimizer python api (open-mmlab#121) * add passes * add python api * use python api instead of executable * Merge Master, update optimizer (open-mmlab#151) * [Feature] add yolox ncnn (open-mmlab#29) * add yolox ncnn * add ncnn android performance of yolox * add ut * fix lint * fix None bugs for ncnn * test codecov * test codecov * add device * fix yapf * remove if-else for img shape * use channelshuffle optimize * change benchmark after channelshuffle * fix yapf * fix yapf * fuse continuous reshape * fix static shape deploy * fix code * drop pad * only static shape * fix static * fix docstring * Added mask overlay to output image, changed fprintf info messages to … (open-mmlab#55) * Added mask overlay to output image, changed fprintf info messages to stdout * Improved box filtering (filter area/score), make sure roi coordinates stay within bounds * clang-format * Support UNet in mmseg (open-mmlab#77) * Repeatdataset in train has no CLASSES & PALETTE * update result for unet * update docstring for mmdet * remove ppl for unet in docs * fix ort wrap about input type (open-mmlab#81) * Fix memleak (open-mmlab#86) * delete [] * fix build error when enble MMDEPLOY_ACTIVE_LEVEL * fix lint * [Doc] Nano benchmark and tutorial (open-mmlab#71) * add cls benchmark * add nano zh-cn benchmark and en tutorial * add device row * add doc path to index.rst * fix typo * [Fix] fix missing deploy_core (open-mmlab#80) * fix missing deploy_core * mv flag to demo * target link * [Docs] Fix links in Chinese doc (open-mmlab#84) * Fix docs in Chinese link * Fix links * Delete symbolic link and add links to html * delete files * Fix link * [Feature] Add docker files (open-mmlab#67) * add gpu and cpu dockerfile * fix lint * fix cpu docker and remove redundant * use pip instead * add build arg and readme * fix grammar * update readme * add chinese doc for dockerfile and add docker build to build.md * grammar * refine dockerfiles * add FAQs * update Dpplcv_DIR for SDK building * remove mmcls * add sdk demos * fix typo and lint * update FAQs * [Fix]fix check_env (open-mmlab#101) * fix check_env * update * Replace convert_syncbatchnorm in mmseg (open-mmlab#93) * replace convert_syncbatchnorm with revert_sync_batchnorm from mmcv * change logger * [Doc] Update FAQ for TensorRT (open-mmlab#96) * update FAQ * comment * [Docs]: Update doc for openvino installation (open-mmlab#102) * fix docs * fix docs * fix docs * fix mmcv version * fix docs * rm blank line * simplify non batch nms (open-mmlab#99) * [Enhacement] Allow test.py to save evaluation results (open-mmlab#108) * Add log file * Delete debug code * Rename logger * resolve comments * [Enhancement] Support mmocr v0.4+ (open-mmlab#115) * support mmocr v0.4+ * 0.4.0 -> 0.4.1 * fix onnxruntime wrapper for gpu inference (open-mmlab#123) * fix ncnn wrapper for ort-gpu * resolve comment * fix lint * Fix typo (open-mmlab#132) * lock mmcls version (open-mmlab#131) * [Enhancement] upgrade isort in pre-commit config (open-mmlab#141) * [Enhancement] upgrade isort in pre-commit config by refering to mmflow pr open-mmlab#87 * fix lint * remove .isort.cfg and put its known_third_party to setup.cfg * Fix ci for mmocr (open-mmlab#144) * fix mmocr unittests * remove useless * lock mmdet maximum version to 2.20 * pip install -U numpy * Fix capture_output (open-mmlab#125) Co-authored-by: hanrui1sensetime <83800577+hanrui1sensetime@users.noreply.github.com> Co-authored-by: Johannes L <tehkillerbee@users.noreply.github.com> Co-authored-by: RunningLeon <mnsheng@yeah.net> Co-authored-by: VVsssssk <88368822+VVsssssk@users.noreply.github.com> Co-authored-by: lvhan028 <lvhan_028@163.com> Co-authored-by: AllentDan <41138331+AllentDan@users.noreply.github.com> Co-authored-by: Yifan Zhou <singlezombie@163.com> Co-authored-by: 杨培文 (Yang Peiwen) <915505626@qq.com> Co-authored-by: Semyon Bevzyuk <semen.bevzuk@gmail.com> * configs for all tasks * use torchvision roi align * remote unnecessary code * fix ut * fix ut * export * det dynamic * det dynamic * add ut * fix ut * add ut and docs * fix ut * skip torchscript ut if no ops available * add torchscript option to build.md * update benchmark and resolve comments * resolve conflicts * rename configs * fix mrcnn cuda test * remove useless * add version requirements to docs and comments to codes * enable empty image exporting for torchscript and accelerate ORT inference for MRCNN * rebase * update example for torchscript.md * update FAQs for torchscript.md * resolve comments * only use torchvision roi_align for torchscript * fix ut * use torchvision roi align when pool model is avg * resolve comments Co-authored-by: grimoire <streetyao@live.com> Co-authored-by: grimoire <yaoqian@sensetime.com> Co-authored-by: hanrui1sensetime <83800577+hanrui1sensetime@users.noreply.github.com> Co-authored-by: Johannes L <tehkillerbee@users.noreply.github.com> Co-authored-by: RunningLeon <mnsheng@yeah.net> Co-authored-by: VVsssssk <88368822+VVsssssk@users.noreply.github.com> Co-authored-by: lvhan028 <lvhan_028@163.com> Co-authored-by: Yifan Zhou <singlezombie@163.com> Co-authored-by: 杨培文 (Yang Peiwen) <915505626@qq.com> Co-authored-by: Semyon Bevzyuk <semen.bevzuk@gmail.com> * Update supported mmseg models (open-mmlab#181) * fix ocrnet cascade decoder * update mmseg support models * update mmseg configs * support emanet and icnet * set max K of TopK for tensorrt * update supported models for mmseg in docs * add test for emamodule * add configs and update docs * Update docs * update benchmark * [Features]Support mmdet3d (open-mmlab#103) * add mmdet3d code * add code * update code * [log]This commit finish pointpillar export and evaluate on onnxruntime.The model is sample with nvidia repo model * add tensorrt config * fix config * update * support for tensorrt * add config * fix config` * fix apis about torch2onnx * update * mmdet3d deploy version1.0 * map is ok * fix code * version1.0 * fix code * fix visual * fix bug * tensorrt support success * add docstring * add docs * fix docs * fix comments * fix comment * fix comment * fix openvino wrapper * add unit test * fix device about cpu * fix comment * fix show_result * fix lint * fix requirments * remove ci about det3d * fix ut * add ut data * support for new version pointpillars * fix comment * fix support_list * fix comments * fix config name * [Enhancement] Update pad logic in detection heads (open-mmlab#168) * pad with register * fix lint Co-authored-by: AllentDan <dongchunyu@sensetime.com> * [Enhancement] Additional arguments support for OpenVINO Model Optimizer (open-mmlab#178) * Add mo args. * [Docs]: update docs and argument descriptions (open-mmlab#196) * bump version to v0.4.0 * update docs and argument descriptions * revert version change * fix unnecessary change of config for dynamic exportation (open-mmlab#199) * fix mmcls get classes (open-mmlab#215) * fix mmcls get classes * resolve comment * resolve comment * Add ModelOptimizerOptions. * Fix merge bugs. * Update mmpose.md (open-mmlab#224) * [Dostring]add example in apis docstring (open-mmlab#214) * add example in apis docstring * add backend example in docstring * rm blank line * Fixed get_mo_options_from_cfg args * fix l2norm test Co-authored-by: RunningLeon <mnsheng@yeah.net> Co-authored-by: Haofan Wang <frankmiracle@outlook.com> Co-authored-by: VVsssssk <88368822+VVsssssk@users.noreply.github.com> Co-authored-by: grimoire <yaoqian@sensetime.com> * [Enhancement] Switch to statically typed Value::Any (open-mmlab#209) * replace std::any with StaticAny * fix __compare_typeid * remove fallback id support * constraint on traits::TypeId<T>::value * fix includes * support for centerpoint * [Enhancement] TensorRT DCN support (open-mmlab#205) * add tensorrt dcn support * fix lint * add docstring and dcn model support * add centerpoint ut and docs * add config and fix input rank * fix merge error * fix a bug * fix comment * [Doc] update benchmark add supported-model-list (#286) * update benchmark add supported-model-list * fix lint * fix lint * loc mmocr maximum version * fix ut Co-authored-by: maningsheng <mnsheng@yeah.net> Co-authored-by: Yifan Zhou <singlezombie@163.com> Co-authored-by: AllentDan <41138331+AllentDan@users.noreply.github.com> Co-authored-by: grimoire <streetyao@live.com> Co-authored-by: grimoire <yaoqian@sensetime.com> Co-authored-by: hanrui1sensetime <83800577+hanrui1sensetime@users.noreply.github.com> Co-authored-by: Johannes L <tehkillerbee@users.noreply.github.com> Co-authored-by: lvhan028 <lvhan_028@163.com> Co-authored-by: 杨培文 (Yang Peiwen) <915505626@qq.com> Co-authored-by: Semyon Bevzyuk <semen.bevzuk@gmail.com> Co-authored-by: AllentDan <dongchunyu@sensetime.com> Co-authored-by: Haofan Wang <frankmiracle@outlook.com> Co-authored-by: lzhangzz <lzhang329@gmail.com> Co-authored-by: maningsheng <mnsheng@yeah.net> Co-authored-by: Yifan Zhou <singlezombie@163.com> Co-authored-by: AllentDan <41138331+AllentDan@users.noreply.github.com> Co-authored-by: grimoire <streetyao@live.com> Co-authored-by: grimoire <yaoqian@sensetime.com> Co-authored-by: hanrui1sensetime <83800577+hanrui1sensetime@users.noreply.github.com> Co-authored-by: Johannes L <tehkillerbee@users.noreply.github.com> Co-authored-by: VVsssssk <88368822+VVsssssk@users.noreply.github.com> Co-authored-by: 杨培文 (Yang Peiwen) <915505626@qq.com> Co-authored-by: Semyon Bevzyuk <semen.bevzuk@gmail.com> Co-authored-by: AllentDan <dongchunyu@sensetime.com> Co-authored-by: Haofan Wang <frankmiracle@outlook.com> Co-authored-by: lzhangzz <lzhang329@gmail.com> Co-authored-by: Chen Xin <xinchen.tju@gmail.com> Co-authored-by: chenxin2 <chenxin2@sensetime.com>

pppppM requested review from gaoyang07 and sunnyxiaohu August 1, 2022 07:29

sunnyxiaohu reviewed Aug 2, 2022

View reviewed changes

sunnyxiaohu reviewed Aug 4, 2022

View reviewed changes

mmrazor/engine/runner/autoslim_val_loop.py Outdated Show resolved Hide resolved

mmrazor/engine/runner/autoslim_val_loop.py Outdated Show resolved Hide resolved

mmrazor/models/mutators/channel_mutator/slimmable_channel_mutator.py Outdated Show resolved Hide resolved

wutongshenqiu mentioned this pull request Aug 4, 2022

[Feature] Add BigNAS algorithm #219

Merged

wutongshenqiu force-pushed the add-derived-mutable branch from 148a8ba to 8b55218 Compare August 8, 2022 06:00

wutongshenqiu changed the title ~~[Feature] Add DerivedMutable and refactor dynamic ops~~ [Feature] Add DerivedMutable & MutableValue Aug 8, 2022

sunnyxiaohu reviewed Aug 9, 2022

View reviewed changes

wutongshenqiu added 6 commits August 10, 2022 10:17

fix lint

b897cfd

complement unittest for derived mutable

2313ba2

add docstring for derived mutable

20a06ce

add unittest for mutable value

1504bf9

fix logger error

eaf57a1

fix according to comments

953dfb7

wutongshenqiu force-pushed the add-derived-mutable branch from 089f2a6 to 953dfb7 Compare August 10, 2022 02:19

wutongshenqiu added 3 commits August 10, 2022 13:04

not dump derived mutable when export

fd7e4f9

add warning in export_fix_subnet

e9d1064

fix __mul__ in mutable value

dff284e

sunnyxiaohu merged commit 7dca9ba into open-mmlab:dev-1.x Aug 10, 2022

humu789 pushed a commit to humu789/mmrazor that referenced this pull request Feb 13, 2023

fix mmcls get classes (open-mmlab#215)

120f4ac

* fix mmcls get classes * resolve comment * resolve comment

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[Feature] Add `DerivedMutable` & `MutableValue` #215

[Feature] Add `DerivedMutable` & `MutableValue` #215

wutongshenqiu commented Aug 1, 2022 •

edited

Loading

codecov bot commented Aug 1, 2022 •

edited

Loading

sunnyxiaohu Aug 2, 2022

wutongshenqiu Aug 8, 2022

sunnyxiaohu Aug 9, 2022

wutongshenqiu Aug 10, 2022

sunnyxiaohu Aug 9, 2022

wutongshenqiu Aug 9, 2022

sunnyxiaohu Aug 9, 2022

wutongshenqiu Aug 10, 2022

sunnyxiaohu Aug 9, 2022

wutongshenqiu Aug 9, 2022

sunnyxiaohu Aug 9, 2022

wutongshenqiu Aug 10, 2022

sunnyxiaohu Aug 9, 2022

wutongshenqiu Aug 10, 2022

sunnyxiaohu Aug 9, 2022

wutongshenqiu Aug 10, 2022

sunnyxiaohu Aug 9, 2022

wutongshenqiu Aug 10, 2022

[Feature] Add DerivedMutable & MutableValue #215

[Feature] Add DerivedMutable & MutableValue #215

Conversation

wutongshenqiu commented Aug 1, 2022 • edited Loading

Motivation

Modification

codecov bot commented Aug 1, 2022 • edited Loading

Codecov Report

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

[Feature] Add `DerivedMutable` & `MutableValue` #215

[Feature] Add `DerivedMutable` & `MutableValue` #215

wutongshenqiu commented Aug 1, 2022 •

edited

Loading

codecov bot commented Aug 1, 2022 •

edited

Loading