Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

how to use cwd in feature map #45

Closed
wwjwy opened this issue Jan 8, 2022 · 1 comment
Closed

how to use cwd in feature map #45

wwjwy opened this issue Jan 8, 2022 · 1 comment

Comments

@wwjwy
Copy link

wwjwy commented Jan 8, 2022

hi,
I notice that the cwd is used only in Logits map in segmentation task. But the paper also contains the cwd used in feature map, can you give me an example how to modify the config file?

mmrazor/configs/distill/cwd/cwd_cls_head_pspnet_r101_d8_pspnet_r18_d8_512x1024_cityscapes_80k.py

Line 94 in b6c5fff

student_module='decode_head.conv_seg',

@pppppM
Copy link
Collaborator

pppppM commented Jan 17, 2022

Because the model structure and training settings in CWD are quite different from mmseg, the CWD in mmrazor is not the same as the paper.
If you want to distill on the feature map, you can modify the corresponding name according to your model.
It should be decode_head.bottleneck in the PSPNet.

@pppppM pppppM closed this as completed Jan 26, 2022
humu789 pushed a commit to humu789/mmrazor that referenced this issue Feb 13, 2023
@grimoire @AllentDan
@RunningLeon @SingleZombie
[Feature] Refactor v1 (open-mmlab#56)
2b98040 
* [Refactor] add enum class and use functions to get configuration (open-mmlab#40)

* add task and codebase enum class

* use funcitons to get config

* Refactor wrappers of mmcls and mmseg (open-mmlab#41)

* move wrappers of cls & det to apis

* remove get_classes_from_config

* rename onnx_helper to onnx_utils

* move import to outside of class

* refactor ortwrappers

* Refactor build dataset and dataloader for mmseg (open-mmlab#44)

* refactor build_dataset and build_dataloader for mmcls and mmseg

* remove repeated classes

* set build_dataloader with shuffle=False

* [Refactor] pplwrapper and mmocr refactor (open-mmlab#46)

* add

* add pplwrapper and refactor mmocr

* fix lint

* remove unused arguments

* apply dict input for pplwrapper and ortwrapper

* add condition before import ppl and ort stuff

* update ppl (open-mmlab#51)

* Refactor return value and extract_model (open-mmlab#54)

* remove ret_value

* refactor extract_model

* fix typo

* resolve comments

* [Refactor] Refactor model inference pipeline (open-mmlab#52)

* move attribute_to_dict to extract_model

* simplify the inference and visualization

* remove unused import

* [Feature] Support SRCNN in mmedit with ONNXRuntime and TensorRT (open-mmlab#45)

* finish mmedit-ort

* edit __init__ files

* add noqa

* add tensorrt support

* 1. Rename "base.py"
2. Move srcnn.py to correct directory

* fix bugs

* remove figures

* align to refactor-v1

* update comment in srcnn

* fix lint

* newfunc -> new_func

* Add visualize.py

split visualize() in each codebase

* fix lint

* fix lint

* remove unnecessary code in ORTRestorer

* remove .api

* edit super(), remove dataset

* [Refactor]: Change name of split to partition (open-mmlab#57)

* refactor mmcls configs

* refactor mmdet configs and split params

* rename rest split to partition from master

* remove base.py

* fix init of inference class

* fix mmocr init, add show_result alias

Co-authored-by: AllentDan <41138331+AllentDan@users.noreply.github.com>
Co-authored-by: RunningLeon <maningsheng@sensetime.com>
Co-authored-by: Yifan Zhou <singlezombie@163.com>
humu789 pushed a commit to humu789/mmrazor that referenced this issue Feb 13, 2023
@lzhangzz
Refactor cuda resize (open-mmlab#45)
03ae26c 
* refactor cuda resize

* add warning for ppl.cv < 0.6

* fix code style
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@wwjwy @pppppM