8000 Update PSP Params by zhanghang1989 · Pull Request #629 · dmlc/gluon-cv · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Update PSP Params #629

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

Merged
merged 2 commits into from
Feb 19, 2019
Merged

Update PSP Params #629

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1b1fd8c
psp
Feb 7, 2019
455382c
update psp params
Feb 19, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
43 changes: 31 additions & 12 deletions docs/model_zoo/segmentation.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,28 @@ Table of pre-trained models for semantic segmentation and their performance.
.. role:: raw-html(raw)
:format: html

ADE20K Dataset
--------------

+-----------------------+-----------------+-----------+-----------+------------------------------------------------------------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------+
| Name | Method | pixAcc | mIoU | Command | log |
+=======================+=================+===========+===========+==============================================================================================================================+=====================================================================================================================+
| fcn_resnet50_ade | FCN [2]_ | 79.0 | 39.5 | `shell script <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/fcn_resnet50_ade.sh>`_ | `log <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/fcn_resnet50_ade.log>`_ |
+-----------------------+-----------------+-----------+-----------+------------------------------------------------------------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------+
| fcn_resnet101_ade | FCN [2]_ | 80.6 | 41.6 | `shell script <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/fcn_resnet101_ade.sh>`_ | `log <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/fcn_resnet101_ade.log>`_ |
+-----------------------+-----------------+-----------+-----------+------------------------------------------------------------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------+
| psp_resnet50_ade | PSP [3]_ | 80.1 | 41.5 | `shell script <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/psp_resnet50_ade.sh>`_ | `log <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/psp_resnet50_ade.log>`_ |
+-----------------------+-----------------+-----------+-----------+------------------------------------------------------------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------+
| psp_resnet101_ade | PSP [3]_ | 80.8 | 43.3 | `shell script <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/psp_resnet101_ade.sh>`_ | `log <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/psp_resnet101_ade.log>`_ |
+-----------------------+-----------------+-----------+-----------+------------------------------------------------------------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------+
| deeplab_resnet50_ade | DeepLabV3 [4]_ | 80.5 | 42.5 | `shell script <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/deeplab_resnet50_ade.sh>`_ | `log <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/deeplab_resnet50_ade.log>`_ |
+-----------------------+-----------------+-----------+-----------+------------------------------------------------------------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------+
| deeplab_resnet101_ade | DeepLabV3 [4]_ | 81.1 | 44.1 | `shell script <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/deeplab_resnet101_ade.sh>`_ | `log <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/deeplab_resnet101_ade.log>`_ |
+-----------------------+-----------------+-----------+-----------+------------------------------------------------------------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------+

MS-COCO Dataset Pretrain
------------------------

+-----------------------+-----------------+-----------+-----------+------------------------------------------------------------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------+
| Name | Method | pixAcc | mIoU | Command | log |
+=======================+=================+===========+===========+==============================================================================================================================+=====================================================================================================================+
Expand All @@ -40,6 +62,14 @@ Table of pre-trained models for semantic segmentation and their performance.
+-----------------------+-----------------+-----------+-----------+------------------------------------------------------------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------+
| deeplab_resnet101_coco| DeepLabV3 [4]_ | 92.5 | 70.4 | `shell script <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/deeplab_resnet101_coco.sh>`_ | `log <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/deeplab_resnet101_coco.log>`_|
+-----------------------+-----------------+-----------+-----------+------------------------------------------------------------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------+


Pascal VOC Dataset
------------------

+-----------------------+-----------------+-----------+-----------+------------------------------------------------------------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------+
| Name | Method | pixAcc | mIoU | Command | log |
+=======================+=================+===========+===========+==============================================================================================================================+=====================================================================================================================+
| fcn_resnet101_voc | FCN [2]_ | N/A | 83.6_ | `shell script <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/fcn_resnet101_voc.sh>`_ | `log <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/fcn_resnet101_voc.log>`_ |
+-----------------------+-----------------+-----------+-----------+------------------------------------------------------------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------+
| psp_resnet101_voc | PSP [3]_ | N/A | 85.1_ | `shell script <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/psp_resnet101_voc.sh>`_ | `log <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/psp_resnet101_voc.log>`_ |
Expand All @@ -48,18 +78,6 @@ Table of pre-trained models for semantic segmentation and their performance.
+-----------------------+-----------------+-----------+-----------+------------------------------------------------------------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------+
| deeplab_resnet152_voc | DeepLabV3 [4]_ | N/A | 86.7_ | `shell script <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/deeplab_resnet152_voc.sh>`_ | `log <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/deeplab_resnet152_voc.log>`_ |
+-----------------------+-----------------+-----------+-----------+------------------------------------------------------------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------+
| fcn_resnet50_ade | FCN [2]_ | 79.0 | 39.5 | `shell script <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/fcn_resnet50_ade.sh>`_ | `log <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/fcn_resnet50_ade.log>`_ |
+-----------------------+-----------------+-----------+-----------+------------------------------------------------------------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------+
| fcn_resnet101_ade | FCN [2]_ | 80.6 | 41.6 | `shell script <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/fcn_resnet101_ade.sh>`_ | `log <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/fcn_resnet101_ade.log>`_ |
+-----------------------+-----------------+-----------+-----------+------------------------------------------------------------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------+
| psp_resnet50_ade | PSP [3]_ | 80.1 | 41.6 | `shell script <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/psp_resnet50_ade.sh>`_ | `log <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/psp_resnet50_ade.log>`_ |
+-----------------------+-----------------+-----------+-----------+------------------------------------------------------------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------+
| psp_resnet101_ade | PSP [3]_ | 80.8 | 42.9 | `shell script <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/psp_resnet101_ade.sh>`_ | `log <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/psp_resnet101_ade.log>`_ |
+-----------------------+-----------------+-----------+-----------+------------------------------------------------------------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------+
| deeplab_resnet50_ade | DeepLabV3 [4]_ | 80.5 | 42.5 | `shell script <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/deeplab_resnet50_ade.sh>`_ | `log <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/deeplab_resnet50_ade.log>`_ |
+-----------------------+-----------------+-----------+-----------+------------------------------------------------------------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------+
| deeplab_resnet101_ade | DeepLabV3 [4]_ | 81.1 | 44.1 | `shell script <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/deeplab_resnet101_ade.sh>`_ | `log <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/deeplab_resnet101_ade.log>`_ |
+-----------------------+-----------------+-----------+-----------+------------------------------------------------------------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------+
| psp_resnet101_citys | PSP [3]_ | N/A | 77.1 | `shell script <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/psp_resnet101_city.sh>`_ | `log <https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs/segmentation/psp_resnet101_city.log>`_ |
+-----------------------+-----------------+-----------+-----------+------------------------------------------------------------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------+

Expand All @@ -68,6 +86,7 @@ Table of pre-trained models for semantic segmentation and their performance.
.. _86.2: http://host.robots.ox.ac.uk:8080/anonymous/ZPN6II.html
.. _86.7: http://host.robots.ox.ac.uk:8080/anonymous/XZEXL2.html


Instance Segmentation
~~~~~~~~~~~~~~~~~~~~~

Expand Down
8 changes: 4 additions & 4 deletions gluoncv/model_zoo/model_store.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -89,10 +89,10 @@
('d35bea8817935d1ab310ef1e6dd06bb18c2d5f0d', 'deeplab_resnet152_voc'),
('c7789b237adc7253405bee57c84d53b15db45942', 'deeplab_resnet50_ade'),
('bf1584dfcec12063eff3075ee643e181c0f6d443', 'deeplab_resnet101_ade'),
('09e79ac5b6832724e82b57ec714f08205225a559', 'psp_resnet101_coco'),
('3f1cce66eb3942fdcc0cca68b56a5bb73c464e01', 'psp_resnet101_voc'),
('0c42cb735aebbffc010ca5770e3d5880995da021', 'psp_resnet50_ade'),
('eaaa87eb1b27c36c935b372779214bf164ad5b19', 'psp_resnet101_ade'),
('09f89cad0e107cb2bffdb1b07706ba31798096f2', 'psp_resnet101_coco'),
('2c2f4e1c2b11461b52598a4b2038bccbcfc166eb', 'psp_resnet101_voc'),
('3f220f537400dfa607c3d041ed3b172db39b0b01', 'psp_resnet50_ade'),
('240a4758b506447faf7c55cd7a7837d66f5039a6', 'psp_resnet101_ade'),
('0f49fb59180c4d91305b858380a4fd6eaf068b6c', 'psp_resnet101_citys'),
('f5ece5ce1422eeca3ce2908004e469ffdf91fd41', 'yolo3_darknet53_voc'),
('09767802230b45af1c27697a2dad6d1ebaacc1e2', 'yolo3_darknet53_coco'),
Expand Down
2 changes: 1 addition & 1 deletion gluoncv/model_zoo/pspnet.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -92,7 +92,7 @@ def hybrid_forward(self, F, x):
feat1 = self.upsample(F, self.conv1(self.pool(F, x, 1)), h, w)
feat2 = self.upsample(F, self.conv2(self.pool(F, x, 2)), h, w)
feat3 = self.upsample(F, self.conv3(self.pool(F, x, 3)), h, w)
feat4 = self.upsample(F, self.conv4(self.pool(F, x, 4)), h, w)
feat4 = self.upsample(F, self.conv4(self.pool(F, x, 6)), h, w)
return F.concat(x, feat1, feat2, feat3, feat4, dim=1)


Expand Down
0