Skip to content

Commit

Permalink
DeepLabV3_ResNeSt200_ADE 48.36 mIoU (zhanghang1989#264)
Browse files Browse the repository at this point in the history
  • Loading branch information
@zhanghang1989
zhanghang1989 committed Apr 26, 2020
1 parent 69ba678 commit 3e384b4
Show file tree
Hide file tree
Showing 4 changed files with 298 additions and 20 deletions.
43 changes: 24 additions & 19 deletions docs/source/model_zoo/segmentation.rst
View file
Original file line number Diff line number Diff line change
Expand Up @@ -36,31 +36,36 @@ ResNeSt Backbone Models
Model pixAcc mIoU Command
============================================================================== ============== ============== =========================================================================================================
FCN_ResNeSt50_ADE 80.18% 42.94% :raw-html:`<a href="javascript:toggleblock('cmd_fcn_nest50_ade')" class="toggleblock">cmd</a>`
DeepLabV3_ResNeSt50_ADE 81.17% 45.12% :raw-html:`<a href="javascript:toggleblock('cmd_deeplab_resnest50_ade')" class="toggleblock">cmd</a>`
DeepLabV3_ResNeSt101_ADE 82.07% 46.91% :raw-html:`<a href="javascript:toggleblock('cmd_deeplab_resnest101_ade')" class="toggleblock">cmd</a>`
DeepLabV3_ResNeSt269_ADE 82.62% 47.60% :raw-html:`<a href="javascript:toggleblock('cmd_deeplab_resnest269_ade')" class="toggleblock">cmd</a>`
DeepLab_ResNeSt50_ADE 81.17% 45.12% :raw-html:`<a href="javascript:toggleblock('cmd_deeplab_resnest50_ade')" class="toggleblock">cmd</a>`
DeepLab_ResNeSt101_ADE 82.07% 46.91% :raw-html:`<a href="javascript:toggleblock('cmd_deeplab_resnest101_ade')" class="toggleblock">cmd</a>`
DeepLab_ResNeSt200_ADE 82.45% 48.36% :raw-html:`<a href="javascript:toggleblock('cmd_deeplab_resnest200_ade')" class="toggleblock">cmd</a>`
DeepLab_ResNeSt269_ADE 82.62% 47.60% :raw-html:`<a href="javascript:toggleblock('cmd_deeplab_resnest269_ade')" class="toggleblock">cmd</a>`
============================================================================== ============== ============== =========================================================================================================

.. raw:: html

<code xml:space="preserve" id="cmd_fcn_nest50_ade" style="display: none; text-align: left; white-space: pre-wrap">
python train_dist.py --dataset ADE20K --model fcn --aux --backbone resnest50
python train.py --dataset ADE20K --model fcn --aux --backbone resnest50
</code>

<code xml:space="preserve" id="cmd_enc_nest50_ade" style="display: none; text-align: left; white-space: pre-wrap">
python train_dist.py --dataset ADE20K --model EncNet --aux --se-loss --backbone resnest50
python train.py --dataset ADE20K --model EncNet --aux --se-loss --backbone resnest50
</code>

<code xml:space="preserve" id="cmd_deeplab_resnest50_ade" style="display: none; text-align: left; white-space: pre-wrap">
python train_dist.py --dataset ADE20K --model deeplab --aux --backbone resnest50
python train.py --dataset ADE20K --model deeplab --aux --backbone resnest50
</code>

<code xml:space="preserve" id="cmd_deeplab_resnest101_ade" style="display: none; text-align: left; white-space: pre-wrap">
python train_dist.py --dataset ADE20K --model deeplab --aux --backbone resnest101
python train.py --dataset ADE20K --model deeplab --aux --backbone resnest101
</code>

<code xml:space="preserve" id="cmd_deeplab_resnest200_ade" style="display: none; text-align: left; white-space: pre-wrap">
python train.py --dataset ADE20K --model deeplab --aux --backbone resnest200 --epochs 180
</code>

<code xml:space="preserve" id="cmd_deeplab_resnest269_ade" style="display: none; text-align: left; white-space: pre-wrap">
python train_dist.py --dataset ADE20K --model deeplab --aux --backbone resnest269
python train.py --dataset ADE20K --model deeplab --aux --backbone resnest269
</code>


Expand All @@ -82,19 +87,19 @@ EncNet_ResNet101s_ADE
.. raw:: html

<code xml:space="preserve" id="cmd_fcn50_ade" style="display: none; text-align: left; white-space: pre-wrap">
CUDA_VISIBLE_DEVICES=0,1,2,3 python train_dist.py --dataset ADE20K --model FCN
CUDA_VISIBLE_DEVICES=0,1,2,3 python train.py --dataset ADE20K --model FCN
</code>

<code xml:space="preserve" id="cmd_psp50_ade" style="display: none; text-align: left; white-space: pre-wrap">
CUDA_VISIBLE_DEVICES=0,1,2,3 python train_dist.py --dataset ADE20K --model PSP --aux
CUDA_VISIBLE_DEVICES=0,1,2,3 python train.py --dataset ADE20K --model PSP --aux
</code>

<code xml:space="preserve" id="cmd_enc50_ade" style="display: none; text-align: left; white-space: pre-wrap">
CUDA_VISIBLE_DEVICES=0,1,2,3 python train_dist.py --dataset ADE20K --model EncNet --aux --se-loss
CUDA_VISIBLE_DEVICES=0,1,2,3 python train.py --dataset ADE20K --model EncNet --aux --se-loss
</code>

<code xml:space="preserve" id="cmd_enc101_ade" style="display: none; text-align: left; white-space: pre-wrap">
CUDA_VISIBLE_DEVICES=0,1,2,3 python train_dist.py --dataset ADE20K --model EncNet --aux --se-loss --backbone resnet101
CUDA_VISIBLE_DEVICES=0,1,2,3 python train.py --dataset ADE20K --model EncNet --aux --se-loss --backbone resnet101
</code>

Pascal Context Dataset
Expand All @@ -110,15 +115,15 @@ EncNet_ResNet101s_PContext
.. raw:: html

<code xml:space="preserve" id="cmd_fcn50_pcont" style="display: none; text-align: left; white-space: pre-wrap">
CUDA_VISIBLE_DEVICES=0,1,2,3 python train_dist.py --dataset PContext --model FCN
CUDA_VISIBLE_DEVICES=0,1,2,3 python train.py --dataset PContext --model FCN
</code>

<code xml:space="preserve" id="cmd_enc50_pcont" style="display: none; text-align: left; white-space: pre-wrap">
CUDA_VISIBLE_DEVICES=0,1,2,3 python train_dist.py --dataset PContext --model EncNet --aux --se-loss
CUDA_VISIBLE_DEVICES=0,1,2,3 python train.py --dataset PContext --model EncNet --aux --se-loss
</code>

<code xml:space="preserve" id="cmd_enc101_pcont" style="display: none; text-align: left; white-space: pre-wrap">
CUDA_VISIBLE_DEVICES=0,1,2,3 python train_dist.py --dataset PContext --model EncNet --aux --se-loss --backbone resnet101
CUDA_VISIBLE_DEVICES=0,1,2,3 python train.py --dataset PContext --model EncNet --aux --se-loss --backbone resnet101
</code>


Expand All @@ -136,9 +141,9 @@ EncNet_ResNet101s_VOC
<code xml:space="preserve" id="cmd_enc101_voc" style="display: none; text-align: left; white-space: pre-wrap">
# First finetuning COCO dataset pretrained model on augmented set
# You can also train from scratch on COCO by yourself
CUDA_VISIBLE_DEVICES=0,1,2,3 python train_dist.py --dataset Pascal_aug --model-zoo EncNet_Resnet101_COCO --aux --se-loss --lr 0.001 --syncbn --ngpus 4 --checkname res101 --ft
CUDA_VISIBLE_DEVICES=0,1,2,3 python train.py --dataset Pascal_aug --model-zoo EncNet_Resnet101_COCO --aux --se-loss --lr 0.001 --syncbn --ngpus 4 --checkname res101 --ft
# Finetuning on original set
CUDA_VISIBLE_DEVICES=0,1,2,3 python train_dist.py --dataset Pascal_voc --model encnet --aux --se-loss --backbone resnet101 --lr 0.0001 --syncbn --ngpus 4 --checkname res101 --resume runs/Pascal_aug/encnet/res101/checkpoint.params --ft
CUDA_VISIBLE_DEVICES=0,1,2,3 python train.py --dataset Pascal_voc --model encnet --aux --se-loss --backbone resnet101 --lr 0.0001 --syncbn --ngpus 4 --checkname res101 --resume runs/Pascal_aug/encnet/res101/checkpoint.params --ft
</code>


Expand All @@ -165,9 +170,9 @@ Train Your Own Model

- The training script is in the ``experiments/segmentation/`` folder, example training command::

python train_dist.py --dataset ade20k --model encnet --aux --se-loss
python train.py --dataset ade20k --model encnet --aux --se-loss

- Detail training options, please run ``python train_dist.py -h``. Commands for reproducing pre-trained models can be found in the table.
- Detail training options, please run ``python train.py -h``. Commands for reproducing pre-trained models can be found in the table.

.. hint::
The validation metrics during the training only using center-crop is just for monitoring the
Expand Down
1 change: 1 addition & 0 deletions encoding/models/model_store.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -34,6 +34,7 @@
('4aba491aaf8e4866a9c9981b210e3e3266ac1f2a', 'fcn_resnest50_ade'),
('2225f09d0f40b9a168d9091652194bc35ec2a5a9', 'deeplab_resnest50_ade'),
('06ca799c8cc148fe0fafb5b6d052052935aa3cc8', 'deeplab_resnest101_ade'),
('7b9e7d3e6f0e2c763c7d77cad14d306c0a31fe05', 'deeplab_resnest200_ade'),
('0074dd10a6e6696f6f521653fb98224e75955496', 'deeplab_resnest269_ade'),
]}

Expand Down
1 change: 0 additions & 1 deletion encoding/nn/dropblock.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -123,5 +123,4 @@ def reset_dropblock(start_step, nr_steps, start_value, stop_value, m):
net.apply(apply_drop_prob)
"""
if isinstance(m, DropBlock2D):
print('reseting dropblock')
m.reset_steps(start_step, nr_steps, start_value, stop_value)
Loading

0 comments on commit 3e384b4

Please sign in to comment.