Skip to content

Commit

Permalink
Fast-SCNN implemented (#58)
Browse files Browse the repository at this point in the history
* init commit: fast_scnn

* 247917iters

* 4x8_80k

* configs placed in configs_unify.  4x8_80k exp.running.

* mmseg/utils/collect_env.py modified to support Windows

* study on lr

* bug in configs_unify/***/cityscapes.py fixed.

* lr0.08_100k

* lr_power changed to 1.2

* log_config by_epoch set to False.

* lr1.2

* doc strings added

* add fast_scnn backbone  test

* 80k 0.08,0.12

* add 450k

* fast_scnn test: fix BN bug.

* Add different config files into configs/

* .gitignore recovered.

* configs_unify del

* .gitignore recovered.

* delete sub-optimal config files of fast-scnn

* Code style improved.

* add docstrings to component modules of fast-scnn

* relevant files modified according to Jerry's instructions

* relevant files modified according to Jerry's instructions

* lint problems fixed.

* fast_scnn config extremely simplified.

* InvertedResidual

* fixed padding problems

* add unit test for inverted_residual

* add unit test for inverted_residual: debug 0

* add unit test for inverted_residual: debug 1

* add unit test for inverted_residual: debug 2

* add unit test for inverted_residual: debug 3

* add unit test for sep_fcn_head: debug 0

* add unit test for sep_fcn_head: debug 1

* add unit test for sep_fcn_head: debug 2

* add unit test for sep_fcn_head: debug 3

* add unit test for sep_fcn_head: debug 4

* add unit test for sep_fcn_head: debug 5

* FastSCNN type(dwchannels) changed to tuple.

* t changed to expand_ratio.

* Spaces fixed.

* Update mmseg/models/backbones/fast_scnn.py

Co-authored-by: Jerry Jiarui XU <[email protected]>

* Update mmseg/models/decode_heads/sep_fcn_head.py

Co-authored-by: Jerry Jiarui XU <[email protected]>

* Update mmseg/models/decode_heads/sep_fcn_head.py

Co-authored-by: Jerry Jiarui XU <[email protected]>

* Docstrings fixed.

* Docstrings fixed.

* Inverted Residual kept coherent with mmcl.

* Inverted Residual kept coherent with mmcl. Debug 0

* _make_layer parameters renamed.

* final commit

* Arg scale_factor deleted.

* Expand_ratio docstrings updated.

* final commit

* Readme for Fast-SCNN added.

* model-zoo.md modified.

* fast_scnn README updated.

* Move InvertedResidual module into mmseg/utils.

* test_inverted_residual module corrected.

* test_inverted_residual.py moved.

* encoder_decoder modified to avoid bugs when running PSPNet.
getting_started.md bug fixed.

* Revert "encoder_decoder modified to avoid bugs when running PSPNet. "

This reverts commit dd0aadfb

Co-authored-by: Jerry Jiarui XU <[email protected]>
  • Loading branch information
johnzja and xvjiarui authored Aug 18, 2020
1 parent d948406 commit c1f46a6
Show file tree
Hide file tree
Showing 15 changed files with 714 additions and 12 deletions.
58 changes: 58 additions & 0 deletions configs/_base_/models/fast_scnn.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,58 @@
# model settings
norm_cfg = dict(type='SyncBN', requires_grad=True, momentum=0.01)
model = dict(
type='EncoderDecoder',
backbone=dict(
type='FastSCNN',
downsample_dw_channels=(32, 48),
global_in_channels=64,
global_block_channels=(64, 96, 128),
global_block_strides=(2, 2, 1),
global_out_channels=128,
higher_in_channels=64,
lower_in_channels=128,
fusion_out_channels=128,
out_indices=(0, 1, 2),
norm_cfg=norm_cfg,
align_corners=False),
decode_head=dict(
type='DepthwiseSeparableFCNHead',
in_channels=128,
channels=128,
concat_input=False,
num_classes=19,
in_index=-1,
norm_cfg=norm_cfg,
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.)),
auxiliary_head=[
dict(
type='FCNHead',
in_channels=128,
channels=32,
num_convs=1,
num_classes=19,
in_index=-2,
norm_cfg=norm_cfg,
concat_input=False,
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
dict(
type='FCNHead',
in_channels=64,
channels=32,
num_convs=1,
num_classes=19,
in_index=-3,
norm_cfg=norm_cfg,
concat_input=False,
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
])

# model training and testing settings
train_cfg = dict()
test_cfg = dict(mode='whole')
18 changes: 18 additions & 0 deletions configs/fastscnn/README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,18 @@
# Fast-SCNN for Semantic Segmentation

## Introduction
```
@article{poudel2019fast,
title={Fast-scnn: Fast semantic segmentation network},
author={Poudel, Rudra PK and Liwicki, Stephan and Cipolla, Roberto},
journal={arXiv preprint arXiv:1902.04502},
year={2019}
}
```

## Results and models

### Cityscapes
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | download |
|------------|-----------|-----------|--------:|----------|----------------|------:|---------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Fast-SCNN | Fast-SCNN | 512x1024 | 80000 | 8.4 | 63.61 | 69.06 | - | [model](https://openmmlab.oss-cn-hangzhou.aliyuncs.com/mmsegmentation/v0.5/fast_scnn/fast_scnn_4x8_80k_lr0.12_cityscapes-cae6c46a.pth) &#124; [log](https://openmmlab.oss-cn-hangzhou.aliyuncs.com/mmsegmentation/v0.5/fast_scnn/fast_scnn_4x8_80k_lr0.12_cityscapes-20200807_165744.log.json) |
10 changes: 10 additions & 0 deletions configs/fastscnn/fast_scnn_4x8_80k_lr0.12_cityscapes.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,10 @@
_base_ = [
'../_base_/models/fast_scnn.py', '../_base_/datasets/cityscapes.py',
'../_base_/default_runtime.py', '../_base_/schedules/schedule_80k.py'
]

# Re-config the data sampler.
data = dict(samples_per_gpu=8, workers_per_gpu=4)

# Re-config the optimizer.
optimizer = dict(type='SGD', lr=0.12, momentum=0.9, weight_decay=4e-5)
2 changes: 1 addition & 1 deletion docs/getting_started.md
Original file line number Diff line number Diff line change
Expand Up @@ -338,7 +338,7 @@ The final output filename will be `psp_r50_512x1024_40ki_cityscapes-{hash id}.pt
We provide a script to convert model to [ONNX](https://github.com/onnx/onnx) format. The converted model could be visualized by tools like [Netron](https://github.com/lutzroeder/netron). Besides, we also support comparing the output results between Pytorch and ONNX model.
```shell
python tools/pytorch2onnx.py ${CONFIG_FILE} --checkpoint ${CHECKPOINT_FILE} --output_file ${ONNX_FILE} [--shape ${INPUT_SHAPE} --verify]
python tools/pytorch2onnx.py ${CONFIG_FILE} --checkpoint ${CHECKPOINT_FILE} --output-file ${ONNX_FILE} [--shape ${INPUT_SHAPE} --verify]
```
**Note**: This tool is still experimental. Some customized operators are not supported for now.
Expand Down
5 changes: 4 additions & 1 deletion docs/model_zoo.md
Original file line number Diff line number Diff line change
Expand Up @@ -81,11 +81,14 @@ Please refer to [ANN](https://github.com/open-mmlab/mmsegmentation/blob/master/c

Please refer to [OCRNet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/ocrnet) for details.

### Fast-SCNN

Please refer to [Fast-SCNN](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fastscnn) for details.

### ResNeSt

Please refer to [ResNeSt](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/resnest) for details.


### Mixed Precision (FP16) Training

Please refer [Mixed Precision (FP16) Training](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fp16/README.md) for details.
Expand Down
6 changes: 5 additions & 1 deletion mmseg/models/backbones/__init__.py
Original file line number Diff line number Diff line change
@@ -1,6 +1,10 @@
from .fast_scnn import FastSCNN
from .hrnet import HRNet
from .resnest import ResNeSt
from .resnet import ResNet, ResNetV1c, ResNetV1d
from .resnext import ResNeXt

__all__ = ['ResNet', 'ResNetV1c', 'ResNetV1d', 'ResNeXt', 'HRNet', 'ResNeSt']
__all__ = [
'ResNet', 'ResNetV1c', 'ResNetV1d', 'ResNeXt', 'HRNet', 'FastSCNN',
'ResNeSt'
]
Loading

0 comments on commit c1f46a6

Please sign in to comment.