mirrors
/
EasyCV
mirror of https://github.com/alibaba/EasyCV.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

add segformer algo 

. 增加了segformer的b1, b2, b3, b4几个配置文件。
. 预训练模型，log文件等均已经更新
. 已经从master合并结果
        Link: https://code.alibaba-inc.com/pai-vision/EasyCV/codereview/9931529
pull/191/head
pengyu.lpy 2022-08-30 19:15:15 +08:00 committed by jiangnana.jnn
parent 778d0ec43c
commit 2bf3b55655
7 changed files with 59 additions and 206 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
configs/segmentation/segformer/segformer_b0_coco.py
View File

@ -170,7 +170,6 @@ data = dict(
pipeline=train_pipeline),
val=dict(
imgs_per_gpu=1,
workers_per_gpu=1,
ignore_index=255,
type=dataset_type,
data_source=dict(
@ -185,7 +184,6 @@ data = dict(
pipeline=test_pipeline),
test=dict(
imgs_per_gpu=1,
workers_per_gpu=1,
type=dataset_type,
data_source=dict(
type='SegSourceRaw',

8
configs/segmentation/segformer/segformer_b1_coco.py 100644
View File

@ -0,0 +1,8 @@
_base_ = './segformer_b0_coco.py'
model = dict(
pretrained=
'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/segformer/mit_b1_20220624-02e5a6a1.pth',
backbone=dict(embed_dims=64, ),
decode_head=dict(in_channels=[64, 128, 320, 512], ),
)

14
configs/segmentation/segformer/segformer_b2_coco.py 100644
View File

@ -0,0 +1,14 @@
_base_ = './segformer_b0_coco.py'
model = dict(
pretrained=
'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/segformer/mit_b2_20220624-66e8bf70.pth',
backbone=dict(
embed_dims=64,
num_layers=[3, 4, 6, 3],
),
decode_head=dict(
in_channels=[64, 128, 320, 512],
channels=768,
),
)

14
configs/segmentation/segformer/segformer_b3_coco.py 100644
View File

@ -0,0 +1,14 @@
_base_ = './segformer_b0_coco.py'
model = dict(
pretrained=
'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/segformer/mit_b3_20220624-13b1141c.pth',
backbone=dict(
embed_dims=64,
num_layers=[3, 4, 18, 3],
),
decode_head=dict(
in_channels=[64, 128, 320, 512],
channels=768,
),
)

14
configs/segmentation/segformer/segformer_b4_coco.py 100644
View File

@ -0,0 +1,14 @@
_base_ = './segformer_b0_coco.py'
model = dict(
pretrained=
'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/segformer/mit_b4_20220624-d588d980.pth',
backbone=dict(
embed_dims=64,
num_layers=[3, 8, 27, 3],
),
decode_head=dict(
in_channels=[64, 128, 320, 512],
channels=768,
),
)

207
configs/segmentation/segformer/segformer_b5_coco.py
View File

@ -1,119 +1,18 @@
# segformer B5
_base_ = './segformer_b0_coco.py'
CLASSES = [
'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train',
'truck', 'boat', 'traffic light', 'fire hydrant', 'stop sign',
'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag',
'tie', 'suitcase', 'frisbee', 'skis', 'snowboard', 'sports ball', 'kite',
'baseball bat', 'baseball glove', 'skateboard', 'surfboard',
'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon',
'bowl', 'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot',
'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch', 'potted plant',
'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote',
'keyboard', 'cell phone', 'microwave', 'oven', 'toaster', 'sink',
'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear',
'hair drier', 'toothbrush', 'banner', 'blanket', 'branch', 'bridge',
'building-other', 'bush', 'cabinet', 'cage', 'cardboard', 'carpet',
'ceiling-other', 'ceiling-tile', 'cloth', 'clothes', 'clouds', 'counter',
'cupboard', 'curtain', 'desk-stuff', 'dirt', 'door-stuff', 'fence',
'floor-marble', 'floor-other', 'floor-stone', 'floor-tile', 'floor-wood',
'flower', 'fog', 'food-other', 'fruit', 'furniture-other', 'grass',
'gravel', 'ground-other', 'hill', 'house', 'leaves', 'light', 'mat',
'metal', 'mirror-stuff', 'moss', 'mountain', 'mud', 'napkin', 'net',
'paper', 'pavement', 'pillow', 'plant-other', 'plastic', 'platform',
'playingfield', 'railing', 'railroad', 'river', 'road', 'rock', 'roof',
'rug', 'salad', 'sand', 'sea', 'shelf', 'sky-other', 'skyscraper', 'snow',
'solid-other', 'stairs', 'stone', 'straw', 'structural-other', 'table',
'tent', 'textile-other', 'towel', 'tree', 'vegetable', 'wall-brick',
'wall-concrete', 'wall-other', 'wall-panel', 'wall-stone', 'wall-tile',
'wall-wood', 'water-other', 'waterdrops', 'window-blind', 'window-other',
'wood'
]
PALETTE = [[0, 192, 64], [0, 192, 64], [0, 64, 96],
[128, 192, 192], [0, 64, 64], [0, 192, 224], [0, 192, 192],
[128, 192, 64], [0, 192, 96], [128, 192, 64], [128, 32, 192],
[0, 0, 224], [0, 0, 64], [0, 160, 192], [128, 0, 96], [128, 0, 192],
[0, 32, 192], [128, 128, 224], [0, 0, 192], [128, 160, 192],
[128, 128, 0], [128, 0, 32], [128, 32, 0], [128, 0, 128],
[64, 128, 32], [0, 160, 0], [0, 0, 0], [192, 128, 160], [0, 32, 0],
[0, 128, 128], [64, 128, 160], [128, 160, 0], [0, 128, 0],
[192, 128, 32], [128, 96, 128], [0, 0, 128], [64, 0, 32],
[0, 224, 128], [128, 0, 0], [192, 0, 160], [0, 96, 128],
[128, 128, 128], [64, 0, 160], [128, 224, 128], [128, 128,
64], [192, 0, 32],
[128, 96, 0], [128, 0, 192], [0, 128, 32], [64, 224, 0], [0, 0, 64],
[128, 128, 160], [64, 96, 0], [0, 128, 192], [0, 128, 160],
[192, 224, 0], [0, 128, 64], [128, 128, 32], [192, 32, 128],
[0, 64, 192], [0, 0, 32], [64, 160, 128], [128, 64, 64],
[128, 0, 160], [64, 32, 128], [128, 192, 192], [0, 0, 160],
[192, 160, 128], [128, 192, 0], [128, 0, 96], [192, 32, 0],
[128, 64, 128], [64, 128, 96], [64, 160, 0], [0, 64, 0],
[192, 128, 224], [64, 32, 0], [0, 192, 128], [64, 128, 224],
[192, 160, 0], [0, 192, 0], [192, 128, 96], [192, 96, 128],
[0, 64, 128], [64, 0, 96], [64, 224, 128], [128, 64, 0],
[192, 0, 224], [64, 96, 128], [128, 192, 128], [64, 0, 224],
[192, 224, 128], [128, 192, 64], [192, 0, 96], [192, 96, 0],
[128, 64, 192], [0, 128, 96], [0, 224, 0], [64, 64, 64],
[128, 128, 224], [0, 96, 0], [64, 192, 192], [0, 128, 224],
[128, 224, 0], [64, 192, 64], [128, 128, 96], [128, 32, 128],
[64, 0, 192], [0, 64, 96], [0, 160, 128], [192, 0, 64],
[128, 64, 224], [0, 32, 128], [192, 128, 192], [0, 64, 224],
[128, 160, 128], [192, 128, 0], [128, 64, 32], [128, 32, 64],
[192, 0, 128], [64, 192, 32], [0, 160, 64], [64, 0, 0],
[192, 192, 160], [0, 32, 64], [64, 128, 128], [64, 192, 160],
[128, 160, 64], [64, 128, 0], [192, 192, 32], [128, 96, 192],
[64, 0, 128], [64, 64, 32], [0, 224, 192], [192, 0, 0],
[192, 64, 160], [0, 96, 192], [192, 128, 128], [64, 64, 160],
[128, 224, 192], [192, 128, 64], [192, 64, 32], [128, 96, 64],
[192, 0, 192], [0, 192, 32], [64, 224, 64], [64, 0, 64],
[128, 192, 160], [64, 96, 64], [64, 128, 192], [0, 192, 160],
[192, 224, 64], [64, 128, 64], [128, 192, 32], [192, 32, 192],
[64, 64, 192], [0, 64, 32], [64, 160, 192], [192, 64, 64],
[128, 64, 160], [64, 32, 192], [192, 192, 192], [0, 64, 160],
[192, 160, 192], [192, 192, 0], [128, 64, 96], [192, 32, 64],
[192, 64, 128], [64, 192, 96], [64, 160, 64], [64, 64, 0]]
num_classes = 172
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
type='EncoderDecoder',
pretrained=
'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/segformer/mit_b5_20220624-658746d9.pth',
backbone=dict(
type='MixVisionTransformer',
in_channels=3,
embed_dims=64,
num_stages=4,
num_layers=[3, 6, 40, 3],
num_heads=[1, 2, 5, 8],
patch_sizes=[7, 3, 3, 3],
sr_ratios=[8, 4, 2, 1],
out_indices=(0, 1, 2, 3),
mlp_ratio=4,
qkv_bias=True,
drop_rate=0.0,
attn_drop_rate=0.0,
drop_path_rate=0.1),
),
decode_head=dict(
type='SegformerHead',
in_channels=[64, 128, 320, 512],
in_index=[0, 1, 2, 3],
channels=768,
dropout_ratio=0.1,
num_classes=num_classes,
norm_cfg=norm_cfg,
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
# model training and testing settings
train_cfg=dict(),
test_cfg=dict(mode='whole'))
),
)
# dataset settings
dataset_type = 'SegDataset'
data_root = 'data/coco_stuff164k/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
crop_size = (640, 640)
@ -151,101 +50,3 @@ test_pipeline = [
'flip_direction', 'img_norm_cfg')),
])
]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ignore_index=255,
data_source=dict(
type='SegSourceRaw',
img_suffix='.jpg',
label_suffix='_labelTrainIds.png',
img_root=data_root + 'train2017/',
label_root=data_root + 'annotations/train2017/',
split=data_root + 'train.txt',
classes=CLASSES,
),
pipeline=train_pipeline),
val=dict(
imgs_per_gpu=1,
workers_per_gpu=1,
ignore_index=255,
type=dataset_type,
data_source=dict(
type='SegSourceRaw',
img_suffix='.jpg',
label_suffix='_labelTrainIds.png',
img_root=data_root + 'val2017/',
label_root=data_root + 'annotations/val2017',
split=data_root + 'val.txt',
classes=CLASSES,
),
pipeline=test_pipeline),
test=dict(
imgs_per_gpu=1,
workers_per_gpu=1,
type=dataset_type,
data_source=dict(
type='SegSourceRaw',
img_suffix='.jpg',
label_suffix='_labelTrainIds.png',
img_root=data_root + 'val2017/',
label_root=data_root + 'annotations/val2017',
split=data_root + 'val.txt',
classes=CLASSES,
),
pipeline=test_pipeline))
optimizer = dict(
type='AdamW',
lr=6e-05,
betas=(0.9, 0.999),
weight_decay=0.01,
paramwise_options=dict(
custom_keys=dict(
pos_block=dict(decay_mult=0.0),
norm=dict(decay_mult=0.0),
head=dict(lr_mult=10.0))))
optimizer_config = dict()
lr_config = dict(
policy='poly',
warmup='linear',
warmup_iters=800,
warmup_ratio=1e-06,
power=1.0,
min_lr=0.0,
by_epoch=False)
# runtime settings
total_epochs = 20
checkpoint_config = dict(interval=1)
eval_config = dict(interval=1, gpu_collect=False)
eval_pipelines = [
dict(
mode='test',
evaluators=[
dict(
type='SegmentationEvaluator',
classes=CLASSES,
metric_names=['mIoU'])
],
)
]
predict = dict(type='SegmentationPredictor')
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
dist_params = dict(backend='nccl')
cudnn_benchmark = False
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]

6
docs/source/model_zoo_seg.md
View File

@ -36,4 +36,8 @@ Semantic segmentation models trained on **CoCo_stuff164k**.
| Algorithm | Config | Params<br/>(backbone/total) | inference time(V100)<br/>(ms/img) |mIoU | Download |
| ---------- | ------------------------------------------------------------ | ------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ |
| SegFormer_B0 | [segformer_b0_coco.py](https://github.com/alibaba/EasyCV/tree/master/configs/segmentation/segformer/segformer_b0_coco.py) | 3.3M/3.8M | 47.2ms | 34.79 | [model](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/damo/modelzoo/segmentation/segformer/segformer_b0/SegmentationEvaluator_mIoU_best.pth) - [log](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/damo/modelzoo/segmentation/segformer/segformer_b0/20220810_102335.log.json) |
| SegFormer_B5 | [segformer_b5_coco.py](https://github.com/alibaba/EasyCV/tree/master/configs/segmentation/segformer/segformer_b5_coco.py) | 81M/85M | 99.2ms | 46.75 | [model](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/damo/modelzoo/segmentation/segformer/segformer_b5/SegmentationEvaluator_mIoU_best.pth) - [log](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/damo/modelzoo/segmentation/segformer/segformer_b5/20220812_144336.log.json) |
| SegFormer_B1 | [segformer_b1_coco.py](https://github.com/alibaba/EasyCV/tree/master/configs/segmentation/segformer/segformer_b1_coco.py) | 13.2M/13.7M | 46.8ms | 39.27 | [model](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/damo/modelzoo/segmentation/segformer/segformer_b1/SegmentationEvaluator_mIoU_best.pth) - [log](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/damo/modelzoo/segmentation/segformer/segformer_b1/20220819_142214.log.json) |
| SegFormer_B2 | [segformer_b2_coco.py](https://github.com/alibaba/EasyCV/tree/master/configs/segmentation/segformer/segformer_b2_coco.py) | 24.2M/27.5M | 49.1ms | 44.01 | [model](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/damo/modelzoo/segmentation/segformer/segformer_b2/SegmentationEvaluator_mIoU_best.pth) - [log](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/damo/modelzoo/segmentation/segformer/segformer_b2/20220822_100513.log.json) |
| SegFormer_B3 | [segformer_b3_coco.py](https://github.com/alibaba/EasyCV/tree/master/configs/segmentation/segformer/segformer_b3_coco.py) | 44.1M/47.4M | 52.3ms | 45.31 | [model](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/damo/modelzoo/segmentation/segformer/segformer_b3/SegmentationEvaluator_mIoU_best.pth) - [log](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/damo/modelzoo/segmentation/segformer/segformer_b3/20220823_100744.log.json) |
| SegFormer_B4 | [segformer_b4_coco.py](https://github.com/alibaba/EasyCV/tree/master/configs/segmentation/segformer/segformer_b4_coco.py) | 60.8M/64.1M | 58.5ms | 46.00 | [model](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/damo/modelzoo/segmentation/segformer/segformer_b4/SegmentationEvaluator_mIoU_best.pth) - [log](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/damo/modelzoo/segmentation/segformer/segformer_b4/20220824_102735.log.json) |
| SegFormer_B5 | [segformer_b5_coco.py](https://github.com/alibaba/EasyCV/tree/master/configs/segmentation/segformer/segformer_b5_coco.py) | 81.4M/85.7M | 99.2ms | 46.75 | [model](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/damo/modelzoo/segmentation/segformer/segformer_b5/SegmentationEvaluator_mIoU_best.pth) - [log](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/damo/modelzoo/segmentation/segformer/segformer_b5/20220812_144336.log.json) |