Skip to content
Snippets Groups Projects

Compare revisions

Changes are shown as if the source revision was being merged into the target revision. Learn more about comparing revisions.

Source

Select target project
No results found

Target

Select target project
  • Archana_Badagi/food-round2
  • eric_a_scuccimarra/food-round2
  • joel_joseph/food-round2
  • darthgera123/food-round2
  • reshmarameshbabu/food-round2
  • nikhil_rayaprolu/food-round2
6 results
Show changes
Hide whitespace changes
Inline Side-by-side
Showing
with 1500 additions and 16 deletions
configs/dcn/mask_rcnn_mdconv_c3-c5_r50_fpn_1x.py 0 → 100644
View file @ 49243848
# model settings
model = dict(
type='MaskRCNN',
pretrained='torchvision://resnet50',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch',
dcn=dict(type='DCNv2', deformable_groups=1, fallback_on_stride=False),
stage_with_dcn=(False, True, True, True)),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_scales=[8],
anchor_ratios=[0.5, 1.0, 2.0],
anchor_strides=[4, 8, 16, 32, 64],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0],
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='SharedFCBBoxHead',
num_fcs=2,
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=81,
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=False,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
mask_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
mask_head=dict(
type='FCNMaskHead',
num_convs=4,
in_channels=256,
conv_out_channels=256,
num_classes=81,
loss_mask=dict(
type='CrossEntropyLoss', use_mask=True, loss_weight=1.0)))
# model training and testing settings
train_cfg = dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=0,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_across_levels=False,
nms_pre=2000,
nms_post=2000,
max_num=2000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False))
test_cfg = dict(
rpn=dict(
nms_across_levels=False,
nms_pre=1000,
nms_post=1000,
max_num=1000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100,
mask_thr_binary=0.5))
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[8, 11])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 12
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/mask_rcnn_dconv_c3-c5_r50_fpn_1x'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/empirical_attention/faster_rcnn_r50_fpn_attention_0010_dcn_1x.py
View file @ 49243848
......@@ -12,8 +12,7 @@ model = dict(
gen_attention=dict(
spatial_range=-1, num_heads=8, attention_type='0010', kv_stride=2),
stage_with_gen_attention=[[], [], [0, 1, 2, 3, 4, 5], [0, 1, 2]],
dcn=dict(
modulated=False, deformable_groups=1, fallback_on_stride=False),
dcn=dict(type='DCN', deformable_groups=1, fallback_on_stride=False),
stage_with_dcn=(False, True, True, True),
),
neck=dict(
......
configs/empirical_attention/faster_rcnn_r50_fpn_attention_1111_dcn_1x.py
View file @ 49243848
......@@ -12,8 +12,7 @@ model = dict(
gen_attention=dict(
spatial_range=-1, num_heads=8, attention_type='1111', kv_stride=2),
stage_with_gen_attention=[[], [], [0, 1, 2, 3, 4, 5], [0, 1, 2]],
dcn=dict(
modulated=False, deformable_groups=1, fallback_on_stride=False),
dcn=dict(type='DCN', deformable_groups=1, fallback_on_stride=False),
stage_with_dcn=(False, True, True, True),
),
neck=dict(
......
configs/free_anchor/README.md
View file @ 49243848
......@@ -21,3 +21,4 @@
**Notes:**
- We use 8 GPUs with 2 images/GPU.
- For more settings and models, please refer to the [official repo](https://github.com/zhangxiaosong18/FreeAnchor).
configs/hrnet/htc_hrnetv2p_w32_20e.py
View file @ 49243848
......@@ -221,7 +221,7 @@ train_pipeline = [
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='SegResizeFlipPadRescale', scale_factor=1 / 8),
dict(type='SegRescale', scale_factor=1 / 8),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
......
configs/htc/htc_dconv_c3-c5_mstrain_400_1400_x101_64x4d_fpn_20e.py
View file @ 49243848
......@@ -15,7 +15,7 @@ model = dict(
frozen_stages=1,
style='pytorch',
dcn=dict(
modulated=False,
type='DCN',
groups=64,
deformable_groups=1,
fallback_on_stride=False),
......@@ -217,7 +217,7 @@ train_pipeline = [
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='SegResizeFlipPadRescale', scale_factor=1 / 8),
dict(type='SegRescale', scale_factor=1 / 8),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
......
configs/htc/htc_r101_fpn_20e.py
View file @ 49243848
......@@ -205,7 +205,7 @@ train_pipeline = [
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='SegResizeFlipPadRescale', scale_factor=1 / 8),
dict(type='SegRescale', scale_factor=1 / 8),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
......
configs/htc/htc_r50_fpn_1x.py
View file @ 49243848
......@@ -205,7 +205,7 @@ train_pipeline = [
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='SegResizeFlipPadRescale', scale_factor=1 / 8),
dict(type='SegRescale', scale_factor=1 / 8),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
......
configs/htc/htc_r50_fpn_20e.py
View file @ 49243848
......@@ -205,7 +205,7 @@ train_pipeline = [
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='SegResizeFlipPadRescale', scale_factor=1 / 8),
dict(type='SegRescale', scale_factor=1 / 8),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
......
configs/htc/htc_x101_32x4d_fpn_20e_16gpu.py
View file @ 49243848
......@@ -207,7 +207,7 @@ train_pipeline = [
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='SegResizeFlipPadRescale', scale_factor=1 / 8),
dict(type='SegRescale', scale_factor=1 / 8),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
......
configs/htc/htc_x101_64x4d_fpn_20e_16gpu.py
View file @ 49243848
......@@ -207,7 +207,7 @@ train_pipeline = [
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='SegResizeFlipPadRescale', scale_factor=1 / 8),
dict(type='SegRescale', scale_factor=1 / 8),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
......
configs/htc_r50.py 0 → 100644
View file @ 49243848
# model settings
model = dict(
type='HybridTaskCascade',
num_stages=3,
pretrained='torchvision://resnet50',
interleaved=True,
mask_info_flow=True,
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch'),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_scales=[8],
anchor_ratios=[0.5, 1.0, 2.0],
anchor_strides=[4, 8, 16, 32, 64],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0],
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=[
dict(
type='SharedFCBBoxHead',
num_fcs=2,
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=62,
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=True,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=62,
target_means=[0., 0., 0., 0.],
target_stds=[0.05, 0.05, 0.1, 0.1],
reg_class_agnostic=True,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=62,
target_means=[0., 0., 0., 0.],
target_stds=[0.033, 0.033, 0.067, 0.067],
reg_class_agnostic=True,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
],
mask_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
mask_head=dict(
type='HTCMaskHead',
num_convs=4,
in_channels=256,
conv_out_channels=256,
num_classes=62,
loss_mask=dict(
type='CrossEntropyLoss', use_mask=True, loss_weight=1.0)),
)
# model training and testing settings
train_cfg = dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=0,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_across_levels=False,
nms_pre=2000,
nms_post=2000,
max_num=2000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=[
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False),
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.6,
neg_iou_thr=0.6,
min_pos_iou=0.6,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False),
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.7,
min_pos_iou=0.7,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False)
],
stage_loss_weights=[1, 0.5, 0.25])
test_cfg = dict(
rpn=dict(
nms_across_levels=False,
nms_pre=1000,
nms_post=1000,
max_num=1000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
score_thr=0.001,
nms=dict(type='soft_nms', iou_thr=0.3),
max_per_img=10,
mask_thr_binary=0.5),
keep_all_stages=False)
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
albu_train_transforms = [
dict(
type='ShiftScaleRotate',
shift_limit=0.0625,
scale_limit=0.0,
rotate_limit=0,
interpolation=1,
p=0.5),
dict(
type='RandomBrightnessContrast',
brightness_limit=[0.1, 0.3],
contrast_limit=[0.1, 0.3],
p=0.2),
dict(
type='OneOf',
transforms=[
dict(
type='RGBShift',
r_shift_limit=10,
g_shift_limit=10,
b_shift_limit=10,
p=1.0),
dict(
type='HueSaturationValue',
hue_shift_limit=20,
sat_shift_limit=30,
val_shift_limit=20,
p=1.0)
],
p=0.1),
dict(type='JpegCompression', quality_lower=85, quality_upper=95, p=0.2),
dict(type='ChannelShuffle', p=0.1),
dict(
type='OneOf',
transforms=[
dict(type='Blur', blur_limit=3, p=1.0),
dict(type='MedianBlur', blur_limit=3, p=1.0)
],
p=0.1),
]
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='LoadAnnotations', with_bbox=True, with_mask=True),
dict(type='Resize', img_scale=(800, 800), keep_ratio=True),
dict(type='Pad', size_divisor=32),
dict(
type='Albu',
transforms=albu_train_transforms,
bbox_params=dict(
type='BboxParams',
format='pascal_voc',
label_fields=['gt_labels'],
min_visibility=0.0,
filter_lost_elements=True),
keymap={
'img': 'image',
'gt_masks': 'masks',
'gt_bboxes': 'bboxes'
},
update_pad_shape=False,
skip_img_without_anno=True),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks'],
meta_keys=('filename', 'ori_shape', 'img_shape', 'img_norm_cfg',
'pad_shape', 'scale_factor'))
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(800, 800),
flip=True,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
imgs_per_gpu=4,
workers_per_gpu=8,
train=dict(
type=dataset_type,
ann_file=data_root + 'train/annotations.json',
img_prefix=data_root + 'train/images',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'val/annotations.json',
img_prefix=data_root + 'val/images',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'val/annotations.json',
img_prefix=data_root + 'val/images',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[17, 24])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 30
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/htc_r50_fpn'
load_from = 'htc_r50_fpn_20e_20190408-c03b7015.pth'
resume_from = None
workflow = [('train', 1)]
configs/instaboost/README.md 0 → 100644
View file @ 49243848
# InstaBoost for MMDetection
Configs in this directory is the implementation for ICCV2019 paper "InstaBoost: Boosting Instance Segmentation Via Probability Map Guided Copy-Pasting" and provided by the authors of the paper. InstaBoost is a data augmentation method for object detection and instance segmentation. The paper has been released on [`arXiv`](https://arxiv.org/abs/1908.07801).
```
@inproceedings{fang2019instaboost,
title={Instaboost: Boosting instance segmentation via probability map guided copy-pasting},
author={Fang, Hao-Shu and Sun, Jianhua and Wang, Runzhong and Gou, Minghao and Li, Yong-Lu and Lu, Cewu},
booktitle={Proceedings of the IEEE International Conference on Computer Vision},
pages={682--691},
year={2019}
}
```
## Usage
### Requirements
You need to install `instaboostfast` before using it.
```
pip install instaboostfast
```
The code and more details can be found [here](https://github.com/GothicAi/Instaboost).
### Integration with MMDetection
InstaBoost have been already integrated in the data pipeline, thus all you need is to add or change **InstaBoost** configurations after **LoadImageFromFile**. We have provided examples like [this](mask_rcnn_r50_fpn_instaboost_4x.py#L121). You can refer to [`InstaBoostConfig`](https://github.com/GothicAi/InstaBoost-pypi#instaboostconfig) for more details.
## Results and Models
- All models were trained on `coco_2017_train` and tested on `coco_2017_val` for conveinience of evaluation and comparison. In the paper, the results are obtained from `test-dev`.
- To balance accuracy and training time when using InstaBoost, models released in this page are all trained for 48 Epochs. Other training and testing configs strictly follow the original framework.
- The results and models are provided by the [authors](https://github.com/GothicAi/Instaboost) (many thanks).
| InstaBoost | Network | Backbone | Lr schd | box AP | mask AP | Download |
| :-------------: | :-------------: | :--------: | :-----: | :----: | :-----: | :-----------------: |
| × | Mask R-CNN | R-50-FPN | 1x | 37.3 | 34.2 | - |
| √ | Mask R-CNN | R-50-FPN | 4x |**40.0**|**36.2** |[Baidu](https://pan.baidu.com/s/1PLn1K5qreDoM4wh7nbsLqA) / [Google](https://drive.google.com/file/d/1uUT1qc3oYS8xHLyM7bJWgxBNbW-9sa1f/view?usp=sharing)|
| × | Mask R-CNN | R-101-FPN | 1x | 39.4 | 35.9 | - |
| √ | Mask R-CNN | R-101-FPN | 4x |**42.1**|**37.8** |[Baidu](https://pan.baidu.com/s/1IZpqCDrcrOiwNJ-Y_3wpOQ) / [Google](https://drive.google.com/file/d/1idGMPexovIDUHXSNlpIA1mjKzgnFrcW3/view?usp=sharing)|
| × | Mask R-CNN | X-101-64x4d-FPN | 1x | 42.1 | 38.0 | - |
| × | Mask R-CNN | X-101-64x4d-FPN | 2x | *42.0* | *37.7* | - |
| √ | Mask R-CNN | X-101-64x4d-FPN | 4x |**44.5**|**39.5** |[Baidu](https://pan.baidu.com/s/1KrHQBHcHjWONpXbC2qUzxw) / [Google](https://drive.google.com/file/d/1qD4V9uYbtpaZBmTMTgP7f0uw46zroY9-/view?usp=sharing)|
| × | Cascade R-CNN | R-101-FPN | 1x | 42.6 | 37.0 | - |
| √ | Cascade R-CNN | R-101-FPN | 4x |**45.4**|**39.2** |[Baidu](https://pan.baidu.com/s/1_4cJ0B9fugcA-oBHYe9o_A) / [Google](https://drive.google.com/file/d/1xhiuFoOMQyDIvOrz6MiAZPboRRe1YK8p/view?usp=sharing)|
| × | Cascade R-CNN | X-101-64x4d-FPN | 1x | 45.4 | 39.1 | - |
| √ | Cascade R-CNN | X-101-64x4d-FPN | 4x |**47.2**|**40.4** |[Baidu](https://pan.baidu.com/s/1nu73IpRbTEb4caPMHWJMXA) / [Google](https://drive.google.com/file/d/11iaKH-ZeVCi-65wzlT5OxxUOkREMzXRW/view?usp=sharing)|
| × | SSD | VGG16-512 | 120e | 29.3 | - | - |
| √ | SSD | VGG16-512 | 360e |**30.3**| - |[Baidu](https://pan.baidu.com/s/1G-1atZ81A8mLLx8taJAuwQ) / [Google](https://drive.google.com/file/d/1sqMIEusZw2Y7Ge8DuJgmhSP-2V74BNKy/view?usp=sharing)|
configs/instaboost/cascade_mask_rcnn_r50_fpn_instaboost_4x.py 0 → 100644
View file @ 49243848
# model settings
model = dict(
type='CascadeRCNN',
num_stages=3,
pretrained='torchvision://resnet50',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch'),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_scales=[8],
anchor_ratios=[0.5, 1.0, 2.0],
anchor_strides=[4, 8, 16, 32, 64],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0],
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=[
dict(
type='SharedFCBBoxHead',
num_fcs=2,
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=81,
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=True,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=81,
target_means=[0., 0., 0., 0.],
target_stds=[0.05, 0.05, 0.1, 0.1],
reg_class_agnostic=True,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=81,
target_means=[0., 0., 0., 0.],
target_stds=[0.033, 0.033, 0.067, 0.067],
reg_class_agnostic=True,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
],
mask_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
mask_head=dict(
type='FCNMaskHead',
num_convs=4,
in_channels=256,
conv_out_channels=256,
num_classes=81,
loss_mask=dict(
type='CrossEntropyLoss', use_mask=True, loss_weight=1.0)))
# model training and testing settings
train_cfg = dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=0,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_across_levels=False,
nms_pre=2000,
nms_post=2000,
max_num=2000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=[
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False),
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.6,
neg_iou_thr=0.6,
min_pos_iou=0.6,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False),
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.7,
min_pos_iou=0.7,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False)
],
stage_loss_weights=[1, 0.5, 0.25])
test_cfg = dict(
rpn=dict(
nms_across_levels=False,
nms_pre=1000,
nms_post=1000,
max_num=1000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100,
mask_thr_binary=0.5))
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='InstaBoost',
action_candidate=('normal', 'horizontal', 'skip'),
action_prob=(1, 0, 0),
scale=(0.8, 1.2),
dx=15,
dy=15,
theta=(-1, 1),
color_prob=0.5,
hflag=False,
aug_ratio=0.5),
dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[32, 44])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 48
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/cascade_mask_rcnn_r50_fpn_instaboost_4x'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/instaboost/mask_rcnn_r50_fpn_instaboost_4x.py 0 → 100644
View file @ 49243848
# model settings
model = dict(
type='MaskRCNN',
pretrained='torchvision://resnet50',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch'),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_scales=[8],
anchor_ratios=[0.5, 1.0, 2.0],
anchor_strides=[4, 8, 16, 32, 64],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0],
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='SharedFCBBoxHead',
num_fcs=2,
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=81,
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=False,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
mask_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
mask_head=dict(
type='FCNMaskHead',
num_convs=4,
in_channels=256,
conv_out_channels=256,
num_classes=81,
loss_mask=dict(
type='CrossEntropyLoss', use_mask=True, loss_weight=1.0)))
# model training and testing settings
train_cfg = dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=0,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_across_levels=False,
nms_pre=2000,
nms_post=2000,
max_num=2000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False))
test_cfg = dict(
rpn=dict(
nms_across_levels=False,
nms_pre=1000,
nms_post=1000,
max_num=1000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100,
mask_thr_binary=0.5))
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='InstaBoost',
action_candidate=('normal', 'horizontal', 'skip'),
action_prob=(1, 0, 0),
scale=(0.8, 1.2),
dx=15,
dy=15,
theta=(-1, 1),
color_prob=0.5,
hflag=False,
aug_ratio=0.5),
dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[32, 44])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
evaluation = dict(interval=1)
# runtime settings
total_epochs = 48
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/mask_rcnn_r50_fpn_instaboost_4x'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/instaboost/ssd300_coco_instaboost_4x.py 0 → 100644
View file @ 49243848
# model settings
input_size = 300
model = dict(
type='SingleStageDetector',
pretrained='open-mmlab://vgg16_caffe',
backbone=dict(
type='SSDVGG',
input_size=input_size,
depth=16,
with_last_pool=False,
ceil_mode=True,
out_indices=(3, 4),
out_feature_indices=(22, 34),
l2_norm_scale=20),
neck=None,
bbox_head=dict(
type='SSDHead',
input_size=input_size,
in_channels=(512, 1024, 512, 256, 256, 256),
num_classes=81,
anchor_strides=(8, 16, 32, 64, 100, 300),
basesize_ratio_range=(0.15, 0.9),
anchor_ratios=([2], [2, 3], [2, 3], [2, 3], [2], [2]),
target_means=(.0, .0, .0, .0),
target_stds=(0.1, 0.1, 0.2, 0.2)))
cudnn_benchmark = True
train_cfg = dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.,
ignore_iof_thr=-1,
gt_max_assign_all=False),
smoothl1_beta=1.,
allowed_border=-1,
pos_weight=-1,
neg_pos_ratio=3,
debug=False)
test_cfg = dict(
nms=dict(type='nms', iou_thr=0.45),
min_bbox_size=0,
score_thr=0.02,
max_per_img=200)
# model training and testing settings
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(mean=[123.675, 116.28, 103.53], std=[1, 1, 1], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile', to_float32=True),
dict(
type='InstaBoost',
action_candidate=('normal', 'horizontal', 'skip'),
action_prob=(1, 0, 0),
scale=(0.8, 1.2),
dx=15,
dy=15,
theta=(-1, 1),
color_prob=0.5,
hflag=False,
aug_ratio=0.5),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='PhotoMetricDistortion',
brightness_delta=32,
contrast_range=(0.5, 1.5),
saturation_range=(0.5, 1.5),
hue_delta=18),
dict(
type='Expand',
mean=img_norm_cfg['mean'],
to_rgb=img_norm_cfg['to_rgb'],
ratio_range=(1, 4)),
dict(
type='MinIoURandomCrop',
min_ious=(0.1, 0.3, 0.5, 0.7, 0.9),
min_crop_size=0.3),
dict(type='Resize', img_scale=(300, 300), keep_ratio=False),
dict(type='Normalize', **img_norm_cfg),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(300, 300),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=False),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
imgs_per_gpu=8,
workers_per_gpu=3,
train=dict(
type='RepeatDataset',
times=5,
dataset=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline)),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=2e-3, momentum=0.9, weight_decay=5e-4)
optimizer_config = dict()
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[64, 88])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 96
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/ssd300_coco_instaboost_4x'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/libra_rcnn/libra_retinanet_r50_fpn_1x.py
View file @ 49243848
......@@ -15,7 +15,6 @@ model = dict(
in_channels=[256, 512, 1024, 2048],
out_channels=256,
start_level=1,
extra_convs_on_inputs=True,
add_extra_convs=True,
num_outs=5),
dict(
......@@ -57,9 +56,6 @@ train_cfg = dict(
neg_iou_thr=0.4,
min_pos_iou=0,
ignore_iof_thr=-1),
smoothl1_beta=0.11,
gamma=2.0,
alpha=0.25,
allowed_border=-1,
pos_weight=-1,
debug=False)
......
configs/nas_fpn/README.md 0 → 100644
View file @ 49243848
# NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection
## Introduction
```
@inproceedings{ghiasi2019fpn,
title={Nas-fpn: Learning scalable feature pyramid architecture for object detection},
author={Ghiasi, Golnaz and Lin, Tsung-Yi and Le, Quoc V},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
pages={7036--7045},
year={2019}
}
```
## Results and Models
We benchmark the new training schedule (crop training, large batch, unfrozen BN, 50 epochs) introduced in NAS-FPN. RetinaNet is used in the paper.
| Backbone | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | box AP | Download |
|:-----------:|:-------:|:--------:|:-------------------:|:--------------:|:------:|:--------:|
| R-50-FPN | 50e | 12.8 | 0.513 | 15.3 | 37.0 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/nas_fpn/retinanet_crop640_r50_fpn_50e_190824-4d75bfa0.pth) |
| R-50-NASFPN | 50e | 14.8 | 0.662 | 13.1 | 39.8 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/nas_fpn/retinanet_crop640_r50_nasfpn_50e_20191225-b82d3a86.pth) |
**Note**: We find that it is unstable to train NAS-FPN and there is a small chance that results can be 3% mAP lower.
configs/nas_fpn/retinanet_crop640_r50_fpn_50e.py 0 → 100644
View file @ 49243848
cudnn_benchmark = True
# model settings
norm_cfg = dict(type='BN', requires_grad=True)
model = dict(
type='RetinaNet',
pretrained='torchvision://resnet50',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=norm_cfg,
norm_eval=False,
style='pytorch'),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
start_level=1,
add_extra_convs=True,
relu_before_extra_convs=True,
no_norm_on_lateral=True,
norm_cfg=norm_cfg,
num_outs=5),
bbox_head=dict(
type='RetinaSepBNHead',
num_classes=81,
num_ins=5,
in_channels=256,
stacked_convs=4,
feat_channels=256,
octave_base_scale=4,
scales_per_octave=3,
anchor_ratios=[0.5, 1.0, 2.0],
anchor_strides=[8, 16, 32, 64, 128],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0],
norm_cfg=norm_cfg,
loss_cls=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0)))
# training and testing settings
train_cfg = dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0,
ignore_iof_thr=-1),
allowed_border=-1,
pos_weight=-1,
debug=False)
test_cfg = dict(
nms_pre=1000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100)
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='Resize',
img_scale=(640, 640),
ratio_range=(0.8, 1.2),
keep_ratio=True),
dict(type='RandomCrop', crop_size=(640, 640)),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size=(640, 640)),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(640, 640),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=64),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
imgs_per_gpu=8,
workers_per_gpu=4,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(
type='SGD',
lr=0.08,
momentum=0.9,
weight_decay=0.0001,
paramwise_options=dict(norm_decay_mult=0))
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=1000,
warmup_ratio=0.1,
step=[30, 40])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 50
device_ids = range(8)
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/retinanet_crop640_r50_fpn_50e'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/nas_fpn/retinanet_crop640_r50_nasfpn_50e.py 0 → 100644
View file @ 49243848
cudnn_benchmark = True
# model settings
norm_cfg = dict(type='BN', requires_grad=True)
model = dict(
type='RetinaNet',
pretrained='torchvision://resnet50',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=norm_cfg,
norm_eval=False,
style='pytorch'),
neck=dict(
type='NASFPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5,
stack_times=7,
start_level=1,
add_extra_convs=True,
norm_cfg=norm_cfg),
bbox_head=dict(
type='RetinaSepBNHead',
num_classes=81,
num_ins=5,
in_channels=256,
stacked_convs=4,
feat_channels=256,
octave_base_scale=4,
scales_per_octave=3,
anchor_ratios=[0.5, 1.0, 2.0],
anchor_strides=[8, 16, 32, 64, 128],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0],
norm_cfg=norm_cfg,
loss_cls=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0)))
# training and testing settings
train_cfg = dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0,
ignore_iof_thr=-1),
allowed_border=-1,
pos_weight=-1,
debug=False)
test_cfg = dict(
nms_pre=1000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100)
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='Resize',
img_scale=(640, 640),
ratio_range=(0.8, 1.2),
keep_ratio=True),
dict(type='RandomCrop', crop_size=(640, 640)),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size=(640, 640)),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(640, 640),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=128),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
imgs_per_gpu=8,
workers_per_gpu=4,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(
type='SGD',
lr=0.08,
momentum=0.9,
weight_decay=0.0001,
paramwise_options=dict(norm_decay_mult=0))
optimizer_config = dict(grad_clip=None)
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=1000,
warmup_ratio=0.1,
step=[30, 40])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 50
device_ids = range(8)
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/retinanet_crop640_r50_nasfpn_50e'
load_from = None
resume_from = None
workflow = [('train', 1)]