"test/vscode:/vscode.git/clone" did not exist on "1998ce40466577a9563149e1449f997dcd162cee"
Commit 85529f35 authored by unknown's avatar unknown
Browse files

添加openmmlab测试用例

parent b21b0c01
_base_ = './paa_r50_fpn_1x_coco.py'
lr_config = dict(step=[16, 22])
runner = dict(type='EpochBasedRunner', max_epochs=24)
_base_ = './paa_r50_fpn_1x_coco.py'
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=[(1333, 640), (1333, 800)],
multiscale_mode='range',
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']),
]
data = dict(train=dict(pipeline=train_pipeline))
lr_config = dict(step=[28, 34])
runner = dict(type='EpochBasedRunner', max_epochs=36)
# Path Aggregation Network for Instance Segmentation
## Introduction
<!-- [ALGORITHM] -->
```
@inproceedings{liu2018path,
author = {Shu Liu and
Lu Qi and
Haifang Qin and
Jianping Shi and
Jiaya Jia},
title = {Path Aggregation Network for Instance Segmentation},
booktitle = {Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2018}
}
```
## Results and Models
## Results and Models
| Backbone | style | Lr schd | Mem (GB) | Inf time (fps) | box AP | mask AP | Config | Download |
|:-------------:|:----------:|:-------:|:--------:|:--------------:|:------:|:-------:|:------:|:--------:|
| R-50-FPN | pytorch | 1x | 4.0 | 17.2 | 37.5 | | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/pafpn/faster_rcnn_r50_pafpn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/pafpn/faster_rcnn_r50_pafpn_1x_coco/faster_rcnn_r50_pafpn_1x_coco_bbox_mAP-0.375_20200503_105836-b7b4b9bd.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/pafpn/faster_rcnn_r50_pafpn_1x_coco/faster_rcnn_r50_pafpn_1x_coco_20200503_105836.log.json) |
_base_ = '../faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py'
model = dict(
neck=dict(
type='PAFPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5))
Collections:
- Name: PAFPN
Metadata:
Training Data: COCO
Training Techniques:
- SGD with Momentum
- Weight Decay
Training Resources: 8x NVIDIA V100 GPUs
Architecture:
- PAFPN
Paper: https://arxiv.org/abs/1803.01534
README: configs/pafpn/README.md
Models:
- Name: faster_rcnn_r50_pafpn_1x_coco
In Collection: PAFPN
Config: configs/pafpn/faster_rcnn_r50_pafpn_1x_coco.py
Metadata:
Training Memory (GB): 4.0
inference time (s/im): 0.05814
Epochs: 12
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 37.5
Weights: https://download.openmmlab.com/mmdetection/v2.0/pafpn/faster_rcnn_r50_pafpn_1x_coco/faster_rcnn_r50_pafpn_1x_coco_bbox_mAP-0.375_20200503_105836-b7b4b9bd.pth
# PASCAL VOC Dataset
<!-- [DATASET] -->
```
@Article{Everingham10,
author = "Everingham, M. and Van~Gool, L. and Williams, C. K. I. and Winn, J. and Zisserman, A.",
title = "The Pascal Visual Object Classes (VOC) Challenge",
journal = "International Journal of Computer Vision",
volume = "88",
year = "2010",
number = "2",
month = jun,
pages = "303--338",
}
```
## Results and Models
| Architecture | Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | Config | Download |
|:------------:|:---------:|:-------:|:-------:|:--------:|:--------------:|:------:|:------:|:--------:|
| Faster R-CNN | R-50 | pytorch | 1x | 2.6 | - | 79.5 |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/pascal_voc/faster_rcnn_r50_fpn_1x_voc0712.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/pascal_voc/faster_rcnn_r50_fpn_1x_voc0712/faster_rcnn_r50_fpn_1x_voc0712_20200624-c9895d40.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/pascal_voc/faster_rcnn_r50_fpn_1x_voc0712/20200623_015208.log.json) |
| Retinanet | R-50 | pytorch | 1x | 2.1 | - | 77.3 |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/pascal_voc/retinanet_r50_fpn_1x_voc0712.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/pascal_voc/retinanet_r50_fpn_1x_voc0712/retinanet_r50_fpn_1x_voc0712_20200617-47cbdd0e.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/pascal_voc/retinanet_r50_fpn_1x_voc0712/retinanet_r50_fpn_1x_voc0712_20200616_014642.log.json) |
_base_ = [
'../_base_/models/faster_rcnn_r50_fpn.py', '../_base_/datasets/voc0712.py',
'../_base_/default_runtime.py'
]
model = dict(roi_head=dict(bbox_head=dict(num_classes=20)))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
# learning policy
# actual epoch = 3 * 3 = 9
lr_config = dict(policy='step', step=[3])
# runtime settings
runner = dict(
type='EpochBasedRunner', max_epochs=4) # actual epoch = 4 * 3 = 12
_base_ = [
'../_base_/models/faster_rcnn_r50_fpn.py', '../_base_/datasets/voc0712.py',
'../_base_/default_runtime.py'
]
model = dict(roi_head=dict(bbox_head=dict(num_classes=20)))
CLASSES = ('aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus', 'car',
'cat', 'chair', 'cow', 'diningtable', 'dog', 'horse', 'motorbike',
'person', 'pottedplant', 'sheep', 'sofa', 'train', 'tvmonitor')
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/VOCdevkit/'
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=(1000, 600), 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']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1000, 600),
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(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
type='RepeatDataset',
times=3,
dataset=dict(
type=dataset_type,
ann_file='data/voc0712_trainval.json',
img_prefix='data/VOCdevkit',
pipeline=train_pipeline,
classes=CLASSES)),
val=dict(
type=dataset_type,
ann_file='data/voc07_test.json',
img_prefix='data/VOCdevkit',
pipeline=test_pipeline,
classes=CLASSES),
test=dict(
type=dataset_type,
ann_file='data/voc07_test.json',
img_prefix='data/VOCdevkit',
pipeline=test_pipeline,
classes=CLASSES))
evaluation = dict(interval=1, metric='bbox')
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
# learning policy
# actual epoch = 3 * 3 = 9
lr_config = dict(policy='step', step=[3])
# runtime settings
runner = dict(
type='EpochBasedRunner', max_epochs=4) # actual epoch = 4 * 3 = 12
_base_ = [
'../_base_/models/retinanet_r50_fpn.py', '../_base_/datasets/voc0712.py',
'../_base_/default_runtime.py'
]
model = dict(bbox_head=dict(num_classes=20))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
# learning policy
# actual epoch = 3 * 3 = 9
lr_config = dict(policy='step', step=[3])
# runtime settings
runner = dict(
type='EpochBasedRunner', max_epochs=4) # actual epoch = 4 * 3 = 12
_base_ = [
'../_base_/models/ssd300.py', '../_base_/datasets/voc0712.py',
'../_base_/default_runtime.py'
]
model = dict(
bbox_head=dict(
num_classes=20, anchor_generator=dict(basesize_ratio_range=(0.2,
0.9))))
# dataset settings
dataset_type = 'VOCDataset'
data_root = 'data/VOCdevkit/'
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='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(
samples_per_gpu=8,
workers_per_gpu=3,
train=dict(
type='RepeatDataset', times=10, dataset=dict(pipeline=train_pipeline)),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=1e-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=0.001,
step=[16, 20])
checkpoint_config = dict(interval=1)
# runtime settings
runner = dict(type='EpochBasedRunner', max_epochs=24)
_base_ = 'ssd300_voc0712.py'
input_size = 512
model = dict(
backbone=dict(input_size=input_size),
bbox_head=dict(
in_channels=(512, 1024, 512, 256, 256, 256, 256),
anchor_generator=dict(
input_size=input_size,
strides=[8, 16, 32, 64, 128, 256, 512],
basesize_ratio_range=(0.15, 0.9),
ratios=([2], [2, 3], [2, 3], [2, 3], [2, 3], [2], [2]))))
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='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=(512, 512), 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=(512, 512),
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(
train=dict(dataset=dict(pipeline=train_pipeline)),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
# Prime Sample Attention in Object Detection
## Introduction
<!-- [ALGORITHM] -->
```latex
@inproceedings{cao2019prime,
title={Prime sample attention in object detection},
author={Cao, Yuhang and Chen, Kai and Loy, Chen Change and Lin, Dahua},
booktitle={IEEE Conference on Computer Vision and Pattern Recognition},
year={2020}
}
```
## Results and models
| PISA | Network | Backbone | Lr schd | box AP | mask AP | Config | Download |
|:----:|:-------:|:-------------------:|:-------:|:------:|:-------:|:------:|:--------:|
| × | Faster R-CNN | R-50-FPN | 1x | 36.4 | | - |
| √ | Faster R-CNN | R-50-FPN | 1x | 38.4 | | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/pisa/pisa_faster_rcnn_r50_fpn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_faster_rcnn_r50_fpn_1x_coco/pisa_faster_rcnn_r50_fpn_1x_coco-dea93523.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_faster_rcnn_r50_fpn_1x_coco/pisa_faster_rcnn_r50_fpn_1x_coco_20200506_185619.log.json) |
| × | Faster R-CNN | X101-32x4d-FPN | 1x | 40.1 | | - |
| √ | Faster R-CNN | X101-32x4d-FPN | 1x | 41.9 | | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/pisa/pisa_faster_rcnn_x101_32x4d_fpn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_faster_rcnn_x101_32x4d_fpn_1x_coco/pisa_faster_rcnn_x101_32x4d_fpn_1x_coco-e4accec4.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_faster_rcnn_x101_32x4d_fpn_1x_coco/pisa_faster_rcnn_x101_32x4d_fpn_1x_coco_20200505_181503.log.json) |
| × | Mask R-CNN | R-50-FPN | 1x | 37.3 | 34.2 | - |
| √ | Mask R-CNN | R-50-FPN | 1x | 39.1 | 35.2 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/pisa/pisa_mask_rcnn_r50_fpn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_mask_rcnn_r50_fpn_1x_coco/pisa_mask_rcnn_r50_fpn_1x_coco-dfcedba6.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_mask_rcnn_r50_fpn_1x_coco/pisa_mask_rcnn_r50_fpn_1x_coco_20200508_150500.log.json) |
| × | Mask R-CNN | X101-32x4d-FPN | 1x | 41.1 | 37.1 | - |
| √ | Mask R-CNN | X101-32x4d-FPN | 1x | | | |
| × | RetinaNet | R-50-FPN | 1x | 35.6 | | - |
| √ | RetinaNet | R-50-FPN | 1x | 36.9 | | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/pisa/pisa_retinanet_r50_fpn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_retinanet_r50_fpn_1x_coco/pisa_retinanet_r50_fpn_1x_coco-76409952.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_retinanet_r50_fpn_1x_coco/pisa_retinanet_r50_fpn_1x_coco_20200504_014311.log.json) |
| × | RetinaNet | X101-32x4d-FPN | 1x | 39.0 | | - |
| √ | RetinaNet | X101-32x4d-FPN | 1x | 40.7 | | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/pisa/pisa_retinanet_x101_32x4d_fpn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_retinanet_x101_32x4d_fpn_1x_coco/pisa_retinanet_x101_32x4d_fpn_1x_coco-a0c13c73.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_retinanet_x101_32x4d_fpn_1x_coco/pisa_retinanet_x101_32x4d_fpn_1x_coco_20200505_001404.log.json) |
| × | SSD300 | VGG16 | 1x | 25.6 | | - |
| √ | SSD300 | VGG16 | 1x | 27.6 | | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/pisa/pisa_ssd300_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_ssd300_coco/pisa_ssd300_coco-710e3ac9.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_ssd300_coco/pisa_ssd300_coco_20200504_144325.log.json) |
| × | SSD300 | VGG16 | 1x | 29.3 | | - |
| √ | SSD300 | VGG16 | 1x | 31.8 | | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/pisa/pisa_ssd512_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_ssd512_coco/pisa_ssd512_coco-247addee.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_ssd512_coco/pisa_ssd512_coco_20200508_131030.log.json) |
**Notes:**
- In the original paper, all models are trained and tested on mmdet v1.x, thus results may not be exactly the same with this release on v2.0.
- It is noted PISA only modifies the training pipeline so the inference time remains the same with the baseline.
Collections:
- Name: PISA
Metadata:
Training Data: COCO
Training Techniques:
- SGD with Momentum
- Weight Decay
Training Resources: 8x NVIDIA V100 GPUs
Architecture:
- FPN
- PISA
- RPN
- ResNet
- RoIPool
Paper: https://arxiv.org/abs/1904.04821
README: configs/pisa/README.md
Models:
- Name: pisa_faster_rcnn_r50_fpn_1x_coco
In Collection: PISA
Config: configs/pisa/pisa_faster_rcnn_r50_fpn_1x_coco.py
Metadata:
Epochs: 12
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 38.4
Weights: https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_faster_rcnn_r50_fpn_1x_coco/pisa_faster_rcnn_r50_fpn_1x_coco-dea93523.pth
- Name: pisa_faster_rcnn_x101_32x4d_fpn_1x_coco
In Collection: PISA
Config: configs/pisa/pisa_faster_rcnn_x101_32x4d_fpn_1x_coco.py
Metadata:
Epochs: 12
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 41.9
Weights: https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_faster_rcnn_x101_32x4d_fpn_1x_coco/pisa_faster_rcnn_x101_32x4d_fpn_1x_coco-e4accec4.pth
- Name: pisa_mask_rcnn_r50_fpn_1x_coco
In Collection: PISA
Config: configs/pisa/pisa_mask_rcnn_r50_fpn_1x_coco.py
Metadata:
Epochs: 12
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 39.1
- Task: Instance Segmentation
Dataset: COCO
Metrics:
mask AP: 35.2
Weights: https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_mask_rcnn_r50_fpn_1x_coco/pisa_mask_rcnn_r50_fpn_1x_coco-dfcedba6.pth
- Name: pisa_retinanet_r50_fpn_1x_coco
In Collection: PISA
Config: configs/pisa/pisa_retinanet_r50_fpn_1x_coco.py
Metadata:
Epochs: 12
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 36.9
Weights: https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_retinanet_r50_fpn_1x_coco/pisa_retinanet_r50_fpn_1x_coco-76409952.pth
- Name: pisa_retinanet_x101_32x4d_fpn_1x_coco
In Collection: PISA
Config: configs/pisa/pisa_retinanet_x101_32x4d_fpn_1x_coco.py
Metadata:
Epochs: 12
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 40.7
Weights: https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_retinanet_x101_32x4d_fpn_1x_coco/pisa_retinanet_x101_32x4d_fpn_1x_coco-a0c13c73.pth
- Name: pisa_ssd300_coco
In Collection: PISA
Config: configs/pisa/pisa_ssd300_coco.py
Metadata:
Epochs: 24
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 27.6
Weights: https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_ssd300_coco/pisa_ssd300_coco-710e3ac9.pth
- Name: pisa_ssd512_coco
In Collection: PISA
Config: configs/pisa/pisa_ssd512_coco.py
Metadata:
Epochs: 24
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 31.8
Weights: https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_ssd512_coco/pisa_ssd512_coco-247addee.pth
_base_ = '../faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py'
model = dict(
roi_head=dict(
type='PISARoIHead',
bbox_head=dict(
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))),
train_cfg=dict(
rpn_proposal=dict(
nms_pre=2000,
max_per_img=2000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
sampler=dict(
type='ScoreHLRSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True,
k=0.5,
bias=0.),
isr=dict(k=2, bias=0),
carl=dict(k=1, bias=0.2))),
test_cfg=dict(
rpn=dict(
nms_pre=2000,
max_per_img=2000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0)))
_base_ = '../faster_rcnn/faster_rcnn_x101_32x4d_fpn_1x_coco.py'
model = dict(
roi_head=dict(
type='PISARoIHead',
bbox_head=dict(
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))),
train_cfg=dict(
rpn_proposal=dict(
nms_pre=2000,
max_per_img=2000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
sampler=dict(
type='ScoreHLRSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True,
k=0.5,
bias=0.),
isr=dict(k=2, bias=0),
carl=dict(k=1, bias=0.2))),
test_cfg=dict(
rpn=dict(
nms_pre=2000,
max_per_img=2000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0)))
_base_ = '../mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py'
model = dict(
roi_head=dict(
type='PISARoIHead',
bbox_head=dict(
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))),
train_cfg=dict(
rpn_proposal=dict(
nms_pre=2000,
max_per_img=2000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
sampler=dict(
type='ScoreHLRSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True,
k=0.5,
bias=0.),
isr=dict(k=2, bias=0),
carl=dict(k=1, bias=0.2))),
test_cfg=dict(
rpn=dict(
nms_pre=2000,
max_per_img=2000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0)))
_base_ = '../mask_rcnn/mask_rcnn_x101_32x4d_fpn_1x_coco.py'
model = dict(
roi_head=dict(
type='PISARoIHead',
bbox_head=dict(
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))),
train_cfg=dict(
rpn_proposal=dict(
nms_pre=2000,
max_per_img=2000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
sampler=dict(
type='ScoreHLRSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True,
k=0.5,
bias=0.),
isr=dict(k=2, bias=0),
carl=dict(k=1, bias=0.2))),
test_cfg=dict(
rpn=dict(
nms_pre=2000,
max_per_img=2000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0)))
_base_ = '../retinanet/retinanet_r50_fpn_1x_coco.py'
model = dict(
bbox_head=dict(
type='PISARetinaHead',
loss_bbox=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0)),
train_cfg=dict(isr=dict(k=2., bias=0.), carl=dict(k=1., bias=0.2)))
_base_ = '../retinanet/retinanet_x101_32x4d_fpn_1x_coco.py'
model = dict(
bbox_head=dict(
type='PISARetinaHead',
loss_bbox=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0)),
train_cfg=dict(isr=dict(k=2., bias=0.), carl=dict(k=1., bias=0.2)))
_base_ = '../ssd/ssd300_coco.py'
model = dict(
bbox_head=dict(type='PISASSDHead'),
train_cfg=dict(isr=dict(k=2., bias=0.), carl=dict(k=1., bias=0.2)))
optimizer_config = dict(
_delete_=True, grad_clip=dict(max_norm=35, norm_type=2))
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment