Skip to content

Commit

Permalink
Add files
Browse files Browse the repository at this point in the history
  • Loading branch information
@hysts
hysts committed Oct 19, 2021
1 parent 31c19f8 commit 285675b
Show file tree
Hide file tree
Showing 9 changed files with 563 additions and 0 deletions.
4 changes: 4 additions & 0 deletions MANIFEST.in
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
include LICENSE
include README.md
include requirements.txt
recursive-include configs *.py
3 changes: 3 additions & 0 deletions README.md
View file
Original file line number Diff line number Diff line change
@@ -1,2 +1,5 @@
# Anime Face Detector

This is an anime face detector using
[mmdetection](https://github.com/open-mmlab/mmdetection)
and [mmpose](https://github.com/open-mmlab/mmpose).
14 changes: 14 additions & 0 deletions anime_face_detector/__init__.py
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,14 @@
import pathlib

from .detector import LandmarkDetector


def get_config_path(model_name: str) -> pathlib.Path:
assert model_name in ['faster-rcnn', 'yolov3', 'hrnetv2']

package_path = pathlib.Path(__file__).parent.resolve()
if model_name in ['faster-rcnn', 'yolov3']:
config_dir = package_path / 'configs' / 'mmdet'
else:
config_dir = package_path / 'configs' / 'mmpose'
return config_dir / f'{model_name}.py'
66 changes: 66 additions & 0 deletions anime_face_detector/configs/mmdet/faster-rcnn.py
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,66 @@
model = dict(type='FasterRCNN',
backbone=dict(type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=True,
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_generator=dict(type='AnchorGenerator',
scales=[8],
ratios=[0.5, 1.0, 2.0],
strides=[4, 8, 16, 32, 64]),
bbox_coder=dict(type='DeltaXYWHBBoxCoder',
target_means=[0.0, 0.0, 0.0, 0.0],
target_stds=[1.0, 1.0, 1.0, 1.0])),
roi_head=dict(
type='StandardRoIHead',
bbox_roi_extractor=dict(type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign',
output_size=7,
sampling_ratio=0),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=1,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0.0, 0.0, 0.0, 0.0],
target_stds=[0.1, 0.1, 0.2, 0.2]),
reg_class_agnostic=False)),
test_cfg=dict(rpn=dict(nms_pre=1000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100)))
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',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]
data = dict(test=dict(pipeline=test_pipeline))
47 changes: 47 additions & 0 deletions anime_face_detector/configs/mmdet/yolov3.py
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,47 @@
model = dict(type='YOLOV3',
backbone=dict(type='Darknet', depth=53, out_indices=(3, 4, 5)),
neck=dict(type='YOLOV3Neck',
num_scales=3,
in_channels=[1024, 512, 256],
out_channels=[512, 256, 128]),
bbox_head=dict(type='YOLOV3Head',
num_classes=1,
in_channels=[512, 256, 128],
out_channels=[1024, 512, 256],
anchor_generator=dict(type='YOLOAnchorGenerator',
base_sizes=[[(116, 90),
(156, 198),
(373, 326)],
[(30, 61),
(62, 45),
(59, 119)],
[(10, 13),
(16, 30),
(33, 23)]],
strides=[32, 16, 8]),
bbox_coder=dict(type='YOLOBBoxCoder'),
featmap_strides=[32, 16, 8]),
test_cfg=dict(nms_pre=1000,
min_bbox_size=0,
score_thr=0.05,
conf_thr=0.005,
nms=dict(type='nms', iou_threshold=0.45),
max_per_img=100))
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='MultiScaleFlipAug',
img_scale=(608, 608),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize',
mean=[0, 0, 0],
std=[255.0, 255.0, 255.0],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]
data = dict(test=dict(pipeline=test_pipeline))
250 changes: 250 additions & 0 deletions anime_face_detector/configs/mmpose/hrnetv2.py
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,250 @@
channel_cfg = dict(num_output_channels=28,
dataset_joints=28,
dataset_channel=[
list(range(28)),
],
inference_channel=list(range(28)))

model = dict(
type='TopDown',
backbone=dict(type='HRNet',
in_channels=3,
extra=dict(stage1=dict(num_modules=1,
num_branches=1,
block='BOTTLENECK',
num_blocks=(4, ),
num_channels=(64, )),
stage2=dict(num_modules=1,
num_branches=2,
block='BASIC',
num_blocks=(4, 4),
num_channels=(18, 36)),
stage3=dict(num_modules=4,
num_branches=3,
block='BASIC',
num_blocks=(4, 4, 4),
num_channels=(18, 36, 72)),
stage4=dict(num_modules=3,
num_branches=4,
block='BASIC',
num_blocks=(4, 4, 4, 4),
num_channels=(18, 36, 72, 144),
multiscale_output=True),
upsample=dict(mode='bilinear',
align_corners=False))),
keypoint_head=dict(type='TopdownHeatmapSimpleHead',
in_channels=[18, 36, 72, 144],
in_index=(0, 1, 2, 3),
input_transform='resize_concat',
out_channels=channel_cfg['num_output_channels'],
num_deconv_layers=0,
extra=dict(final_conv_kernel=1,
num_conv_layers=1,
num_conv_kernels=(1, )),
loss_keypoint=dict(type='JointsMSELoss',
use_target_weight=True)),
test_cfg=dict(flip_test=True,
post_process='unbiased',
shift_heatmap=True,
modulate_kernel=11))

data_cfg = dict(image_size=[256, 256],
heatmap_size=[64, 64],
num_output_channels=channel_cfg['num_output_channels'],
num_joints=channel_cfg['dataset_joints'],
dataset_channel=channel_cfg['dataset_channel'],
inference_channel=channel_cfg['inference_channel'])

test_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='TopDownAffine'),
dict(type='ToTensor'),
dict(type='NormalizeTensor',
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]),
dict(type='Collect',
keys=['img'],
meta_keys=['image_file', 'center', 'scale', 'rotation',
'flip_pairs']),
]

dataset_info = dict(dataset_name='anime_face',
paper_info=dict(),
keypoint_info={
0:
dict(name='kpt-0',
id=0,
color=[255, 255, 255],
type='',
swap='kpt-4'),
1:
dict(name='kpt-1',
id=1,
color=[255, 255, 255],
type='',
swap='kpt-3'),
2:
dict(name='kpt-2',
id=2,
color=[255, 255, 255],
type='',
swap=''),
3:
dict(name='kpt-3',
id=3,
color=[255, 255, 255],
type='',
swap='kpt-1'),
4:
dict(name='kpt-4',
id=4,
color=[255, 255, 255],
type='',
swap='kpt-0'),
5:
dict(name='kpt-5',
id=5,
color=[255, 255, 255],
type='',
swap='kpt-10'),
6:
dict(name='kpt-6',
id=6,
color=[255, 255, 255],
type='',
swap='kpt-9'),
7:
dict(name='kpt-7',
id=7,
color=[255, 255, 255],
type='',
swap='kpt-8'),
8:
dict(name='kpt-8',
id=8,
color=[255, 255, 255],
type='',
swap='kpt-7'),
9:
dict(name='kpt-9',
id=9,
color=[255, 255, 255],
type='',
swap='kpt-6'),
10:
dict(name='kpt-10',
id=10,
color=[255, 255, 255],
type='',
swap='kpt-5'),
11:
dict(name='kpt-11',
id=11,
color=[255, 255, 255],
type='',
swap='kpt-19'),
12:
dict(name='kpt-12',
id=12,
color=[255, 255, 255],
type='',
swap='kpt-18'),
13:
dict(name='kpt-13',
id=13,
color=[255, 255, 255],
type='',
swap='kpt-17'),
14:
dict(name='kpt-14',
id=14,
color=[255, 255, 255],
type='',
swap='kpt-22'),
15:
dict(name='kpt-15',
id=15,
color=[255, 255, 255],
type='',
swap='kpt-21'),
16:
dict(name='kpt-16',
id=16,
color=[255, 255, 255],
type='',
swap='kpt-20'),
17:
dict(name='kpt-17',
id=17,
color=[255, 255, 255],
type='',
swap='kpt-13'),
18:
dict(name='kpt-18',
id=18,
color=[255, 255, 255],
type='',
swap='kpt-12'),
19:
dict(name='kpt-19',
id=19,
color=[255, 255, 255],
type='',
swap='kpt-11'),
20:
dict(name='kpt-20',
id=20,
color=[255, 255, 255],
type='',
swap='kpt-16'),
21:
dict(name='kpt-21',
id=21,
color=[255, 255, 255],
type='',
swap='kpt-15'),
22:
dict(name='kpt-22',
id=22,
color=[255, 255, 255],
type='',
swap='kpt-14'),
23:
dict(name='kpt-23',
id=23,
color=[255, 255, 255],
type='',
swap=''),
24:
dict(name='kpt-24',
id=24,
color=[255, 255, 255],
type='',
swap='kpt-26'),
25:
dict(name='kpt-25',
id=25,
color=[255, 255, 255],
type='',
swap=''),
26:
dict(name='kpt-26',
id=26,
color=[255, 255, 255],
type='',
swap='kpt-24'),
27:
dict(name='kpt-27',
id=27,
color=[255, 255, 255],
type='',
swap='')
},
skeleton_info={},
joint_weights=[1.] * 28,
sigmas=[])

data = dict(test=dict(type='',
data_cfg=data_cfg,
pipeline=test_pipeline,
dataset_info=dataset_info), )
Loading

0 comments on commit 285675b

Please sign in to comment.