今日笔记主要是关于如何使用mmdetection完成第二次作业的
1. 安装ffmpeg
- 下载解压
wget http://www.ffmpeg.org/releases/ffmpeg-3.1.tar.gz
tar -zxvf ffmpeg-3.1.tar.gz
- 进入解压后目录,输入如下命令/usr/local/ffmpeg为自己指定的安装目录
cd ffmpeg-3.1
./configure --prefix=/usr/local/ffmpeg
make && make install
- 配置变量
vi /etc/profile
在最后PATH添加环境变量:
export PATH=$PATH:/usr/local/ffmpeg/bin
保存退出
查看是否生效
source /ect/profile 设置生效
- 查看版本
ffmpeg -version 查看版本
2. 将数据集转为coco格式
原来的数据集是via格式的,这里使用脚本将其转为coco格式
import os.path as osp
import mmcv
def convert_VIA_to_coco(ann_file, out_file, image_prefix):
data_infos = mmcv.load(ann_file)
annotations = []
images = []
obj_count = 0
for idx, v in enumerate(mmcv.track_iter_progress(data_infos.values())):
filename = v['filename']
img_path = osp.join(image_prefix, filename)
height, width = mmcv.imread(img_path).shape[:2]
images.append(dict(
id=idx,
file_name=filename,
height=height,
width=width))
bboxes = []
labels = []
masks = []
#多个类别标注,循环获取每一个一个类别
for n in range(len(v['regions'])):
obj = v['regions'][str(n)]
obj = obj['shape_attributes']
px = obj['all_points_x']
py = obj['all_points_y']
poly = [(x + 0.5, y + 0.5) for x, y in zip(px, py)]
poly = [p for x in poly for p in x]
x_min, y_min, x_max, y_max = (
min(px), min(py), max(px), max(py))
data_anno = dict(
image_id=idx,
id=obj_count,
category_id=n,
bbox=[x_min, y_min, x_max - x_min, y_max - y_min],
area=(x_max - x_min) * (y_max - y_min),
segmentation=[poly],
iscrowd=0)
annotations.append(data_anno)
obj_count += 1
coco_format_json = dict(
images=images,
annotations=annotations,
categories=[{'id': 0, 'name': 'fish'} , {'id': 1, 'name': 'face'}])#添加自己训练数据的类别
mmcv.dump(coco_format_json, out_file)
convert_VIA_to_coco("./data/balloon/train/via_region_data.json", "./data/balloon/train/annotation_coco.json", "./data/balloon/train")
convert_VIA_to_coco("./data/balloon/val/via_region_data.json", "./data/balloon/val/annotation_coco.json", "./data/balloon/val")
3. 修改配置文件
主要针对数据集路径以及模型类别进行修改
# model settings
model = dict(
type='MaskRCNN',
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',
init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
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],
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='L1Loss', loss_weight=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=80,
num_classes=1,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
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='L1Loss', loss_weight=1.0)),
mask_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
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=1,
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,
match_low_quality=True,
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=-1,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_pre=2000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=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,
match_low_quality=True,
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_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,
mask_thr_binary=0.5)))
# dataset settings
dataset_type = 'CocoDataset'
data_root = './data/balloon'
CLASSES = ('balloon', )
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(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + '/train/annotation_coco.json',
img_prefix=data_root + '/train/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + '/val/annotation_coco.json',
img_prefix=data_root + '/val/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + '/val/annotation_coco.json',
img_prefix=data_root + '/val/',
pipeline=test_pipeline))
evaluation = dict(metric=['bbox', 'segm'])
# optimizer
optimizer = dict(type='SGD', lr=0.001, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=0.0001,
step=[16, 22])
runner = dict(type='EpochBasedRunner', max_epochs=10)
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=25,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
custom_hooks = [dict(type='NumClassCheckHook')]
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = "./mask_rcnn_r50_fpn_mstrain-poly_3x_coco_20210524_201154-21b550bb.pth"
resume_from = None
workflow = [('train', 1)]
# disable opencv multithreading to avoid system being overloaded
opencv_num_threads = 0
# set multi-process start method as `fork` to speed up the training
mp_start_method = 'fork'
# Default setting for scaling LR automatically
# - `enable` means enable scaling LR automatically
# or not by default.
# - `base_batch_size` = (8 GPUs) x (2 samples per GPU).
auto_scale_lr = dict(enable=False, base_batch_size=16)