mmsegmentaion安装记录
mmsegmentaion安装记录
安装anaconda环境
conda create --name Hopenmmlab python=3.8 -y
conda activate Hopenmmlab
安装GPU torch
pip3 install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu116
安装mmcv-full
安装mmcv-full，由系统cuda版本和安装的pytorch版本安装对应版本mmcv[此处的Torch版本应于你当前安装的torch版本一致]
pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/cu116/torch1.12.1/index.html
使用 MIM/PIP 安装 MMCV
pip install -U openmim
mim install mmcv-full
安装 MMSegmentation(源码下载方式)
git clone https://github.com/open-mmlab/mmsegmentation.git
cd mmsegmentation
pip install -v -e .
# "-v "指详细说明，或更多的输出
# "-e" 表示在可编辑模式下安装项目，因此对代码所做的任何本地修改都会生效，从而无需重新安装。
安装 MMEngine
- https://mmengine.readthedocs.io/zh_CN/latest/get_started/installation.html[官方教程]
由于pip和min没有安装成功，因此用源码的方式试试
如果克隆代码仓库的速度过慢，可以从 https://gitee.com/open-mmlab/mmengine.git 克隆
git clone https://github.com/open-mmlab/mmengine.git
cd mmengine
pip install -e . -v
测试是否正确安装了 MMEngine
python -c import mmengine;print(mmengine.__version__)
注：源码好使，不要开VPN
简单测试一波
第一步: 我们需要下载配置文件和模型权重文件。
mim download mmsegmentation --config pspnet_r50-d8_512x1024_40k_cityscapes --dest .
第二步 验证推理示例
如果您是从源码安装的 MMSegmentation，那么直接运行以下命令进行验证：
python demo/image_demo.py demo/demo.png pspnet_r50-d8_512x1024_40k_cityscapes.py pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth --device cpu --out-file result.jpg
注意：
由于这里是单卡训练，不是多卡。因此需要将type=‘SyncBN’ 修改为 type=‘BN’ 。具体修改这个文件
修改之后的文件
norm_cfg = dict(type='BN', requires_grad=True)
model = dict(
type='EncoderDecoder',
pretrained='open-mmlab://resnet50_v1c',
backbone=dict(
type='ResNetV1c',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
dilations=(1, 1, 2, 4),
strides=(1, 2, 1, 1),
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=False,
style='pytorch',
contract_dilation=True),
decode_head=dict(
type='PSPHead',
in_channels=2048,
in_index=3,
channels=512,
pool_scales=(1, 2, 3, 6),
dropout_ratio=0.1,
num_classes=19,
norm_cfg=dict(type='BN', requires_grad=True),
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
auxiliary_head=dict(
type='FCNHead',
in_channels=1024,
in_index=2,
channels=256,
num_convs=1,
concat_input=False,
dropout_ratio=0.1,
num_classes=19,
norm_cfg=dict(type='BN', requires_grad=True),
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
train_cfg=dict(),
test_cfg=dict(mode='whole'))
dataset_type = 'CityscapesDataset'
data_root = 'data/cityscapes/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
crop_size = (512, 1024)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations'),
dict(type='Resize', img_scale=(2048, 1024), ratio_range=(0.5, 2.0)),
dict(type='RandomCrop', crop_size=(512, 1024), cat_max_ratio=0.75),
dict(type='RandomFlip', prob=0.5),
dict(type='PhotoMetricDistortion'),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size=(512, 1024), pad_val=0, seg_pad_val=255),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_semantic_seg'])
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(2048, 1024),
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='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
type='CityscapesDataset',
data_root='data/cityscapes/',
img_dir='leftImg8bit/train',
ann_dir='gtFine/train',
pipeline=[
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations'),
dict(
type='Resize', img_scale=(2048, 1024), ratio_range=(0.5, 2.0)),
dict(type='RandomCrop', crop_size=(512, 1024), cat_max_ratio=0.75),
dict(type='RandomFlip', prob=0.5),
dict(type='PhotoMetricDistortion'),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size=(512, 1024), pad_val=0, seg_pad_val=255),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_semantic_seg'])
]),
val=dict(
type='CityscapesDataset',
data_root='data/cityscapes/',
img_dir='leftImg8bit/val',
ann_dir='gtFine/val',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(2048, 1024),
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='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]),
test=dict(
type='CityscapesDataset',
data_root='data/cityscapes/',
img_dir='leftImg8bit/val',
ann_dir='gtFine/val',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(2048, 1024),
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='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]))
log_config = dict(
interval=50, hooks=[dict(type='TextLoggerHook', by_epoch=False)])
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
cudnn_benchmark = True
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
optimizer_config = dict()
lr_config = dict(policy='poly', power=0.9, min_lr=0.0001, by_epoch=False)
runner = dict(type='IterBasedRunner', max_iters=40000)
checkpoint_config = dict(by_epoch=False, interval=4000)
evaluation = dict(interval=4000, metric='mIoU', pre_eval=True)
运行上述分割代码
图片存储的路径如下
参考教程
- https://mmsegmentation.readthedocs.io/zh_CN/latest/get_started.html#id2
- https://mmengine.readthedocs.io/zh_CN/latest/get_started/installation.html