PolarMask代碼跑通

0、環境配置

• conda create --name polarmask python=3.7
• conda activate polarmask
• pip install torch==1.2.0
• pip install torchvision==0.4.0
• pip install Cython
• python setup.py develop
• pip install mmcv
• pip install prompt-toolkit==2.0.10
• pip install Polygon3

1、config設置

配置文件的設置：

# model settings
model = dict(
    type='PolarMask',
    pretrained='open-mmlab://resnet50_caffe',
    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=False),
        style='caffe'),
    neck=dict(
        type='FPN',
        in_channels=[256, 512, 1024, 2048],
        out_channels=256,
        start_level=1,
        add_extra_convs=True,
        extra_convs_on_inputs=False,  # use P5
        num_outs=5,
        relu_before_extra_convs=True),
    bbox_head=dict(
        type='PolarMask_Head',
        num_classes=81,
        in_channels=256,
        stacked_convs=4,
        feat_channels=256,
        strides=[8, 16, 32, 64, 128],
        loss_cls=dict(
            type='FocalLoss',
            use_sigmoid=True,
            gamma=2.0,
            alpha=0.25,
            loss_weight=1.0),
        loss_bbox=dict(type='IoULoss', loss_weight=1.0),
        loss_centerness=dict(
            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0)))
# training and testing settings
train_cfg = dict(
    assigner=dict(
        type='MaxIoUAssigner',
        pos_iou_thr=0.5,
        neg_iou_thr=0.4,
        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 = 'Coco_Seg_Dataset'
data_root = '/media/dell/Elements/dataset/MSCOCO/2017/' # 數據路徑
img_norm_cfg = dict(
    mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
data = dict(
    imgs_per_gpu=2,
    workers_per_gpu=5,
    train=dict(
        type=dataset_type,
        ann_file=data_root + 'annotations/instances_train2017.json',
        img_prefix=data_root + 'train2017/',
        img_scale=(1280, 768),
        img_norm_cfg=img_norm_cfg,
        # size_divisor=0,
        flip_ratio=0.5,
        with_mask=True,
        with_crowd=False,
        with_label=True,
        resize_keep_ratio=False),
    val=dict(
        type=dataset_type,
        ann_file=data_root + 'annotations/instances_val2017.json',
        img_prefix=data_root + 'val2017/',
        img_scale=(1280, 768),
        img_norm_cfg=img_norm_cfg,
        # size_divisor=0,
        flip_ratio=0,
        with_mask=False,
        with_crowd=False,
        with_label=True,
        resize_keep_ratio=False),
    test=dict(
        type=dataset_type,
        ann_file=data_root + 'annotations/instances_val2017.json',
        img_prefix=data_root + 'val2017/',
        img_scale=(1280, 768),
        img_norm_cfg=img_norm_cfg,
        size_divisor=32,
        flip_ratio=0,
        with_mask=False,
        with_crowd=False,
        with_label=False,
        resize_keep_ratio=False,
        test_mode=True))
# optimizer
lr_ratio = 1

optimizer = dict(
    type='SGD',
    lr=0.01 * lr_ratio,
    momentum=0.9,
    weight_decay=0.0001,
    paramwise_options=dict(bias_lr_mult=2., bias_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=500,
    warmup_ratio=1.0 / 3 / lr_ratio,
    step=[8, 11])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
    interval=10,
    hooks=[
        dict(type='TextLoggerHook'),
        # dict(type='TensorboardLoggerHook')
    ])
# yapf:enable
# runtime settings
total_epochs = 12
device_ids = range(2) # 由幾張卡決定
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/trash'
load_from = None
resume_from = None
workflow = [('train', 1)]

2、訓練語句

雙GPU:python ./tools/train.py configs/polarmask/4gpu/polar_768_1x_r50.py --gpus 2 --launcher pytorch --work_dir ./tools/work_dirs/polar_768_1x_r50_4gpu --resume_from ./tools/work_dirs/polar_768_1x_r50_4gpu/epoch_2.pth

單GPU:python ./tools/train.py configs/polarmask/4gpu/polar_768_1x_r50.py --gpus 1 --launcher pytorch --work_dir ./tools/work_dirs/polar_768_1x_r50_4gpu

3、測試語句

python ./tools/test.py configs/polarmask/4gpu/polar_768_1x_r50.py ./tools/work_dirs/polar_768_1x_r50_4gpu/latest.pth --launcher pytorch --out work_dirs/trash/res.pkl --eval segm

4、出現問題

1、ModuleNotFoundError: No module named ‘mmcv.cnn.weight_init’
解決：pip install mmcv==0.5.9

2、ImportError: cannot import name ‘AsyncGenerator’
解決：```pip install prompt-toolkit==2.0.10``

3、ImportError: cannot import name ‘get_dist_info’
解決：
change /PolarMask/mmdet/datasets/loader/sampler.py line 6 from mmcv.runner.utils import get_dist_infoto from mmcv.runner import get_dist_info

from mmcv.runner import get_dist_info

4、anaconda3/lib/python3.6/sitepackages/torch/lib/libtorch_python.so: undefined symbol: PySlice_Unpack
解決：將python3.6.0升級更高（3.6.2及以上）