1
2
3
4
5
6
7
8

sudo mkdir -p /etc/docker
sudo tee /etc/docker/daemon.json <<-'EOF'
{
  "registry-mirrors": ["https://adfx5pa6.mirror.aliyuncs.com"]
}
EOF
sudo systemctl daemon-reload
sudo systemctl restart docker

1

docker build -t mmedetection:1.0 .

1
2

RUN echo 'nameserver 223.5.5.5' > /etc/resolv.conf
RUN echo 'nameserver 223.6.6.6' > /etc/resolv.conf

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32

ARG PYTORCH="1.6.0"
ARG CUDA="10.1"
ARG CUDNN="7"

FROM pytorch/pytorch:${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel
ENV TORCH_CUDA_ARCH_LIST="6.0 6.1 7.0+PTX"
ENV TORCH_NVCC_FLAGS="-Xfatbin -compress-all"
ENV CMAKE_PREFIX_PATH="$(dirname $(which conda))/../"
RUN sed -i s@/archive.ubuntu.com/@/mirrors.aliyun.com/@g /etc/apt/sources.list
RUN apt-get clean
RUN apt-get update
RUN pip config set global.index-url http://mirrors.aliyun.com/pypi/simple
RUN pip config set install.trusted-host mirrors.aliyun.com
RUN pip install -U pip
RUN echo 'nameserver 223.5.5.5' > /etc/resolv.conf
RUN echo 'nameserver 223.6.6.6' > /etc/resolv.conf
RUN apt-get install -y ffmpeg libsm6 libxext6 git ninja-build libglib2.0-0 libsm6 libxrender-dev libxext6 \
    && apt-get clean \
    && rm -rf /var/lib/apt/lists/*

# Install MMCV
RUN pip install  pytest-runner -i http://pypi.douban.com/simple --trusted-host pypi.douban.com
RUN pip install mmcv
# RUN pip install mmcv-full==latest+torch1.6.0+cu101 -f https://download.openmmlab.com/mmcv/dist/index.html

# Install MMDetection
RUN conda clean --all
RUN git clone https://gitee.com/Xingyu-Romantic/mmdetection.git /mmdetection
WORKDIR /mmdetection
ENV FORCE_CUDA="1"
RUN pip install -r requirements/build.txt
RUN pip install --no-cache-dir -e .

1
2

pd.read_json('anno_train.json')['defect_name'].unique()
# array(['虫粘', '色差', '沾污', '缝头', '花毛', '织疵', '缝头印', '褶子', '漏印', '错花', '网折','破洞', '水印'], dtype=object)

1
2

CLASSES = ('虫粘', '色差',  '沾污', '缝头', '花毛', '织疵', '缝头印', '褶子',
    '漏印', '错花', '网折', '破洞', '水印')

1
2

CLASSES = ('虫粘', '色差',  '沾污', '缝头', '花毛', '织疵', '缝头印', '褶子',
    '漏印', '错花', '网折', '破洞', '水印')

1
2
3
4
5

def coco_classes():
    return [
        '虫粘', '色差',  '沾污', '缝头', '花毛', '织疵', '缝头印', '褶子',
    '漏印', '错花', '网折', '破洞', '水印'
    ]

1
2
3

docker run --gpus all -v ~/Desktop/机器学习/Computer_Vision/mmdetection_new/data/coco/:/mmdetection/data/coco \
-it 7fd91b5345bf \
/bin/bash

1
2
3

docker run --gpus all \
-v ~/Desktop/机器学习/Computer_Vision/mmdetection_new/data/coco/val2017/:/tcdata/guangdong1_round2_testB_20191024/201908262_de5bf60c1d3b79ad0201908262154188OK \
-it e6732164f22d /bin/bash

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280

# model settings
model = dict(
    type='CascadeRCNN',
    #num_stages=4,
    pretrained='torchvision://resnet50',
    backbone=dict(
        type='ResNet',
        depth=50,
        num_stages=4,
        out_indices=(0, 1, 2, 3),
        frozen_stages=1,
        dcn=dict(   #在最后一个阶段加入可变形卷积 改进点1
            deformable_groups=1, fallback_on_stride=False, type='DCN'),
        stage_with_dcn=(False, False, False, 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=[0.02, 0.05, 0.1, 0.5, 1.0, 2.0, 10.0, 20.0, 50.0], #根据样本瑕疵尺寸分布，修改anchor的长宽比。 点2
            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),   #此处可替换成focalloss
        loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
    roi_head=dict(
        type='CascadeRoIHead',
        num_stages=3,
        stage_loss_weights=[1, 0.5, 0.25],
        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=13,
                bbox_coder=dict(
                    type='DeltaXYWHBBoxCoder',
                    target_means=[0., 0., 0., 0.],
                    target_stds=[0.1, 0.1, 0.2, 0.2]),
                reg_class_agnostic=True,
                loss_cls=dict(
                    type='CrossEntropyLoss',
                    use_sigmoid=False,
                    loss_weight=1.0),
                loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
                               loss_weight=1.0)),
            dict(
                type='Shared2FCBBoxHead',
                in_channels=256,
                fc_out_channels=1024,
                roi_feat_size=7,
                num_classes=13,
                bbox_coder=dict(
                    type='DeltaXYWHBBoxCoder',
                    target_means=[0., 0., 0., 0.],
                    target_stds=[0.05, 0.05, 0.1, 0.1]),
                reg_class_agnostic=True,
                loss_cls=dict(
                    type='CrossEntropyLoss',
                    use_sigmoid=False,
                    loss_weight=1.0),
                loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
                               loss_weight=1.0)),
            dict(
                type='Shared2FCBBoxHead',
                in_channels=256,
                fc_out_channels=1024,
                roi_feat_size=7,
                num_classes=13,
                bbox_coder=dict(
                    type='DeltaXYWHBBoxCoder',
                    target_means=[0., 0., 0., 0.],
                    target_stds=[0.033, 0.033, 0.067, 0.067]),
                reg_class_agnostic=True,
                loss_cls=dict(
                    type='CrossEntropyLoss',
                    use_sigmoid=False,
                    loss_weight=1.0),
                loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
        ]),
    train_cfg = dict(
        rpn=dict(
            assigner=dict(
                type='MaxIoUAssigner',
                pos_iou_thr=0.7,
                neg_iou_thr=0.3,
                min_pos_iou=0.3,
                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=0,
            pos_weight=-1,
            debug=False),
        rpn_proposal=dict(
            nms_across_levels=False,
            nms_pre=2000,
            nms_post=2000,
            max_num=2000,
            nms_thr=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,
                    ignore_iof_thr=-1),
                sampler=dict(   #默认使用的是随机采样RandomSampler，这里替换成OHEM采样，即每个级联层引入在线难样本学习，改进点3
                    type='OHEMSampler',
                    num=512,
                    pos_fraction=0.25,
                    neg_pos_ub=-1,
                    add_gt_as_proposals=True),
                pos_weight=-1,
                debug=False),
            dict(
                assigner=dict(
                    type='MaxIoUAssigner',
                    pos_iou_thr=0.6,
                    neg_iou_thr=0.6,
                    min_pos_iou=0.6,
                    ignore_iof_thr=-1),
                sampler=dict( 
                    type='OHEMSampler',
                    num=512,
                    pos_fraction=0.25,
                    neg_pos_ub=-1,
                    add_gt_as_proposals=True),
                pos_weight=-1,
                debug=False),
            dict(
                assigner=dict(
                    type='MaxIoUAssigner',
                    pos_iou_thr=0.7,
                    neg_iou_thr=0.7,
                    min_pos_iou=0.7,
                    ignore_iof_thr=-1),
                sampler=dict(
                    type='OHEMSampler',
                    num=512,
                    pos_fraction=0.25,
                    neg_pos_ub=-1,
                    add_gt_as_proposals=True),
                pos_weight=-1,
                debug=False)
        ],
        stage_loss_weights=[1, 0.5, 0.25]),
    test_cfg = dict(
        rpn=dict(
            nms_across_levels=False,
            nms_pre=1000,
            nms_post=1000,
            max_num=1000,
            nms_thr=0.7,
            min_bbox_size=0),
        rcnn=dict(
            score_thr=0.05, nms=dict(type='nms', iou_thr=0.5), max_per_img=100),
        keep_all_stages=False)
    )
# model training and testing settings

# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
CLASSES = ('虫粘', '色差', '沾污', '缝头', '花毛', '织疵', '缝头印', '褶子', '漏印', '错花', '网折', '破洞', '水印')
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=(640, 320), keep_ratio=True), #考虑算力原有限，修改图像尺寸为半图，可修改为全图训练
    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=(1223, 500), 
        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(
    imgs_per_gpu=1,  #每张gpu训练多少张图片  batch_size = gpu_num(训练使用gpu数量) * imgs_per_gpu
    workers_per_gpu=1,
    train=dict(
        type=dataset_type,
        ann_file=data_root + 'annotations/instances_train2017.json', #修改成自己的训练集标注文件路径
        img_prefix=data_root + 'train2017', #训练图片路径
        pipeline=train_pipeline),
    val=dict(
        type=dataset_type,
        ann_file=data_root + 'annotations/instances_val2017.json', #修改成自己的验证集标注文件路径
        img_prefix=data_root + 'val2017', #验证图片路径
        pipeline=test_pipeline),
    test=dict(
        type=dataset_type,
        ann_file=data_root + 'annotations/instances_val2017.json', #修改成自己的验证集标注文件路径
        img_prefix=data_root + 'val2017', #验证图片路径
        pipeline=test_pipeline))

# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0025)  #学习率的设置尤为关键：lr = 0.00125*batch_size
optimizer_config = dict(grad_clip=None)
#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,
    step=[8, 11])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
    interval=50,
    hooks=[
        dict(type='TextLoggerHook'),
        # dict(type='TensorboardLoggerHook')
    ])
# yapf:enable
# runtime settings
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
    interval=50,
    hooks=[
        dict(type='TextLoggerHook'),
        # dict(type='TensorboardLoggerHook')
    ])
# yapf:enable
custom_hooks = [dict(type='NumClassCheckHook')]

dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None#'./checkpoints/cascade_rcnn_r50_fpn_1x_coco_20200316-3dc56deb.pth' #采用coco预训练模型 ,需要对权重类别数进行处理
resume_from = None
workflow = [('train', 1)]
total_epochs = 12
'''
checkpoint_config = dict(interval=1)
total_epochs = 12  
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/cascade_rcnn_r50_fpn_1x' #训练的权重和日志保存路径
load_from = './checkpoints/cascade_rcnn_r50_fpn_1x_coco_20200316-3dc56deb.pth' #采用coco预训练模型 ,需要对权重类别数进行处理
resume_from = None
workflow = [('train', 1)]'''