【MMDetection 超全专栏】一，结构设计和官方文档2.0伪译

 _base_ = [
  '../_base_/models/mask_rcnn_r50_fpn.py',
  '../_base_/datasets/cityscapes_instance.py', '../_base_/default_runtime.py'
 ]
 

 model = dict(
    pretrained=None,
    roi_head=dict(
        bbox_head=dict(
            type='Shared2FCBBoxHead',
            in_channels=256,
            fc_out_channels=1024,
            roi_feat_size=7,
            num_classes=8,    # new num_classes
            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='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
        mask_head=dict(
            type='FCNMaskHead',
            num_convs=4,
            in_channels=256,
            conv_out_channels=256,
            num_classes=8,
            loss_mask=dict(
                type='CrossEntropyLoss', use_mask=True, loss_weight=1.0)))
 

 # optimizer
 # lr is set for a batch size of 8
 optimizer = dict(type='SGD', lr=0.01, 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=0.001,
  # [7] yields higher performance than [6]
  step=[7])
 total_epochs = 8  # actual epoch = 8 * 8 = 64
 log_config = dict(interval=100)

load_from = 'https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r50_fpn_2x_20181010-41d35c05.pth' 

...
 # dataset settings
 dataset_type = 'CocoDataset'
 classes = ('a', 'b', 'c', 'd', 'e')    ＃ 自己的五类名字
 ...
 data = dict(
  samples_per_gpu=2,
  workers_per_gpu=2,
  train=dict(
   type=dataset_type,
   classes=classes,
   ann_file='path/to/your/train/data',
   ...),
  val=dict(
   type=dataset_type,
   classes=classes,
   ann_file='path/to/your/val/data',
   ...),
  test=dict(
   type=dataset_type,
   classes=classes,
   ann_file='path/to/your/test/data',
   ...))
 ...
 

[
  {
   'filename': 'a.jpg',
   'width': 1280,
   'height': 720,
   'ann': {
    'bboxes': <np.ndarray, float32> (n, 4),
    'labels': <np.ndarray, int64> (n, ),
    'bboxes_ignore': <np.ndarray, float32> (k, 4),
    'labels_ignore': <np.ndarray, int64> (k, ) (optional field)
   }
  },
  ...
 ]
 

#
000001.jpg
1280 720
2
10 20 40 60 1
20 40 50 60 2
#
000002.jpg
1280 720
3
50 20 40 60 2
20 40 30 45 2
30 40 50 60 3

import mmcv
import numpy as np

from .builder import DATASETS
from .custom import CustomDataset

@DATASETS.register_module()
class MyDataset(CustomDataset):

 CLASSES = ('person', 'bicycle', 'car', 'motorcycle')

 def load_annotations(self, ann_file):
  ann_list = mmcv.list_from_file(ann_file)

  data_infos = []
  for i, ann_line in enumerate(ann_list):
   if ann_line != '#':
    continue

   img_shape = ann_list[i + 2].split(' ')
   width = int(img_shape[0])
   height = int(img_shape[1])
   bbox_number = int(ann_list[i + 3])

   anns = ann_line.split(' ')
   bboxes = []
   labels = []
   for anns in ann_list[i + 4:i + 4 + bbox_number]:
    bboxes.append([float(ann) for ann in anns[:4]])
    labels.append(int(anns[4]))

   data_infos.append(
    dict(
     filename=ann_list[i + 1],
     width=width,
     height=height,
     ann=dict(
      bboxes=np.array(bboxes).astype(np.float32),
      labels=np.array(labels).astype(np.int64))
    ))

  return data_infos

 def get_ann_info(self, idx):
  return self.data_infos[idx]['ann']

# 配置文件做如下更改:

dataset_A_train = dict(
    type='MyDataset',
    ann_file = 'image_list.txt',
    pipeline=train_pipeline
)

classes = ('person', 'bicycle', 'car')
# classes = 'path/to/classes.txt'  # 或者类别从文件中读取
data = dict(
 train=dict(classes=classes),
 val=dict(classes=classes),
 test=dict(classes=classes))

# １．实现新增强函数 my\_pipeline.py
# 和pytorch原始transforms中的增强方式一样，实现__call__方法的类即可
from mmdet.datasets import PIPELINES

@PIPELINES.register_module()
class MyTransform:

    def __call__(self, results):    # 输入的是mmdet设定的字典格式
        results['dummy'] = True
  return results
  
# 2. 导入新类.
from .my_pipeline import MyTransform

# 3. 配置文件调用

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=(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='MyTransform'),
    dict(type='DefaultFormatBundle'),
    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]

from mmcv.utils import build_from_cfg

from mmdet.core.optimizer import OPTIMIZER_BUILDERS, OPTIMIZERS
from mmdet.utils import get_root_logger
from .cocktail_optimizer import CocktailOptimizer

@OPTIMIZER_BUILDERS.register_module
class CocktailOptimizerConstructor(object):

 def __init__(self, optimizer_cfg, paramwise_cfg=None):

 def __call__(self, model):

  return my_optimizer
 

# 1.在 mmdet/models/losses/my_loss.py实现新的box回归函数
import torch
import torch.nn as nn

from ..builder import LOSSES
from .utils import weighted_loss

@weighted_loss    ＃ 加权损失函数，可参考损失函数章节
def my_loss(pred, target):
 assert pred.size() == target.size() and target.numel() > 0
 loss = torch.abs(pred - target)
 return loss

@LOSSES.register_module
class MyLoss(nn.Module):

 def __init__(self, reduction='mean', loss_weight=1.0):
  super(MyLoss, self).__init__()
  self.reduction = reduction
  self.loss_weight = loss_weight

 def forward(self,
    pred,
    target,
    weight=None,
    avg_factor=None,
    reduction_override=None):
  assert reduction_override in (None, 'none', 'mean', 'sum')
  reduction = (
   reduction_override if reduction_override else self.reduction)
  loss_bbox = self.loss_weight * my_loss(
   pred, target, weight, reduction=reduction, avg_factor=avg_factor)

# ２．然后在mmdet/models/losses/__init__.py.中注册
from .my_loss import MyLoss, my_loss

# 3. 配置文件使用
loss_bbox=dict(type='MyLoss', loss_weight=1.0))