CSH
GitHub
parent
645dcf8c49
commit
6468d3150a
|
|
@ -12,15 +12,10 @@ The structure of this guide is as follows:
|
|||
|
||||
## Design of Data pipelines
|
||||
|
||||
Following typical conventions, we use `Dataset` and `DataLoader` for data loading
|
||||
with multiple workers. `Dataset` returns a dict of data items corresponding
|
||||
the arguments of models' forward method.
|
||||
Since the data in semantic segmentation may not be the same size,
|
||||
we introduce a new `DataContainer` type in MMCV to help collect and distribute
|
||||
data of different size.
|
||||
See [here](https://github.com/open-mmlab/mmcv/blob/master/mmcv/parallel/data_container.py) for more details.
|
||||
Following typical conventions, we use `Dataset` and `DataLoader` for data loading with multiple workers. `Dataset` returns a dict of data items corresponding the arguments of models' forward method. Since the data in semantic segmentation may not be the same size, we introduce a new `DataContainer` type in MMCV to help collect and distribute data of different size. See [here](https://github.com/open-mmlab/mmcv/blob/master/mmcv/parallel/data_container.py) for more details.
|
||||
|
||||
In 1.x version of MMSegmentation, all data transformations are inherited from [`BaseTransform`](https://github.com/open-mmlab/mmcv/blob/2.x/mmcv/transforms/base.py#L6).
|
||||
|
||||
The input and output types of transformations are both dict. A simple example is as follows:
|
||||
|
||||
```python
|
||||
|
|
@ -38,13 +33,11 @@ The input and output types of transformations are both dict. A simple example is
|
|||
dict_keys(['img_path', 'seg_map_path', 'reduce_zero_label', 'seg_fields', 'gt_seg_map'])
|
||||
```
|
||||
|
||||
The data preparation pipeline and the dataset are decomposed. Usually a dataset
|
||||
defines how to process the annotations and a data pipeline defines all the steps to prepare a data dict.
|
||||
A pipeline consists of a sequence of operations. Each operation takes a dict as input and also outputs a dict for the next transform.
|
||||
The data preparation pipeline and the dataset are decomposed. Usually a dataset defines how to process the annotations and a data pipeline defines all the steps to prepare a data dict. A pipeline consists of a sequence of operations. Each operation takes a dict as input and also outputs a dict for the next transform.
|
||||
|
||||
The operations are categorized into data loading, pre-processing, formatting and test-time augmentation.
|
||||
|
||||
Here is a pipeline example for PSPNet.
|
||||
Here is a pipeline example for PSPNet:
|
||||
|
||||
```python
|
||||
crop_size = (512, 1024)
|
||||
|
|
@ -71,8 +64,7 @@ test_pipeline = [
|
|||
]
|
||||
```
|
||||
|
||||
For each operation, we list the related dict fields that are `added`/`updated`/`removed`.
|
||||
Before pipelines, the information we can directly obtain from the datasets are `img_path` and `seg_map_path`.
|
||||
For each operation, we list the related dict fields that are `added`/`updated`/`removed`. Before pipelines, the information we can directly obtain from the datasets are `img_path` and `seg_map_path`.
|
||||
|
||||
### Data loading
|
||||
|
||||
|
|
@ -98,16 +90,14 @@ Before pipelines, the information we can directly obtain from the datasets are `
|
|||
|
||||
`RandomCrop`: Random crop image & segmentation map.
|
||||
|
||||
- update: `img`, `gt_seg_map`, `img_shape`.
|
||||
- update: `img`, `gt_seg_map`, `img_shape`
|
||||
|
||||
`RandomFlip`: Flip the image & segmentation map.
|
||||
|
||||
- add: `flip`, `flip_direction`
|
||||
- update: `img`, `gt_seg_map`
|
||||
|
||||
`PhotoMetricDistortion`: Apply photometric distortion to image sequentially,
|
||||
every transformation is applied with a probability of 0.5.
|
||||
The position of random contrast is in second or second to last(mode 0 or 1 below, respectively).
|
||||
`PhotoMetricDistortion`: Apply photometric distortion to image sequentially, every transformation is applied with a probability of 0.5. The position of random contrast is in second or second to last(mode 0 or 1 below, respectively).
|
||||
|
||||
```
|
||||
1. random brightness
|
||||
|
|
|
|||
|
|
@ -1,3 +1,119 @@
|
|||
# 数据增强变化
|
||||
|
||||
中文版文档支持中，请先阅读[英文版本](../../en/advanced_guides/transforms.md)
|
||||
在本教程中，我们将介绍 MMSegmentation 中数据增强变化流程的设计。
|
||||
|
||||
本指南的结构如下：
|
||||
|
||||
- [数据增强变化](#数据增强变化)
|
||||
- [数据增强变化流程设计](#数据增强变化流程设计)
|
||||
- [数据加载](#数据加载)
|
||||
- [预处理](#预处理)
|
||||
- [格式修改](#格式修改)
|
||||
|
||||
## 数据增强变化流程设计
|
||||
|
||||
按照惯例，我们使用 `Dataset` 和 `DataLoader` 多进程地加载数据。`Dataset` 返回与模型 forward 方法的参数相对应的数据项的字典。由于语义分割中的数据可能大小不同，我们在 MMCV 中引入了一种新的 `DataContainer` 类型，以帮助收集和分发不同大小的数据。参见[此处](https://github.com/open-mmlab/mmcv/blob/master/mmcv/parallel/data_container.py)了解更多详情。
|
||||
|
||||
在 MMSegmentation 的 1.x 版本中，所有数据转换都继承自 [`BaseTransform`](https://github.com/open-mmlab/mmcv/blob/2.x/mmcv/transforms/base.py#L6).
|
||||
|
||||
转换的输入和输出类型都是字典。一个简单的示例如下：
|
||||
|
||||
```python
|
||||
>>> from mmseg.datasets.transforms import LoadAnnotations
|
||||
>>> transforms = LoadAnnotations()
|
||||
>>> img_path = './data/cityscapes/leftImg8bit/train/aachen/aachen_000000_000019_leftImg8bit.png.png'
|
||||
>>> gt_path = './data/cityscapes/gtFine/train/aachen/aachen_000015_000019_gtFine_instanceTrainIds.png'
|
||||
>>> results = dict(
|
||||
>>> img_path=img_path,
|
||||
>>> seg_map_path=gt_path,
|
||||
>>> reduce_zero_label=False,
|
||||
>>> seg_fields=[])
|
||||
>>> data_dict = transforms(results)
|
||||
>>> print(data_dict.keys())
|
||||
dict_keys(['img_path', 'seg_map_path', 'reduce_zero_label', 'seg_fields', 'gt_seg_map'])
|
||||
```
|
||||
|
||||
数据准备流程和数据集是解耦的。通常，数据集定义如何处理标注，数据流程定义准备数据字典的所有步骤。流程由一系列操作组成。每个操作都将字典作为输入，并为接下来的转换输出字典。
|
||||
|
||||
操作分为数据加载、预处理、格式修改和测试数据增强。
|
||||
|
||||
这里是 PSPNet 的流程示例：
|
||||
|
||||
```python
|
||||
crop_size = (512, 1024)
|
||||
train_pipeline = [
|
||||
dict(type='LoadImageFromFile'),
|
||||
dict(type='LoadAnnotations'),
|
||||
dict(
|
||||
type='RandomResize',
|
||||
scale=(2048, 1024),
|
||||
ratio_range=(0.5, 2.0),
|
||||
keep_ratio=True),
|
||||
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
|
||||
dict(type='RandomFlip', prob=0.5),
|
||||
dict(type='PhotoMetricDistortion'),
|
||||
dict(type='PackSegInputs')
|
||||
]
|
||||
test_pipeline = [
|
||||
dict(type='LoadImageFromFile'),
|
||||
dict(type='Resize', scale=(2048, 1024), keep_ratio=True),
|
||||
# add loading annotation after ``Resize`` because ground truth
|
||||
# does not need to resize data transform
|
||||
dict(type='LoadAnnotations'),
|
||||
dict(type='PackSegInputs')
|
||||
]
|
||||
```
|
||||
|
||||
对于每个操作，我们列出了 `添加`/`更新`/`删除` 相关的字典字段。在流程前，我们可以从数据集直接获得的信息是 `img_path` 和 `seg_map_path`。
|
||||
|
||||
### 数据加载
|
||||
|
||||
`LoadImageFromFile`：从文件加载图像。
|
||||
|
||||
- 添加：`img`，`img_shape`，`ori_shape`
|
||||
|
||||
`LoadAnnotations`：加载数据集提供的语义分割图。
|
||||
|
||||
- 添加：`seg_fields`，`gt_seg_map`
|
||||
|
||||
### 预处理
|
||||
|
||||
`RandomResize`：随机调整图像和分割图大小。
|
||||
|
||||
-添加：`scale`，`scale_factor`，`keep_ratio`
|
||||
-更新：`img`，`img_shape`，`gt_seg_map`
|
||||
|
||||
`Resize`：调整图像和分割图的大小。
|
||||
|
||||
-添加：`scale`，`scale_factor`，`keep_ratio`
|
||||
-更新：`img`，`gt_seg_map`，`img_shape`
|
||||
|
||||
`RandomCrop`：随机裁剪图像和分割图。
|
||||
|
||||
-更新：`img`，`gt_seg_map`，`img_shape`
|
||||
|
||||
`RandomFlip`：翻转图像和分割图。
|
||||
|
||||
-添加：`flip`，`flip_direction`
|
||||
-更新：`img`，`gt_seg_map`
|
||||
|
||||
`PhotoMetricDistortion`：按顺序对图像应用光度失真，每个变换的应用概率为 0.5。随机对比度的位置是第二或倒数第二（分别为下面的模式 0 或 1）。
|
||||
|
||||
```
|
||||
1.随机亮度
|
||||
2.随机对比度（模式 0）
|
||||
3.将颜色从 BGR 转换为 HSV
|
||||
4.随机饱和度
|
||||
5.随机色调
|
||||
6.将颜色从 HSV 转换为 BGR
|
||||
7.随机对比度（模式 1）
|
||||
```
|
||||
|
||||
- 更新：`img`
|
||||
|
||||
### 格式修改
|
||||
|
||||
`PackSegInputs`：为语义分段打包输入数据。
|
||||
|
||||
- 添加：`inputs`，`data_sample`
|
||||
- 删除：由 `meta_keys` 指定的 keys（合并到 data_sample 的 metainfo 中），所有其他 keys
|
||||
|
|
|
|||
Loading…
Reference in New Issue