First commit

u7ko4 · Aug 26, 2019 · 951d342 · 951d342
1 parent f8e28e8
commit 951d342
Show file tree

Hide file tree

Showing 183 changed files with 11,059 additions and 1 deletion.
diff --git a/README.md b/README.md
@@ -1 +1,83 @@
-# PaddleSeg
+# PaddleSeg 语义分割库
+
+## 简介
+
+PaddleSeg是基于[PaddlePaddle](https://www.paddlepaddle.org.cn)开发的语义分割库，覆盖了DeepLabv3+, U-Net, ICNet三类主流的分割模型。通过统一的配置，帮助用户更便捷地完成从训练到部署的全流程图像分割应用。
+具备高性能、丰富的数据增强、工业级部署、全流程应用的特点。
+
+
+
+- **丰富的数据增强**
+
+  - 基于百度视觉技术部的实际业务经验，内置10+种数据增强策略，可结合实际业务场景进行定制组合，提升模型泛化能力和鲁棒性。
+
+- **主流模型覆盖**
+
+  - 支持U-Net, DeepLabv3+, ICNet三类主流分割网络，结合预训练模型和可调节的骨干网络，满足不同性能和精度的要求。
+
+- **高性能**
+
+  - PaddleSeg支持多进程IO、多卡并行、多卡Batch Norm, FP16混合精度等训练加速策略，通过飞桨核心框架的显存优化算法，可以大幅度节约分割模型的显存开销，更快完成分割模型训练。
+
+- **工业级部署**
+
+  - 基于[Paddle Serving](https://github.com/PaddlePaddle/Serving)和PaddlePaddle高性能预测引擎, 结合百度开放的AI能力，轻松搭建人像分割和车道线分割服务。
+
+
+
+
+更多模型信息与技术细节请查看[模型介绍](./docs/models.md)和[预训练模型](./docs/mode_zoo.md)
+
+## AI Studio教程
+
+### 快速开始
+
+通过 [PaddleSeg人像分割](https://aistudio.baidu.com/aistudio/projectDetail/100798) 教程可快速体验PaddleSeg人像分割模型的效果。
+
+### 入门教程
+
+入门教程以经典的U-Net模型为例, 结合Oxford-IIIT宠物数据集，快速熟悉PaddleSeg使用流程, 详情请点击[U-Net宠物分割](https://aistudio.baidu.com/aistudio/projectDetail/102889)。
+
+### 高级教程
+
+高级教程以DeepLabv3+模型为例，结合Cityscapes数据集，快速了解ASPP, Backbone网络切换，多卡Batch Norm同步等策略，详情请点击[DeepLabv3+图像分割](https://aistudio.baidu.com/aistudio/projectDetail/101696)。
+
+### 垂类模型
+
+更多特色垂类分割模型如LIP人体部件分割、人像分割、车道线分割模型可以参考[contrib](./contrib/README.md)
+
+## 使用文档
+
+* [安装说明](./docs/installation.md)
+* [数据准备](./docs/data_prepare.md)
+* [数据增强](./docs/data_aug.md)
+* [预训练模型](./docs/model_zoo.md)
+* [训练/评估/预测(可视化)](./docs/usage.md)
+* [预测库集成](./inference/README.md)
+* [服务端部署](./serving/README.md)
+* [垂类分割模型](./contrib/README.md)
+
+
+## FAQ
+
+#### Q:图像分割的数据增强如何配置，unpadding, step scaling, range scaling的原理是什么？
+
+A:数据增强的配置可以参考文档[数据增强](./docs/data_aug.md)
+
+#### Q: 预测时图片过大，导致显存不足如何处理？
+
+A: 降低Batch size，使用Group Norm策略等。
+
+## 更新日志
+
+### 2019.08.25
+
+#### v0.1.0
+
+* PaddleSeg分割库初始版本发布，包含DeepLabv3+, U-Net, ICNet三类分割模型, 其中DeepLabv3+支持Xception, MobileNet两种可调节的骨干网络。
+* CVPR 19' LIP人体部件分割比赛冠军预测模型发布[ACE2P](./contrib/ACE2P)
+* 预置基于DeepLabv3+网络的[人像分割](./contrib/HumanSeg/)和[车道线分割](./contrib/RoadLine)预测模型发布
+
+## 如何贡献代码
+
+我们非常欢迎您为PaddleSeg贡献代码或者提供使用建议。
diff --git a/configs/cityscape.yaml b/configs/cityscape.yaml
@@ -0,0 +1,56 @@
+EVAL_CROP_SIZE: (2049, 1025) # (width, height), for unpadding rangescaling and stepscaling
+TRAIN_CROP_SIZE: (769, 769) # (width, height), for unpadding rangescaling and stepscaling
+AUG:
+    AUG_METHOD: "stepscaling" # choice unpadding rangescaling and stepscaling
+    FIX_RESIZE_SIZE: (640, 640) # (width, height), for unpadding
+    INF_RESIZE_VALUE: 500  # for rangescaling
+    MAX_RESIZE_VALUE: 600  # for rangescaling
+    MIN_RESIZE_VALUE: 400  # for rangescaling
+    MAX_SCALE_FACTOR: 2.0  # for stepscaling
+    MIN_SCALE_FACTOR: 0.5  # for stepscaling
+    SCALE_STEP_SIZE: 0.25  # for stepscaling
+    MIRROR: True
+    RICH_CROP:
+        ENABLE: False
+        ASPECT_RATIO: 0.33
+        BLUR: True
+        BLUR_RATIO: 0.1
+        FLIP: True
+        FLIP_RATIO: 0.2
+        MAX_ROTATION: 15
+        MIN_AREA_RATIO: 0.5
+        BRIGHTNESS_JITTER_RATIO: 0.5
+        CONTRAST_JITTER_RATIO: 0.5
+        SATURATION_JITTER_RATIO: 0.5
+BATCH_SIZE: 4
+MEAN: [0.5, 0.5, 0.5]
+STD: [0.5, 0.5, 0.5]
+DATASET:
+    DATA_DIR: "./dataset/cityscapes/"
+    IMAGE_TYPE: "rgb"  # choice rgb or rgba
+    NUM_CLASSES: 19
+    TEST_FILE_LIST: "dataset/cityscapes/val.list"
+    TRAIN_FILE_LIST: "dataset/cityscapes/train.list"
+    VAL_FILE_LIST: "dataset/cityscapes/val.list"
+    IGNORE_INDEX: 255
+FREEZE:
+    MODEL_FILENAME: "model"
+    PARAMS_FILENAME: "params"
+MODEL:
+    DEFAULT_NORM_TYPE: "gn"
+    MODEL_NAME: "deeplabv3p"
+    DEEPLAB:
+        ASPP_WITH_SEP_CONV: True
+        DECODER_USE_SEP_CONV: True
+TEST:
+    TEST_MODEL: "snapshots/cityscape_v5/final/"
+TRAIN:
+    MODEL_SAVE_DIR: "snapshots/cityscape_v7/"
+    PRETRAINED_MODEL: u"pretrain/deeplabv3plus_gn_init"
+    RESUME: False
+    SNAPSHOT_EPOCH: 10
+SOLVER:
+    LR: 0.001
+    LR_POLICY: "poly"
+    OPTIMIZER: "sgd"
+    NUM_EPOCHS: 700
diff --git a/configs/coco.yaml b/configs/coco.yaml
@@ -0,0 +1,55 @@
+EVAL_CROP_SIZE: (513, 513) # (width, height), for unpadding rangescaling and stepscaling
+TRAIN_CROP_SIZE: (513, 513) # (width, height), for unpadding rangescaling and stepscaling
+AUG:
+    AUG_METHOD: u"stepscaling" # choice unpadding rangescaling and stepscaling
+    FIX_RESIZE_SIZE: (640, 640) # (width, height), for unpadding
+    INF_RESIZE_VALUE: 500  # for rangescaling
+    MAX_RESIZE_VALUE: 600  # for rangescaling
+    MIN_RESIZE_VALUE: 400  # for rangescaling
+    MAX_SCALE_FACTOR: 2.0  # for stepscaling
+    MIN_SCALE_FACTOR: 0.5  # for stepscaling
+    SCALE_STEP_SIZE: 0.25  # for stepscaling
+    MIRROR: True
+    RICH_CROP:
+        ENABLE: False
+        ASPECT_RATIO: 0.33
+        BLUR: True
+        BLUR_RATIO: 0.1
+        FLIP: True
+        FLIP_RATIO: 0.2
+        MAX_ROTATION: 15
+        MIN_AREA_RATIO: 0.5
+        BRIGHTNESS_JITTER_RATIO: 0.5
+        CONTRAST_JITTER_RATIO: 0.5
+        SATURATION_JITTER_RATIO: 0.5
+BATCH_SIZE: 8
+MEAN: [104.008, 116.669, 122.675]
+STD: [1.0, 1.0, 1.0]
+DATASET:
+    DATA_DIR: "./data/COCO2014/"
+    IMAGE_TYPE: "rgb"  # choice rgb or rgba
+    NUM_CLASSES: 21
+    TEST_FILE_LIST: "data/COCO2014/VOC_ImageSets/val.txt"
+    TRAIN_FILE_LIST: "data/COCO2014/ImageSets/train.txt"
+    VAL_FILE_LIST: "data/COCO2014/VOC_ImageSets/val.txt"
+    SEPARATOR: " "
+    IGNORE_INDEX: 255
+FREEZE:
+    MODEL_FILENAME: "model"
+    PARAMS_FILENAME: "params"
+MODEL:
+    DEFAULT_NORM_TYPE: "bn"
+    MODEL_NAME: "deeplabv3p"
+TEST:
+    TEST_MODEL: "snapshots/coco_v1/final"
+TRAIN:
+    MODEL_SAVE_DIR: "snapshots/coco_v1/"
+    PRETRAINED_MODEL: "pretrain/xception65_pretrained/"
+    RESUME: False
+    SNAPSHOT_EPOCH: 5
+SOLVER:
+    LR: 0.007
+    WEIGHT_DECAY: 0.00004
+    NUM_EPOCHS: 40
+    LR_POLICY: "poly"
+    OPTIMIZER: "SGD"
diff --git a/configs/humanseg.yaml b/configs/humanseg.yaml
@@ -0,0 +1,57 @@
+TRAIN_CROP_SIZE: (513, 513) # (width, height), for unpadding rangescaling and stepscaling
+EVAL_CROP_SIZE: (513, 513) # (width, height), for unpadding rangescaling and stepscaling
+AUG:
+    AUG_METHOD: u"unpadding" # choice unpadding rangescaling and stepscaling
+    FIX_RESIZE_SIZE: (513, 513) # (width, height), for unpadding
+    INF_RESIZE_VALUE: 513  # for rangescaling
+    MAX_RESIZE_VALUE: 400  # for rangescaling
+    MIN_RESIZE_VALUE: 513  # for rangescaling
+    MAX_SCALE_FACTOR: 2.0  # for stepscaling
+    MIN_SCALE_FACTOR: 0.5  # for stepscaling
+    SCALE_STEP_SIZE: 0.25  # for stepscaling
+    MIRROR: True
+    RICH_CROP:
+        ENABLE: True
+        ASPECT_RATIO: 0
+        BLUR: True
+        BLUR_RATIO: 0.1
+        FLIP: True
+        FLIP_RATIO: 0.2
+        MAX_ROTATION: 45
+        MIN_AREA_RATIO: 0
+        BRIGHTNESS_JITTER_RATIO: 0.5
+        CONTRAST_JITTER_RATIO: 0.5
+        SATURATION_JITTER_RATIO: 0.5
+BATCH_SIZE: 24
+MEAN: [104.008, 116.669, 122.675]
+STD: [1.0, 1.0, 1.0]
+DATASET:
+    DATA_DIR: u"./data/humanseg/"
+    IMAGE_TYPE: "rgb"  # choice rgb or rgba
+    NUM_CLASSES: 2
+    TEST_FILE_LIST: u"data/humanseg/list/val.txt"
+    TRAIN_FILE_LIST: u"data/humanseg/list/train.txt"
+    VAL_FILE_LIST: u"data/humanseg/list/val.txt"
+    IGNORE_INDEX: 255
+    SEPARATOR: "|"
+FREEZE:
+    MODEL_FILENAME: u"model"
+    PARAMS_FILENAME: u"params"
+    SAVE_DIR: u"human_freeze_model"
+MODEL:
+    DEFAULT_NORM_TYPE: u"bn"
+    MODEL_NAME: "deeplabv3p"
+    DEEPLAB:
+        BACKBONE: "xception_65"
+TEST:
+    TEST_MODEL: "snapshots/humanseg/aic_v2/final/"
+TRAIN:
+    MODEL_SAVE_DIR: "snapshots/humanseg/aic_v2/"
+    PRETRAINED_MODEL: u"pretrain/xception65_pretrained/"
+    RESUME: False
+    SNAPSHOT_EPOCH: 5
+SOLVER:
+    LR: 0.1
+    NUM_EPOCHS: 40
+    LR_POLICY: "poly"
+    OPTIMIZER: "sgd"
diff --git a/configs/line.yaml b/configs/line.yaml
@@ -0,0 +1,57 @@
+EVAL_CROP_SIZE: (1536, 576) # (width, height), for unpadding rangescaling and stepscaling
+TRAIN_CROP_SIZE: (1536, 576) # (width, height), for unpadding rangescaling and stepscaling
+AUG:
+    AUG_METHOD: u"unpadding" # choice unpadding rangescaling and stepscaling
+    FIX_RESIZE_SIZE: (1536, 576) # (width, height), for unpadding
+    INF_RESIZE_VALUE: 1280  # for rangescaling
+    MAX_RESIZE_VALUE: 1024  # for rangescaling
+    MIN_RESIZE_VALUE: 1536 # for rangescaling
+    MAX_SCALE_FACTOR: 2.0  # for stepscaling
+    MIN_SCALE_FACTOR: 0.5  # for stepscaling
+    SCALE_STEP_SIZE: 0.25  # for stepscaling
+    MIRROR: True
+    RICH_CROP:
+        ENABLE: False
+        ASPECT_RATIO: 0.33
+        BLUR: True
+        BLUR_RATIO: 0.1
+        FLIP: True
+        FLIP_RATIO: 0.2
+        MAX_ROTATION: 15
+        MIN_AREA_RATIO: 0.5
+        BRIGHTNESS_JITTER_RATIO: 0.5
+        CONTRAST_JITTER_RATIO: 0.5
+        SATURATION_JITTER_RATIO: 0.5
+BATCH_SIZE: 1
+MEAN: [127.5, 127.5, 127.5]
+STD: [127.5, 127.5, 127.5]
+DATASET:
+    DATA_DIR: "./data/line/L4_lane_mask_dataset_app/L4_360_0_2class/"
+    IMAGE_TYPE: "rgb"  # choice rgb or rgba
+    NUM_CLASSES: 2
+    TEST_FILE_LIST: "data/line/L4_lane_mask_dataset_app/L4_360_0_2class/val.txt"
+    TRAIN_FILE_LIST: "data/line/L4_lane_mask_dataset_app/L4_360_0_2class/train.txt"
+    VAL_FILE_LIST: "data/line/L4_lane_mask_dataset_app/L4_360_0_2class/val.txt"
+    SEPARATOR: " "
+    IGNORE_INDEX: 255
+FREEZE:
+    MODEL_FILENAME: "__model__"
+    PARAMS_FILENAME: "__params__"
+    SAVE_DIR: "line_freeze_model"
+MODEL:
+    DEFAULT_NORM_TYPE: "bn"
+    MODEL_NAME: "deeplabv3p"
+    DEEPLAB:
+        BACKBONE: "mobilenet"
+TEST:
+    TEST_MODEL: "snapshots/line_v4/final/"
+TRAIN:
+    MODEL_SAVE_DIR: "snapshots/line_v4/"
+    PRETRAINED_MODEL: u"pretrain/MobileNetV2_pretrained/"
+    RESUME: False
+    SNAPSHOT_EPOCH: 10
+SOLVER:
+    LR: 0.01
+    LR_POLICY: "poly"
+    OPTIMIZER: "sgd"
+    NUM_EPOCHS: 40
diff --git a/configs/unet_pet.yaml b/configs/unet_pet.yaml
@@ -0,0 +1,57 @@
+TRAIN_CROP_SIZE: (512, 512) # (width, height), for unpadding rangescaling and stepscaling
+EVAL_CROP_SIZE: (512, 512) # (width, height), for unpadding rangescaling and stepscaling
+AUG:
+    AUG_METHOD: "unpadding" # choice unpadding rangescaling and stepscaling
+    FIX_RESIZE_SIZE: (512, 512) # (width, height), for unpadding
+
+    INF_RESIZE_VALUE: 500  # for rangescaling
+    MAX_RESIZE_VALUE: 600  # for rangescaling
+    MIN_RESIZE_VALUE: 400  # for rangescaling
+
+    MAX_SCALE_FACTOR: 1.25  # for stepscaling
+    MIN_SCALE_FACTOR: 0.75  # for stepscaling
+    SCALE_STEP_SIZE: 0.25  # for stepscaling
+    MIRROR: True
+    RICH_CROP:
+        ENABLE: False
+        ASPECT_RATIO: 0.33
+        BLUR: True
+        BLUR_RATIO: 0.1
+        FLIP: True
+        FLIP_RATIO: 0.2
+        MAX_ROTATION: 15
+        MIN_AREA_RATIO: 0.5
+        BRIGHTNESS_JITTER_RATIO: 0.5
+        CONTRAST_JITTER_RATIO: 0.5
+        SATURATION_JITTER_RATIO: 0.5
+BATCH_SIZE: 4
+MEAN: [104.008, 116.669, 122.675]
+STD: [1.0, 1.0, 1.0]
+DATASET:
+    DATA_DIR: "./dataset/mini_pet/"
+    IMAGE_TYPE: "rgb"  # choice rgb or rgba
+    NUM_CLASSES: 3
+    TEST_FILE_LIST: "./dataset/mini_pet/file_list/test_list.txt"
+    TRAIN_FILE_LIST: "./dataset/mini_pet/file_list/train_list.txt"
+    VAL_FILE_LIST: "./dataset/mini_pet/file_list/val_list.txt"
+    VIS_FILE_LIST: "./dataset/mini_pet/file_list/test_list.txt"
+    IGNORE_INDEX: 255
+    SEPARATOR: " "
+FREEZE:
+    MODEL_FILENAME: "__model__"
+    PARAMS_FILENAME: "__params__"
+MODEL:
+    MODEL_NAME: "unet"
+    DEFAULT_NORM_TYPE: "bn"
+TEST:
+    TEST_MODEL: "./test/saved_model/unet_pet/final/"
+TRAIN:
+    MODEL_SAVE_DIR: "./test/saved_models/unet_pet/"
+    PRETRAINED_MODEL: "./test/models/unet_coco/"
+    RESUME: False
+    SNAPSHOT_EPOCH: 10
+SOLVER:
+    NUM_EPOCHS: 500
+    LR: 0.005
+    LR_POLICY: "poly"
+    OPTIMIZER: "adam"