Merge branch 'master' of https://github.com/PaddlePaddle/PaddleSeg

README.md

@@ -12,31 +12,19 @@ PaddleSeg具备高性能、丰富的数据增强、工业级部署、全流程
 
 - **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。
+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。
+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同步等训练加速策略，结合飞桨核心框架的显存优化算法，可以大幅度减少分割模型的显存开销，更快完成分割模型训练。
+PaddleSeg支持多进程IO、多卡并行、跨卡Batch Norm同步等训练加速策略，结合飞桨核心框架的显存优化功能，可以大幅度减少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。
-
-</br>
-
-## 在线体验
-
-PaddleSeg提供了多种预训练模型，并且以NoteBook的方式提供了在线体验的教程，欢迎体验：
-
-|教程|链接|
-|-|-|
-|U-Net宠物分割|[点击体验](https://aistudio.baidu.com/aistudio/projectDetail/102889)|
-|PaddleSeg人像分割|[点击体验](https://aistudio.baidu.com/aistudio/projectDetail/100798)|
-|DeepLabv3+图像分割|[点击体验](https://aistudio.baidu.com/aistudio/projectDetail/101696)|
+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。
 
 </br>
 
@@ -64,28 +52,39 @@ PaddleSeg提供了多种预训练模型，并且以NoteBook的方式提供了在
 ### 预测部署
 
 * [模型导出](./docs/model_export.md)
-* [预测库使用](./inference)
-* [模型部署与Serving](./serving)
+* [C++预测库使用](./inference)
+* [PaddleSeg Serving服务化部署](./serving)
 
 ### 高级功能
 
 * [PaddleSeg的数据增强](./docs/data_aug.md)
 * [特色垂类模型使用](./contrib)
 
-</br>
 </br>
 
 ## 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)
+A: 更详细数据增强文档可以参考[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。
 
 </br>
+
+## 在线体验
+
+PaddleSeg提供了多种预训练模型，并且以NoteBook的方式提供了在线体验的教程，欢迎体验：
+
+|教程|链接|
+|-|-|
+|U-Net宠物分割|[点击体验](https://aistudio.baidu.com/aistudio/projectDetail/102889)|
+|PaddleSeg人像分割|[点击体验](https://aistudio.baidu.com/aistudio/projectDetail/100798)|
+|DeepLabv3+图像分割|[点击体验](https://aistudio.baidu.com/aistudio/projectDetail/101696)|
+|PaddleSeg特色垂类模型|[点击体验](https://aistudio.baidu.com/aistudio/projectdetail/115541)|
+
 </br>
 
 ## 更新日志
@@ -94,11 +93,10 @@ A: 降低Batch size，使用Group Norm策略等。
 
   **`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)
+  * CVPR19 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
 
 </br>
-</br>
 
 ## 如何贡献代码
 

configs/cityscape.yaml

@@ -10,18 +10,6 @@ AUG:
     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
 DATASET:
     DATA_DIR: "./dataset/cityscapes/"
@@ -44,8 +32,7 @@ TEST:
     TEST_MODEL: "snapshots/cityscape_v5/final/"
 TRAIN:
     MODEL_SAVE_DIR: "snapshots/cityscape_v7/"
-    PRETRAINED_MODEL: u"pretrain/deeplabv3plus_gn_init"
-    RESUME: False
+    PRETRAINED_MODEL_DIR: "pretrain/deeplabv3plus_gn_init"
     SNAPSHOT_EPOCH: 10
 SOLVER:
     LR: 0.001

configs/unet_pet.yaml

@@ -12,18 +12,6 @@ AUG:
     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
 DATASET:
     DATA_DIR: "./dataset/mini_pet/"
@@ -45,8 +33,7 @@ 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
+    PRETRAINED_MODEL_DIR: "./test/models/unet_coco/"
     SNAPSHOT_EPOCH: 10
 SOLVER:
     NUM_EPOCHS: 500

docs/configs/train_group.md

@@ -11,7 +11,7 @@ TRAIN Group存放所有和训练相关的配置
 <br/>
 <br/>
 
-## `PRETRAINED_MODEL`
+## `PRETRAINED_MODEL_DIR`
 预训练模型路径
 
 ## 默认值
@@ -28,19 +28,15 @@ TRAIN Group存放所有和训练相关的配置
 <br/>
 <br/>
 
-## `RESUME`
-是否从预训练模型中恢复参数并继续训练
+## `RESUME_MODEL_DIR`
+从指定路径中恢复参数并继续训练
 
 ## 默认值
-False
+无
 
 ## 注意事项
 
-* 当该字段被置为True且`PRETRAINED_MODEL`不存在时，该选项不生效
-
-* 当该字段被置为True且`PRETRAINED_MODEL`存在时，PaddleSeg会恢复到上一次训练的最近一个epoch，并且恢复训练过程中的临时变量（如已经衰减过的学习率，Optimizer的动量数据等）
-
-* 当该字段被置为True且`PRETRAINED_MODEL`存在时，`PRETRAINED_MODEL`路径的最后一个目录必须为int数值或者字符串final，PaddleSeg会将int数值作为当前起始EPOCH继续训练，若目录为final，则不会继续训练。若目录不满足上述条件，PaddleSeg会抛出错误。
+* 当`RESUME_MODEL_DIR`存在时，PaddleSeg会恢复到上一次训练的最近一个epoch，并且恢复训练过程中的临时变量（如已经衰减过的学习率，Optimizer的动量数据等），`PRETRAINED_MODEL`路径的最后一个目录必须为int数值或者字符串final，PaddleSeg会将int数值作为当前起始EPOCH继续训练，若目录为final，则不会继续训练。若目录不满足上述条件，PaddleSeg会抛出错误。
 
 <br/>
 <br/>
@@ -57,4 +53,4 @@ False
 
 * 仅在GPU多卡训练时该开关有效（Windows不支持多卡训练，因此无需打开该开关）
 
-* GPU多卡训练时，建议开启该开关，可以提升模型的训练效果
\ No newline at end of file
+* GPU多卡训练时，建议开启该开关，可以提升模型的训练效果

docs/data_aug.md

@@ -35,9 +35,6 @@ rich crop是指对图像进行多种变换，保证在训练过程中数据的
 - blur
 图像加模糊，使用开关`AUG.RICH_CROP.BLUR`，为False时该项功能关闭。`AUG.RICH_CROP.BLUR_RATIO`控制加入模糊的概率。
 
-- flip
-图像上下翻转，使用开关`AUG.RICH_CROP.FLIP`，为False时该项功能关闭。`AUG.RICH_CROP.FLIP_RATIO`控制上下翻转的概率。
-
 - rotation
 图像旋转，`AUG.RICH_CROP.MAX_ROTATION`控制最大旋转角度。旋转产生的多余的区域的填充值为均值。
 

docs/model_zoo.md

@@ -4,7 +4,7 @@ PaddleSeg对所有内置的分割模型都提供了公开数据集下的预训
 
 ## ImageNet预训练模型
 
-所有Imagenet预训练模型来自于PaddlePaddle图像分类库，想获取更多细节请点击[这里](https://github.com/PaddlePaddle/models/tree/develop/PaddleCV/image_classification))
+所有Imagenet预训练模型来自于PaddlePaddle图像分类库，想获取更多细节请点击[这里](https://github.com/PaddlePaddle/models/tree/develop/PaddleCV/image_classification)
 
 | 模型 | 数据集合 | Depth multiplier | 下载地址 | Accuray Top1/5 Error|
 |---|---|---|---|---|

docs/usage.md

@@ -76,7 +76,7 @@ python pdseg/train.py --use_gpu \
                       --tb_log_dir train_log \
                       --cfg configs/unet_pet.yaml \
                       BATCH_SIZE 4 \
-                      TRAIN.PRETRAINED_MODEL pretrained_model/unet_bn_coco \
+                      TRAIN.PRETRAINED_MODEL_DIR pretrained_model/unet_bn_coco \
                       TRAIN.SYNC_BATCH_NORM True \
                       SOLVER.LR 5e-5
 ```

pdseg/reader.py

@@ -261,17 +261,18 @@ class SegDataset(object):
                     SATURATION_JITTER_RATIO,
                     contrast_jitter_ratio=cfg.AUG.RICH_CROP.
                     CONTRAST_JITTER_RATIO)
-                if cfg.AUG.RICH_CROP.FLIP:
-                    if cfg.AUG.RICH_CROP.FLIP_RATIO <= 0:
-                        n = 0
-                    elif cfg.AUG.RICH_CROP.FLIP_RATIO >= 1:
-                        n = 1
-                    else:
-                        n = int(1.0 / cfg.AUG.RICH_CROP.FLIP_RATIO)
-                    if n > 0:
-                        if np.random.randint(0, n) == 0:
-                            img = img[::-1, :, :]
-                            grt = grt[::-1, :]
+
+            if cfg.AUG.FLIP:
+                if cfg.AUG.FLIP_RATIO <= 0:
+                    n = 0
+                elif cfg.AUG.FLIP_RATIO >= 1:
+                    n = 1
+                else:
+                    n = int(1.0 / cfg.AUG.FLIP_RATIO)
+                if n > 0:
+                    if np.random.randint(0, n) == 0:
+                        img = img[::-1, :, :]
+                        grt = grt[::-1, :]
 
             if cfg.AUG.MIRROR:
                 if np.random.randint(0, 2) == 1:

pdseg/train.py

@@ -152,15 +152,15 @@ def load_checkpoint(exe, program):
     Load checkpoiont from pretrained model directory for resume training
     """
 
-    print('Resume model training from:', cfg.TRAIN.PRETRAINED_MODEL)
-    if not os.path.exists(cfg.TRAIN.PRETRAINED_MODEL):
+    print('Resume model training from:', cfg.TRAIN.RESUME_MODEL_DIR)
+    if not os.path.exists(cfg.TRAIN.RESUME_MODEL_DIR):
         raise ValueError("TRAIN.PRETRAIN_MODEL {} not exist!".format(
-            cfg.TRAIN.PRETRAINED_MODEL))
+            cfg.TRAIN.RESUME_MODEL_DIR))
 
     fluid.io.load_persistables(
-        exe, cfg.TRAIN.PRETRAINED_MODEL, main_program=program)
+        exe, cfg.TRAIN.RESUME_MODEL_DIR, main_program=program)
 
-    model_path = cfg.TRAIN.PRETRAINED_MODEL
+    model_path = cfg.TRAIN.RESUME_MODEL_DIR
     # Check is path ended by path spearator
     if model_path[-1] == os.sep:
         model_path = model_path[0:-1]
@@ -255,11 +255,11 @@ def train(cfg):
 
     # Resume training
     begin_epoch = cfg.SOLVER.BEGIN_EPOCH
-    if cfg.TRAIN.RESUME:
+    if cfg.TRAIN.RESUME_MODEL_DIR:
         begin_epoch = load_checkpoint(exe, train_prog)
     # Load pretrained model
-    elif os.path.exists(cfg.TRAIN.PRETRAINED_MODEL):
-        print('Pretrained model dir:', cfg.TRAIN.PRETRAINED_MODEL)
+    elif os.path.exists(cfg.TRAIN.PRETRAINED_MODEL_DIR):
+        print('Pretrained model dir:', cfg.TRAIN.PRETRAINED_MODEL_DIR)
         load_vars = []
         load_fail_vars = []
 
@@ -268,10 +268,10 @@ def train(cfg):
             Check whehter persitable variable shape is match with current network
             """
             var_exist = os.path.exists(
-                os.path.join(cfg.TRAIN.PRETRAINED_MODEL, var.name))
+                os.path.join(cfg.TRAIN.PRETRAINED_MODEL_DIR, var.name))
             if var_exist:
                 var_shape = parse_shape_from_file(
-                    os.path.join(cfg.TRAIN.PRETRAINED_MODEL, var.name))
+                    os.path.join(cfg.TRAIN.PRETRAINED_MODEL_DIR, var.name))
                 return var_shape == shape
             return False
 
@@ -285,10 +285,10 @@ def train(cfg):
                     load_fail_vars.append(x)
         if cfg.MODEL.FP16:
             # If open FP16 training mode, load FP16 var separate
-            load_fp16_vars(exe, cfg.TRAIN.PRETRAINED_MODEL, train_prog)
+            load_fp16_vars(exe, cfg.TRAIN.PRETRAINED_MODEL_DIR, train_prog)
         else:
             fluid.io.load_vars(
-                exe, dirname=cfg.TRAIN.PRETRAINED_MODEL, vars=load_vars)
+                exe, dirname=cfg.TRAIN.PRETRAINED_MODEL_DIR, vars=load_vars)
         for var in load_vars:
             print("Parameter[{}] loaded sucessfully!".format(var.name))
         for var in load_fail_vars:
@@ -299,7 +299,7 @@ def train(cfg):
             len(load_vars) + len(load_fail_vars)))
     else:
         print('Pretrained model dir {} not exists, training from scratch...'.
-              format(cfg.TRAIN.PRETRAINED_MODEL))
+              format(cfg.TRAIN.PRETRAINED_MODEL_DIR))
 
     fetch_list = [avg_loss.name, lr.name]
     if args.debug:

pdseg/utils/collect.py

@@ -98,6 +98,16 @@ class SegConfig(dict):
                 'DATASET.IMAGE_TYPE config error, only support `rgb`, `gray` and `rgba`'
             )
 
+        if not self.TRAIN_CROP_SIZE:
+            raise ValueError(
+                'TRAIN_CROP_SIZE is empty! Please set a pair of values in format (width, height)'
+            )
+
+        if not self.EVAL_CROP_SIZE:
+            raise ValueError(
+                'EVAL_CROP_SIZE is empty! Please set a pair of values in format (width, height)'
+            )
+
         if reset_dataset:
             # Ensure file list is use UTF-8 encoding
             train_sets = codecs.open(self.DATASET.TRAIN_FILE_LIST, 'r',

pdseg/utils/config.py

@@ -69,6 +69,10 @@ cfg.DATASET.IGNORE_INDEX = 255
 ########################### 数据增强配置 ######################################
 # 图像镜像左右翻转
 cfg.AUG.MIRROR = True
+# 图像上下翻转开关，True/False
+cfg.AUG.FLIP = False
+# 图像启动上下翻转的概率，0-1
+cfg.AUG.FLIP_RATIO = 0.5
 # 图像resize的固定尺寸（宽，高），非负
 cfg.AUG.FIX_RESIZE_SIZE = tuple()
 # 图像resize的方式有三种：
@@ -107,18 +111,14 @@ cfg.AUG.RICH_CROP.CONTRAST_JITTER_RATIO = 0.5
 cfg.AUG.RICH_CROP.BLUR = False
 # 图像启动模糊百分比，0-1
 cfg.AUG.RICH_CROP.BLUR_RATIO = 0.1
-# 图像上下翻转开关，True/False
-cfg.AUG.RICH_CROP.FLIP = False
-# 图像启动上下翻转的概率，0-1
-cfg.AUG.RICH_CROP.FLIP_RATIO = 0.2
 
 ########################### 训练配置 ##########################################
 # 模型保存路径
 cfg.TRAIN.MODEL_SAVE_DIR = ''
 # 预训练模型路径
-cfg.TRAIN.PRETRAINED_MODEL = ''
+cfg.TRAIN.PRETRAINED_MODEL_DIR = ''
 # 是否resume，继续训练
-cfg.TRAIN.RESUME = False
+cfg.TRAIN.RESUME_MODEL_DIR = ''
 # 是否使用多卡间同步BatchNorm均值和方差
 cfg.TRAIN.SYNC_BATCH_NORM = False
 # 模型参数保存的epoch间隔数，可用来继续训练中断的模型

pretrained_model/download_model.py

@@ -46,7 +46,7 @@ model_urls = {
     "unet_bn_coco": "https://paddleseg.bj.bcebos.com/models/unet_coco_v3.tgz",
 
     # Cityscapes pretrained
-    "deeplabv3plus_mobilenetv2-1-0_bn_cityscapes":
+    "deeplabv3p_mobilenetv2-1-0_bn_cityscapes":
     "https://paddleseg.bj.bcebos.com/models/mobilenet_cityscapes.tgz",
     "deeplabv3p_xception65_gn_cityscapes":
     "https://paddleseg.bj.bcebos.com/models/deeplabv3p_xception65_cityscapes.tgz",

test/configs/deeplabv3p_xception65_cityscapes.yaml

@@ -10,18 +10,6 @@ AUG:
     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
 DATASET:
     DATA_DIR: "./dataset/cityscapes/"
@@ -46,8 +34,7 @@ TEST:
     TEST_MODEL: "snapshots/cityscape_v5/final/"
 TRAIN:
     MODEL_SAVE_DIR: "snapshots/cityscape_v5/"
-    PRETRAINED_MODEL: "pretrain/deeplabv3plus_gn_init"
-    RESUME: False
+    PRETRAINED_MODEL_DIR: "pretrain/deeplabv3plus_gn_init"
     SNAPSHOT_EPOCH: 10
 SOLVER:
     LR: 0.001

test/configs/unet_pet.yaml

@@ -12,18 +12,6 @@ AUG:
     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: 6
 DATASET:
     DATA_DIR: "./dataset/pet/"
@@ -45,8 +33,7 @@ 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
+    PRETRAINED_MODEL_DIR: "./test/models/unet_coco/"
     SNAPSHOT_EPOCH: 10
 SOLVER:
     NUM_EPOCHS: 500

test/local_test_cityscapes.py

@@ -45,7 +45,8 @@ if __name__ == "__main__":
     saved_model = os.path.join(LOCAL_PATH, "saved_model", model_name)
 
     parser = argparse.ArgumentParser(description="PaddleSeg loacl test")
-    parser.add_argument("--devices",
+    parser.add_argument(
+        "--devices",
         dest="devices",
         help="GPU id of running. if more than one, use spacing to separate.",
         nargs="+",
@@ -75,7 +76,7 @@ if __name__ == "__main__":
     train(
         flags=["--cfg", cfg, "--use_gpu", "--log_steps", "10"],
         options=[
-            "SOLVER.NUM_EPOCHS", "1", "TRAIN.PRETRAINED_MODEL", test_model,
+            "SOLVER.NUM_EPOCHS", "1", "TRAIN.PRETRAINED_MODEL_DIR", test_model,
             "TRAIN.MODEL_SAVE_DIR", saved_model
         ],
         devices=devices)

test/local_test_pet.py

@@ -46,7 +46,8 @@ if __name__ == "__main__":
     saved_model = os.path.join(LOCAL_PATH, "saved_model", model_name)
 
     parser = argparse.ArgumentParser(description="PaddleSeg loacl test")
-    parser.add_argument("--devices",
+    parser.add_argument(
+        "--devices",
         dest="devices",
         help="GPU id of running. if more than one, use spacing to separate.",
         nargs="+",
@@ -59,7 +60,7 @@ if __name__ == "__main__":
     train(
         flags=["--cfg", cfg, "--use_gpu", "--log_steps", "10"],
         options=[
-            "SOLVER.NUM_EPOCHS", "1", "TRAIN.PRETRAINED_MODEL", test_model,
+            "SOLVER.NUM_EPOCHS", "1", "TRAIN.PRETRAINED_MODEL_DIR", test_model,
             "TRAIN.MODEL_SAVE_DIR", saved_model, "DATASET.TRAIN_FILE_LIST",
             os.path.join(DATASET_PATH, "mini_pet", "file_list",
                          "train_list.txt"), "DATASET.VAL_FILE_LIST",

test/test_utils.py

@@ -84,7 +84,7 @@ def _uncompress_file(filepath, extrapath, delete_file, print_progress):
     else:
         handler = functools.partial(_uncompress_file_tar, mode="r")
 
-    for total_num, index in handler(filepath, extrapath):
+    for total_num, index, rootpath in handler(filepath, extrapath):
         if print_progress:
             done = int(50 * float(index) / total_num)
             progress(
@@ -95,27 +95,31 @@ def _uncompress_file(filepath, extrapath, delete_file, print_progress):
     if delete_file:
         os.remove(filepath)
 
+    return rootpath
+
 
 def _uncompress_file_zip(filepath, extrapath):
     files = zipfile.ZipFile(filepath, 'r')
     filelist = files.namelist()
+    rootpath = filelist[0]
     total_num = len(filelist)
     for index, file in enumerate(filelist):
         files.extract(file, extrapath)
-        yield total_num, index
+        yield total_num, index, rootpath
     files.close()
-    yield total_num, index
+    yield total_num, index, rootpath
 
 
 def _uncompress_file_tar(filepath, extrapath, mode="r:gz"):
     files = tarfile.open(filepath, mode)
     filelist = files.getnames()
     total_num = len(filelist)
+    rootpath = filelist[0]
     for index, file in enumerate(filelist):
         files.extract(file, extrapath)
-        yield total_num, index
+        yield total_num, index, rootpath
     files.close()
-    yield total_num, index
+    yield total_num, index, rootpath
 
 
 def download_file_and_uncompress(url,
@@ -150,7 +154,9 @@ def download_file_and_uncompress(url,
         if not os.path.exists(savename):
             if not os.path.exists(savepath):
                 _download_file(url, savepath, print_progress)
-            _uncompress_file(savepath, extrapath, delete_file, print_progress)
+            savename = _uncompress_file(savepath, extrapath, delete_file,
+                                        print_progress)
+            savename = os.path.join(extrapath, savename)
         shutil.move(savename, extraname)
 
 

turtorial/finetune_deeplabv3plus.md

@@ -67,7 +67,7 @@ MODEL:
     DEEPLAB:
         BACKBONE: "xception_65"
 TRAIN:
-    PRETRAINED_MODEL: "./pretrained_model/deeplabv3p_xception65_bn_pet/"
+    PRETRAINED_MODEL_DIR: "./pretrained_model/deeplabv3p_xception65_bn_pet/"
 
 
 # 其他配置
@@ -79,7 +79,6 @@ AUG:
 BATCH_SIZE: 4
 TRAIN:
     MODEL_SAVE_DIR: "./finetune/deeplabv3p_xception65_bn_pet/"
-    RESUME: False
     SNAPSHOT_EPOCH: 10
 TEST:
     TEST_MODEL: "./finetune/deeplabv3p_xception65_bn_pet/final"
@@ -128,6 +127,6 @@ python pdseg/eval.py --use_gpu --cfg ./configs/test_pet.yaml
 |xception65_imagenet|-|bn|ImageNet|MODEL.MODEL_NAME: deeplabv3p <br> MODEL.DEEPLAB.BACKBONE: xception_65 <br> MODEL.DEFAULT_NORM_TYPE: bn|
 |deeplabv3p_mobilnetv2-1-0_bn_coco|MobileNet V2|bn|COCO|MODEL.MODEL_NAME: deeplabv3p <br> MODEL.DEEPLAB.BACKBONE: mobilenet <br> MODEL.DEEPLAB.DEPTH_MULTIPLIER: 1.0 <br> MODEL.DEFAULT_NORM_TYPE: bn|
 |deeplabv3p_xception65_bn_coco|Xception|bn|COCO|MODEL.MODEL_NAME: deeplabv3p <br> MODEL.DEEPLAB.BACKBONE: xception_65 <br> MODEL.DEFAULT_NORM_TYPE: bn |
-|deeplabv3p_mobilnetv2-1-0_bn_cityscapes|MobileNet V2|bn|Cityscapes|MODEL.MODEL_NAME: deeplabv3p <br> MODEL.DEEPLAB.BACKBONE: xception_65 <br> MODEL.DEFAULT_NORM_TYPE: bn|
+|deeplabv3p_mobilnetv2-1-0_bn_cityscapes|MobileNet V2|bn|Cityscapes|MODEL.MODEL_NAME: deeplabv3p <br> MODEL.DEEPLAB.BACKBONE: mobilenet <br> MODEL.DEEPLAB.DEPTH_MULTIPLIER: 1.0 <br> MODEL.DEEPLAB.ENCODER_WITH_ASPP: False <br> MODEL.DEEPLAB.ENABLE_DECODER: False <br> MODEL.DEFAULT_NORM_TYPE: bn|
 |deeplabv3p_xception65_gn_cityscapes|Xception|gn|Cityscapes|MODEL.MODEL_NAME: deeplabv3p <br>  MODEL.DEEPLAB.BACKBONE: xception_65 <br> MODEL.DEFAULT_NORM_TYPE: gn|
-|**deeplabv3p_xception65_bn_cityscapes**|Xception|bn|Cityscapes||
+|**deeplabv3p_xception65_bn_cityscapes**|Xception|bn|Cityscapes|MODEL.MODEL_NAME: deeplabv3p <br> MODEL.DEEPLAB.BACKBONE: xception_65 <br> MODEL.DEFAULT_NORM_TYPE: bn|

turtorial/finetune_icnet.md

@@ -64,8 +64,9 @@ DATASET:
 MODEL:
     MODEL_NAME: "icnet"
     DEFAULT_NORM_TYPE: "bn"
+    MULTI_LOSS_WEIGHT: "[1.0, 0.4, 0.16]"
 TRAIN:
-    PRETRAINED_MODEL: "./pretrained_model/icnet_bn_cityscapes/"
+    PRETRAINED_MODEL_DIR: "./pretrained_model/icnet_bn_cityscapes/"
 
 
 # 其他配置
@@ -77,7 +78,6 @@ AUG:
 BATCH_SIZE: 4
 TRAIN:
     MODEL_SAVE_DIR: "./finetune/icnet_pet/"
-    RESUME: False
     SNAPSHOT_EPOCH: 10
 TEST:
     TEST_MODEL: "./finetune/icnet_pet/final"
@@ -117,4 +117,4 @@ python pdseg/eval.py --use_gpu --cfg ./configs/test_pet.yaml
 
 |预训练模型名称|BackBone|Norm|数据集|配置|
 |-|-|-|-|-|
-|icnet_bn_cityscapes|-|bn|Cityscapes|MODEL.MODEL_NAME: icnet <br> MODEL.DEFAULT_NORM_TYPE: bn|
+|icnet_bn_cityscapes|-|bn|Cityscapes|MODEL.MODEL_NAME: icnet <br> MODEL.DEFAULT_NORM_TYPE: bn <br> MULTI_LOSS_WEIGHT: [1.0, 0.4, 0.16]|

turtorial/finetune_unet.md

@@ -65,7 +65,7 @@ MODEL:
     MODEL_NAME: "unet"
     DEFAULT_NORM_TYPE: "bn"
 TRAIN:
-    PRETRAINED_MODEL: "./pretrained_model/unet_bn_coco/"
+    PRETRAINED_MODEL_DIR: "./pretrained_model/unet_bn_coco/"
 
 
 # 其他配置
@@ -77,7 +77,6 @@ AUG:
 BATCH_SIZE: 4
 TRAIN:
     MODEL_SAVE_DIR: "./finetune/unet_pet/"
-    RESUME: False
     SNAPSHOT_EPOCH: 10
 TEST:
     TEST_MODEL: "./finetune/unet_pet/final"