Merge pull request PaddlePaddle#2 from Bobholamovic/unittest

[Test] Add Unittests

.github/workflows/build_and_test.yaml

@@ -0,0 +1,81 @@
+name: build and test
+
+on:
+  push:
+    branches:
+      - develop
+      - "tests/**"
+    paths-ignore:
+      - "docs/**"
+      - "README.md"
+  pull_request:
+    branches:
+      - develop
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  build_and_test_cpu:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ubuntu-latest, windows-latest]
+        python-version: ["3.7", "3.8"]
+        include:
+          - python-version: "3.7"
+            os: windows-latest
+            gdal-whl-url: https://download.lfd.uci.edu/pythonlibs/archived/cp37/GDAL-3.3.3-cp37-cp37m-win_amd64.whl
+          - python-version: "3.7"
+            os: ubuntu-latest
+            gdal-whl-url: https://versaweb.dl.sourceforge.net/project/gdal-wheels-for-linux/GDAL-3.4.1-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.whl
+          - python-version: "3.8"
+            os: windows-latest
+            gdal-whl-url: https://download.lfd.uci.edu/pythonlibs/archived/GDAL-3.3.3-cp38-cp38-win_amd64.whl
+          - python-version: "3.8"
+            os: ubuntu-latest
+            gdal-whl-url: https://versaweb.dl.sourceforge.net/project/gdal-wheels-for-linux/GDAL-3.4.1-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.whl
+      fail-fast: false
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Upgrade pip
+        run: python -m pip install pip --upgrade --user
+      - name: Install PaddlePaddle
+        run: python -m pip install paddlepaddle==2.3.1 -i https://mirror.baidu.com/pypi/simple
+      - name: Install PaddleRS
+        run: |
+          python -m pip install -r requirements.txt
+          python -m pip install -e .
+      - name: Install GDAL
+        run: python -m pip install ${{ matrix.gdal-whl-url }}
+      - name: Run unittests
+        run: |
+          cd tests
+          bash run_fast_tests.sh
+        shell: bash
+
+  build_and_test_cuda102:
+    runs-on: ubuntu-18.04
+    container:
+      image: registry.baidubce.com/paddlepaddle/paddle:2.3.1-gpu-cuda10.2-cudnn7
+    steps:
+      - uses: actions/checkout@v3
+      - name: Upgrade pip
+        run: python3.7 -m pip install pip --upgrade --user
+      - name: Install PaddleRS
+        run: |
+          python3.7 -m pip install -r requirements.txt
+          python3.7 -m pip install -e .
+      - name: Install GDAL
+        run: python3.7 -m pip install https://versaweb.dl.sourceforge.net/project/gdal-wheels-for-linux/GDAL-3.4.1-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.whl
+      # Do not run unittests, because there is NO GPU in the machine.
+      # - name: Run unittests
+      #   run: |
+      #     cd tests
+      #     bash run_fast_tests.sh
+      #   shell: bash

.github/workflows/lint.yaml

@@ -0,0 +1,25 @@
+name: lint
+
+on: [push, pull_request]
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python 3.7
+        uses: actions/setup-python@v4
+        with:
+          python-version: 3.7
+      - name: Upgrade pip
+        run: python -m pip install pip --upgrade --user
+      - name: Install pre-commit hooks
+        run: |
+          pip install pre-commit
+          pre-commit install
+      - name: Lint
+        run: pre-commit run --all-files

README.md

@@ -6,9 +6,9 @@
 
   **基于飞桨框架开发的高性能遥感图像处理开发套件，端到端地完成从训练到部署的全流程遥感深度学习应用。**
 
-  <!-- [![Build Status](https://travis-ci.org/PaddleCV-SIG/PaddleRS.svg?branch=release/0.1)](https://travis-ci.org/PaddleCV-SIG/PaddleRS) -->
-  <!-- [![Version](https://img.shields.io/github/release/PaddleCV-SIG/PaddleRS.svg)](https://github.com/PaddleCV-SIG/PaddleRS/releases) -->
-  [![License](https://img.shields.io/badge/license-Apache%202-blue.svg)](LICENSE)
+  <!-- [![version](https://img.shields.io/github/release/PaddleCV-SIG/PaddleRS.svg)](https://github.com/PaddleCV-SIG/PaddleRS/releases) -->
+  [![license](https://img.shields.io/badge/license-Apache%202-blue.svg)](LICENSE)
+  [![build status](https://github.com/PaddleCV-SIG/PaddleRS/workflows/build_and_test.yaml/badge.svg?branch=develop)](https://github.com/PaddleCV-SIG/PaddleRS/actions)
   ![python version](https://img.shields.io/badge/python-3.7+-orange.svg)
   ![support os](https://img.shields.io/badge/os-linux%2C%20win%2C%20mac-yellow.svg)
 </div>
@@ -92,21 +92,21 @@ PaddleRS是遥感科研院所、相关高校共同基于飞桨开发的遥感处
           <li>ResizeByShort</li>
           <li>RandomResizeByShort</li>
           <li>ResizeByLong</li>  
-          <li>RandomFlipOrRotation</li> 
+          <li>RandomFlipOrRotate</li>
           <li>RandomHorizontalFlip</li>  
           <li>RandomVerticalFlip</li>
           <li>Normalize</li>
           <li>CenterCrop</li>
           <li>RandomCrop</li>
           <li>RandomScaleAspect</li>  
           <li>RandomExpand</li>
-          <li>Padding</li>
+          <li>Pad</li>
           <li>MixupImage</li>  
           <li>RandomDistort</li>  
           <li>RandomBlur</li>  
-          <li>Defogging</li>  
-          <li>DimReducing</li>  
-          <li>BandSelecting</li>  
+          <li>Dehaze</li>  
+          <li>ReduceDim</li>  
+          <li>SelectBand</li>  
           <li>RandomSwap</li>
         </ul>  
       </td>
@@ -223,4 +223,3 @@ PaddleRS是遥感科研院所、相关高校共同基于飞桨开发的遥感处
     year={2022}
 }
 ```
-

deploy/export/README.md

@@ -60,4 +60,3 @@ python deploy/export_model.py --model_dir=./output/deeplabv3p/best_model/ --save
 - 对于检测模型中的YOLO/PPYOLO系列模型，请保证输入影像的`w`和`h`有相同取值、且均为32的倍数；指定`--fixed_input_shape`时，R-CNN模型的`w`和`h`也均需为32的倍数。
 - 指定`[w,h]`时，请使用半角逗号（`,`）分隔`w`和`h`，二者之间不允许存在空格等其它字符。
 - 将`w`和`h`设得越大，则模型在推理过程中的耗时和内存/显存占用越高。不过，如果`w`和`h`过小，则可能对模型的精度存在较大负面影响。
-- 对于变化检测模型BIT，请保证指定`--fixed_input_shape`，并且数值不包含负数，因为BIT用到空间注意力，需要从tensor中获取`b,c,h,w`的属性，若为负数则报错。

deploy/export/export_model.py

@@ -21,9 +21,23 @@
 
 def get_parser():
     parser = argparse.ArgumentParser()
-    parser.add_argument('--model_dir', '-m', type=str, default=None, help='model directory path')
-    parser.add_argument('--save_dir', '-s', type=str, default=None, help='path to save inference model')
-    parser.add_argument('--fixed_input_shape', '-fs', type=str, default=None,
+    parser.add_argument(
+        '--model_dir',
+        '-m',
+        type=str,
+        default=None,
+        help='model directory path')
+    parser.add_argument(
+        '--save_dir',
+        '-s',
+        type=str,
+        default=None,
+        help='path to save inference model')
+    parser.add_argument(
+        '--fixed_input_shape',
+        '-fs',
+        type=str,
+        default=None,
         help="export inference model with fixed input shape: [w,h] or [n,c,w,h]")
     return parser
 
@@ -39,13 +53,17 @@ def get_parser():
         fixed_input_shape = literal_eval(args.fixed_input_shape)
         # Check validaty
         if not isinstance(fixed_input_shape, list):
-            raise ValueError("fixed_input_shape should be of None or list type.")
+            raise ValueError(
+                "fixed_input_shape should be of None or list type.")
         if len(fixed_input_shape) not in (2, 4):
-            raise ValueError("fixed_input_shape contains an incorrect number of elements.")
+            raise ValueError(
+                "fixed_input_shape contains an incorrect number of elements.")
         if fixed_input_shape[-1] <= 0 or fixed_input_shape[-2] <= 0:
-            raise ValueError("the input width and height must be positive integers.")
-        if len(fixed_input_shape)==4 and fixed_input_shape[1] <= 0:
-            raise ValueError("the number of input channels must be a positive integer.")
+            raise ValueError(
+                "Input width and height must be positive integers.")
+        if len(fixed_input_shape) == 4 and fixed_input_shape[1] <= 0:
+            raise ValueError(
+                "The number of input channels must be a positive integer.")
 
     # Set environment variables
     os.environ['PADDLEX_EXPORT_STAGE'] = 'True'
@@ -56,4 +74,4 @@ def get_parser():
 
     # Do dynamic-to-static cast
     # XXX: Invoke a protected (single underscore) method outside of subclasses.
-    model._export_inference_model(args.save_dir, fixed_input_shape)
+    model._export_inference_model(args.save_dir, fixed_input_shape)

docs/README.md

@@ -1,5 +1,3 @@
-PaddleSeg commit fec42fd869b6f796c74cd510671595e3512bc8e9
-
 # 开发规范
 请注意，paddlers/models/ppxxx系列除了修改import路径和支持多通道模型外，不要增删改任何代码。
-新增的模型需放在paddlers/models/下的seg、det、cls、cd目录下。
+新增的模型需放在paddlers/models/下的seg、det、cls、cd目录下。

docs/apis/model_zoo.md

@@ -4,18 +4,18 @@ PaddleRS的基础模型库来自[PaddleClas](https://github.com/PaddlePaddle/Pad
 
 ## 自定义模型库
 
-| 模型名称        | 用途     | 
-| --------------- | -------- | 
+| 模型名称        | 用途     |
+| --------------- | -------- |
 | FarSeg          | 语义分割 |
 | BIT             | 变化检测 |
 | CDNet           | 变化检测 |
 | DSIFN           | 变化检测 |
 | STANet          | 变化检测 |
-| SNUNet          | 变化检测 | 
+| SNUNet          | 变化检测 |
 | DSAMNet         | 变化检测 |
-| FCEarlyFusion | 变化检测 | 
-| FCSiamConc    | 变化检测 | 
-| FCSiamDiff    | 变化检测 | 
+| FCEarlyFusion | 变化检测 |
+| FCSiamConc    | 变化检测 |
+| FCSiamDiff    | 变化检测 |
 
 
 ## 如何导入

docs/apis/transforms.md

@@ -1,6 +1,6 @@
 # 数据增强
 
-PaddleRS将多种任务需要的数据增强进行了有机整合，均通过`Compose`进行使用，数据读取方面通过`ImgDecoder`可以对不只三通道RGB图像进行读取，还可以对SAR以及多通道图像进行读取，提供有转为`uint8`的选项。此外提供以下数据增强的方法。
+PaddleRS将多种任务需要的数据增强进行了有机整合，均通过`Compose`进行使用，数据读取方面通过`DecodeImg`可以对不只三通道RGB图像进行读取，还可以对SAR以及多通道图像进行读取，提供有转为`uint8`的选项。此外提供以下数据增强的方法。
 
 | 数据增强名称         | 用途                                            | 任务     | ...  |
 | -------------------- | ----------------------------------------------- | -------- | ---- |
@@ -16,13 +16,13 @@ PaddleRS将多种任务需要的数据增强进行了有机整合，均通过`Co
 | RandomCrop           | 对输入进行随机中心裁剪                          | 所有     | ...  |
 | RandomScaleAspect    | 裁剪输入并重新调整大小至原始大小                | 所有     | ...  |
 | RandomExpand         | 通过根据随机偏移填充来随机扩展输入              | 所有     | ...  |
-| Padding              | 将输入填充到指定的大小                          | 所有     | ...  |
+| Pad              | 将输入填充到指定的大小                          | 所有     | ...  |
 | MixupImage           | 将两张图片和它们的`gt_bbbox/gt_score`混合在一起 | 目标检测 | ...  |
 | RandomDistort        | 对输入进行随机色彩变换                          | 所有     | ...  |
 | RandomBlur           | 对输入进行随机模糊                              | 所有     | ...  |
-| Defogging            | 对输入图像进行去雾                              | 所有     | ...  |
-| DimReducing          | 对输入图像进行降维                              | 所有     | ...  |
-| BandSelecting        | 选择输入图像的波段                              | 所有     | ...  |
+| Dehaze            | 对输入图像进行去雾                              | 所有     | ...  |
+| ReduceDim          | 对输入图像进行降维                              | 所有     | ...  |
+| SelectBand        | 选择输入图像的波段                              | 所有     | ...  |
 | RandomSwap           | 随机交换两个输入图像                            | 变化检测 | ...  |
 | ...                  | ...                                             |          | ...  |
 

docs/data/coco_tools_cn.md

@@ -85,7 +85,7 @@ Args_show = True
 
 ------------------------------------------------Info------------------------------------------------
 json read...
-json keys: dict_keys(['info', 'licenses', 'images', 'annotations', 'categories']) 
+json keys: dict_keys(['info', 'licenses', 'images', 'annotations', 'categories'])
 
 ***********************info***********************
  Content Type: dict
@@ -409,7 +409,7 @@ Args_show = True
 
 ------------------------------------------------Info------------------------------------------------
 json read...
-json keys: dict_keys(['images', 'categories']) 
+json keys: dict_keys(['images', 'categories'])
 
 **********************images**********************
  Content Type: list

docs/data/dataset_summary.md

@@ -215,4 +215,4 @@
 | [9-5](https://aistudio.baidu.com/aistudio/datasetdetail/136567) | [WHU TCL SatMVS 1.0](http://gpcv.whu.edu.cn/data/whu_tlc.html) | 图像生成   | 5120 * 5120                            | 1         | 300      | __     | tif, jpg | __              | 2.1m, 2.5m         | __           | 卫星影像           | ZY3                                                  | 2021     | 武汉大学                                                  | http://gpcv.whu.edu.cn/data/whu_tlc.html                     | https://aistudio.baidu.com/aistudio/datasetdetail/136567 |
 | [9-6](https://aistudio.baidu.com/aistudio/datasetdetail/136567) | [WHU TCL SatMVS 2.0](http://gpcv.whu.edu.cn/data/whu_tlc.html) | 图像生成   | 768 * 384                              | 1         | 5011     | __     | tif      | __              | 2.1m, 2.5m         | __           | 卫星影像           | ZY3                                                  | 2021     | 武汉大学                                                  | http://gpcv.whu.edu.cn/data/whu_tlc.html                     | https://aistudio.baidu.com/aistudio/datasetdetail/136567 |
 | 9-7                                                          | [DLR-ACD](https://www.dlr.de/eoc/en/desktopdefault.aspx/tabid-12760/22294_read-58354/) | 图像生成   | 3619 * 5226                            | 3         | 33       | 1      | __       | __              | 0.045~ 0.15m       | __           | 航拍影像           | 航拍影像                                             | 2019     | German Aerospace Center                                   | https://www.dlr.de/eoc/en/desktopdefault.aspx/tabid-12760/22294_read-58354/ |                                                          |
-| 9-8                                                          | [SEN12MS-CR](https://mediatum.ub.tum.de/1554803)             | 图像生成   | 256 * 256                              | 13, 2     | 122218   | __     | __       | __              | __                 | __           | 卫星影像           | Sentinel1, Sentinel2                                 | 2020     | TUM                                                       | https://mediatum.ub.tum.de/1554803                           |                                                          |
+| 9-8                                                          | [SEN12MS-CR](https://mediatum.ub.tum.de/1554803)             | 图像生成   | 256 * 256                              | 13, 2     | 122218   | __     | __       | __              | __                 | __           | 卫星影像           | Sentinel1, Sentinel2                                 | 2020     | TUM                                                       | https://mediatum.ub.tum.de/1554803                           |                                                          |

docs/quick_start.md

@@ -39,4 +39,4 @@ python -m paddle.distributed.launch --gpus 0,1 tutorials/train/semantic_segmenta
 visualdl --logdir output/deeplabv3p_resnet50_multi_channel/vdl_log --port 8001
 ```
 
-服务启动后，使用浏览器打开 https://0.0.0.0:8001 或 https://localhost:8001
+服务启动后，使用浏览器打开 https://0.0.0.0:8001 或 https://localhost:8001

paddlers/__init__.py

@@ -21,4 +21,4 @@
 
 log_level = 2
 
-from . import tasks, datasets, transforms, utils, tools, models, deploy
+from . import tasks, datasets, transforms, utils, tools, models, deploy

paddlers/custom_models/__init__.py

@@ -12,4 +12,4 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from . import cls, det, seg, gan, cd
+from . import cls, det, seg, gan, cd

paddlers/custom_models/cd/backbones/__init__.py

@@ -10,4 +10,4 @@
 # distributed under the License is distributed on an "AS IS" BASIS,
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
-# limitations under the License.
+# limitations under the License.

paddlers/custom_models/cd/bit.py

@@ -22,6 +22,15 @@
 from .param_init import KaimingInitMixin
 
 
+def calc_product(*args):
+    if len(args) < 1:
+        raise ValueError
+    ret = args[0]
+    for arg in args[1:]:
+        ret *= arg
+    return ret
+
+
 class BIT(nn.Layer):
     """
     The BIT implementation based on PaddlePaddle.
@@ -131,9 +140,10 @@ def __init__(self,
     def _get_semantic_tokens(self, x):
         b, c = x.shape[:2]
         att_map = self.conv_att(x)
-        att_map = att_map.reshape((b, self.token_len, 1, -1))
+        att_map = att_map.reshape(
+            (b, self.token_len, 1, calc_product(*att_map.shape[2:])))
         att_map = F.softmax(att_map, axis=-1)
-        x = x.reshape((b, 1, c, -1))
+        x = x.reshape((b, 1, c, att_map.shape[-1]))
         tokens = (x * att_map).sum(-1)
         return tokens
 
@@ -172,7 +182,7 @@ def forward(self, t1, t2):
         else:
             token1 = self._get_reshaped_tokens(x1)
             token2 = self._get_reshaped_tokens(x2)
-            
+
         # Transformer encoder forward
         token = paddle.concat([token1, token2], axis=1)
         token = self.encode(token)
@@ -253,6 +263,7 @@ def __init__(self,
 
         inner_dim = head_dim * n_heads
         self.n_heads = n_heads
+        self.head_dim = head_dim
         self.scale = dim**-0.5
 
         self.apply_softmax = apply_softmax
@@ -272,9 +283,10 @@ def forward(self, x, ref):
         k = self.fc_k(ref)
         v = self.fc_v(ref)
 
-        q = q.reshape((b, n, h, -1)).transpose((0, 2, 1, 3))
-        k = k.reshape((b, paddle.shape(ref)[1], h, -1)).transpose((0, 2, 1, 3))
-        v = v.reshape((b, paddle.shape(ref)[1], h, -1)).transpose((0, 2, 1, 3))
+        q = q.reshape((b, n, h, self.head_dim)).transpose((0, 2, 1, 3))
+        rn = ref.shape[1]
+        k = k.reshape((b, rn, h, self.head_dim)).transpose((0, 2, 1, 3))
+        v = v.reshape((b, rn, h, self.head_dim)).transpose((0, 2, 1, 3))
 
         mult = paddle.matmul(q, k, transpose_y=True) * self.scale