Add Colab Tutorial (#7)

* add badge

* Created using Colaboratory

* add read docs

* Fixed readthedocs

* fixed colab ref

* add readthedocs.txt

* add link

* fixed modelzoo link

* add missing reference

* fixed docs

* remove relative path in docs

* add colab in README.md

* update docker image

* add newline

* fixed br

.readthedocs.yml

@@ -0,0 +1,7 @@
+version: 2
+
+python:
+    version: 3.7
+    install:
+      - requirements: requirements/docs.txt
+      - requirements: requirements/readthedocs.txt

README.md

@@ -1,6 +1,14 @@
 <div align="center">
   <img src="resources/mmseg-logo.png" width="600"/>
 </div>
+<br />
+
+[![docs](https://img.shields.io/badge/docs-latest-blue)](https://mmsegmentation.readthedocs.io/en/latest/)
+[![badge](https://github.com/open-mmlab/mmsegmentation/workflows/build/badge.svg)](https://github.com/open-mmlab/mmsegmentation/actions)
+[![codecov](https://codecov.io/gh/open-mmlab/mmsegmentation/branch/master/graph/badge.svg)](https://codecov.io/gh/open-mmlab/mmsegmentation)
+[![license](https://img.shields.io/github/license/open-mmlab/mmsegmentation.svg)](https://github.com/open-mmlab/mmsegmentation/blob/master/LICENSE)
+
+Documentation: https://mmsegmentation.readthedocs.io/
 
 ## Introduction
 
@@ -50,6 +58,7 @@ Supported methods:
 - [x] [DeepLabV3+](configs/deeplabv3plus)
 - [x] [UPerNet](configs/upernet)
 - [x] [NonLocal Net](configs/nonlocal_net)
+- [x] [EncNet](configs/encnet)
 - [x] [CCNet](configs/ccnet)
 - [x] [DANet](configs/danet)
 - [x] [GCNet](configs/gcnet)
@@ -65,6 +74,8 @@ Please refer to [INSTALL.md](docs/install.md) for installation and dataset prepa
 Please see [getting_started.md](docs/getting_started.md) for the basic usage of MMSegmentation.
 There are also tutorials for [adding new dataset](docs/tutorials/new_dataset.md), [designing data pipeline](docs/tutorials/data_pipeline.md), and [adding new modules](docs/tutorials/new_modules.md).
 
+A Colab tutorial is also provided. You may preview the notebook [here](demo/MMSegmentation_Tutorial.ipynb) or directly [run](https://colab.research.google.com/github/open-mmlab/mmsegmentation/blob/master/demo/MMSegmentation_Tutorial.ipynb) on Colab.
+
 ## Contributing
 
 We appreciate all contributions to improve MMSegmentation. Please refer to [CONTRIBUTING.md](.github/CONTRIBUTING.md) for the contributing guideline.

docker/Dockerfile

@@ -1,4 +1,4 @@
-ARG PYTORCH="1.3"
+ARG PYTORCH="1.5"
 ARG CUDA="10.1"
 ARG CUDNN="7"
 
@@ -14,7 +14,8 @@ RUN apt-get update && apt-get install -y libglib2.0-0 libsm6 libxrender-dev libx
 
 # Install mmsegmentation
 RUN conda clean --all
+RUN pip install mmcv-full==latest+torch1.5.0+cu101 -f https://openmmlab.oss-accelerate.aliyuncs.com/mmcv/dist/index.html
 RUN git clone https://github.com/open-mmlab/mmsegmenation.git /mmsegmentation
 WORKDIR /mmsegmentation
-ENV FORCE_CUDA="1"
+RUN pip install -r requirements/build.txt
 RUN pip install --no-cache-dir -e .

docs/getting_started.md

@@ -45,7 +45,7 @@ mmsegmentation
 The data could be found [here](https://www.cityscapes-dataset.com/downloads/) after registration.
 
 By convention, `**labelTrainIds.png` are used for cityscapes training.
-We provided a [scripts](../tools/convert_datasets/cityscapes.py) based on [cityscapesscripts](https://github.com/mcordts/cityscapesScripts)
+We provided a [scripts](https://github.com/open-mmlab/mmsegmentation/blob/master/tools/convert_datasets/cityscapes.py) based on [cityscapesscripts](https://github.com/mcordts/cityscapesScripts)
 to generate `**labelTrainIds.png`.
 ```shell
 # --nproc means 8 process for conversion, which could be omitted as well.
@@ -62,7 +62,7 @@ If you would like to use augmented VOC dataset, please run following command to
 python tools/convert_datasets/voc_aug.py data/VOCdevkit data/VOCdevkit/VOCaug --nproc 8
 ```
 
-Please refer to [concat dataset](tutorials/new_dataset.md#concatenate-dataset) for details about how to concatenate them and train them together.
+Please refer to [concat dataset](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/tutorials/new_dataset.md#concatenate-dataset) for details about how to concatenate them and train them together.
 
 
 ### ADE20K
@@ -311,7 +311,6 @@ Params: 48.98 M
 
 (1) FLOPs are related to the input shape while parameters are not. The default input shape is (1, 3, 1280, 800).
 (2) Some operators are not counted into FLOPs like GN and custom operators.
-You can add support for new operators by modifying [`mmseg/utils/flops_counter.py`](../mmseg/utils/flops_counter.py).
 
 ### Publish a model
 

docs/model_zoo.md

@@ -18,6 +18,8 @@ Results are obtained with the script `tools/benchmark.py` which computes the ave
     * `whole` mode: The `test_cfg` will be like `dict(mode='whole')`.
 
         In this mode, the whole imaged will be passed into network directly.
+
+    By default, we use `slide` inference for 769x769 trained model, `whole` inference for the rest.
 * For input size of 8x+1 (e.g. 769), `align_corner=True` is adopted as a traditional practice.
 Otherwise, for input size of 8x (e.g. 512, 1024), `align_corner=False` is adopted.
 
@@ -25,55 +27,59 @@ Otherwise, for input size of 8x (e.g. 512, 1024), `align_corner=False` is adopte
 
 ### FCN
 
-Please refer to [FCN](https://github.com/open-mmlab/mmsegmentation/tree/master/configs/fcn) for details.
+Please refer to [FCN](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn) for details.
 
 ### PSPNet
 
-Please refer to [PSPNet](https://github.com/open-mmlab/mmsegmentation/tree/master/configs/pspnet) for details.
+Please refer to [PSPNet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/pspnet) for details.
 
 ### DeepLabV3
 
-Please refer to [DeepLabV3](https://github.com/open-mmlab/mmsegmentatio/tree/master/configs/deeplabv3) for details.
+Please refer to [DeepLabV3](https://github.com/open-mmlab/mmsegmentatio/blob/master/configs/deeplabv3) for details.
 
 ### PSANet
 
-Please refer to [PSANet](https://github.com/open-mmlab/mmsegmentation/tree/master/configs/psanet) for details.
+Please refer to [PSANet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/psanet) for details.
 
 ### DeepLabV3+
 
-Please refer to [DeepLabV3+](https://github.com/open-mmlab/mmsegmentatio/tree/master/configs/deeplabv3plus) for details.
+Please refer to [DeepLabV3+](https://github.com/open-mmlab/mmsegmentatio/blob/master/configs/deeplabv3plus) for details.
 
 ### UPerNet
 
-Please refer to [UPerNet](https://github.com/open-mmlab/mmsegmentation/tree/master/configs/upernet) for details.
+Please refer to [UPerNet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/upernet) for details.
 
 ### NonLocal Net
 
-Please refer to [NonLocal Net](https://github.com/open-mmlab/mmsegmentatio/tree/master/configs/nlnet) for details.
+Please refer to [NonLocal Net](https://github.com/open-mmlab/mmsegmentatio/blob/master/configs/nlnet) for details.
+
+### EncNet
+
+Please refer to [NonLocal Net](https://github.com/open-mmlab/mmsegmentatio/blob/master/configs/encnet) for details.
 
 ### CCNet
 
-Please refer to [CCNet](https://github.com/open-mmlab/mmsegmentation/tree/master/configs/ccnet) for details.
+Please refer to [CCNet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/ccnet) for details.
 
 ### DANet
 
-Please refer to [DANet](https://github.com/open-mmlab/mmsegmentation/tree/master/configs/danet) for details.
+Please refer to [DANet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/danet) for details.
 
 ### HRNet
 
-Please refer to [HRNet](https://github.com/open-mmlab/mmsegmentation/tree/master/configs/hrnet) for details.
+Please refer to [HRNet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet) for details.
 
 ### GCNet
 
-Please refer to [GCNet](https://github.com/open-mmlab/mmsegmentation/tree/master/configs/gcnet) for details.
+Please refer to [GCNet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/gcnet) for details.
 
 ### ANN
 
-Please refer to [ANN](https://github.com/open-mmlab/mmsegmentation/tree/master/configs/ann) for details.
+Please refer to [ANN](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/ann) for details.
 
 ### OCRNet
 
-Please refer to [OCRNet](https://github.com/open-mmlab/mmsegmentation/tree/master/configs/ocrnet) for details.
+Please refer to [OCRNet](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/ocrnet) for details.
 
 ## Speed benchmark
 

docs/tutorials/index.rst

@@ -4,3 +4,4 @@
    new_dataset.md
    data_pipeline.md
    new_modules.md
+   training_tricks.md

docs/tutorials/new_modules.md

@@ -121,7 +121,7 @@ model = dict(
 
 ### Add new heads
 
-In MMSegmentation, we provide a base [BaseDecodeHead](../../mmseg/models/decode_heads/decode_head.py) for all segmentation head.
+In MMSegmentation, we provide a base [BaseDecodeHead](https://github.com/open-mmlab/mmsegmentation/blob/master/mmseg/models/decode_heads/decode_head.py) for all segmentation head.
 All newly implemented decode heads should be derived from it.
 Here we show how to develop a new head with the example of [PSPNet](https://arxiv.org/abs/1612.01105) as the following.
 

mmseg/datasets/pipelines/transforms.py

@@ -15,10 +15,13 @@ class Resize(object):
 
     ``img_scale`` can either be a tuple (single-scale) or a list of tuple
     (multi-scale). There are 3 multiscale modes:
+
     - ``ratio_range is not None``: randomly sample a ratio from the ratio range
     and multiply it with the image scale.
+
     - ``ratio_range is None and multiscale_mode == "range"``: randomly sample a
     scale from the a range.
+
     - ``ratio_range is None and multiscale_mode == "value"``: randomly sample a
     scale from multiple scales.
 

mmseg/models/backbones/resnet.py

@@ -330,10 +330,13 @@ class ResNet(nn.Module):
             freeze running stats (mean and var). Note: Effect on Batch Norm
             and its variants only.
         plugins (list[dict]): List of plugins for stages, each dict contains:
-            cfg (dict, required): Cfg dict to build plugin.
-            position (str, required): Position inside block to insert plugin,
+
+            - cfg (dict, required): Cfg dict to build plugin.
+
+            - position (str, required): Position inside block to insert plugin,
             options: 'after_conv1', 'after_conv2', 'after_conv3'.
-            stages (tuple[bool], optional): Stages to apply plugin, length
+
+            - stages (tuple[bool], optional): Stages to apply plugin, length
             should be same as 'num_stages'
         multi_grid (Sequence[int]|None): Multi grid dilation rates of last
             stage. Default: None
@@ -675,13 +678,9 @@ class ResNetV1c(ResNet):
 class ResNetV1d(ResNet):
     """ResNetV1d variant described in [1]_.
 
-    Compared with default ResNet(ResNetV1b), ResNetV1d replaces the 7x7 conv
-    in the input stem with three 3x3 convs. And in the downsampling block,
-    a 2x2 avg_pool with stride 2 is added before conv, whose stride is
-    changed to 1.
-
-    References:
-        .. [1] https://arxiv.org/pdf/1812.01187.pdf
+    Compared with default ResNet(ResNetV1b), ResNetV1d replaces the 7x7 conv in
+    the input stem with three 3x3 convs. And in the downsampling block, a 2x2
+    avg_pool with stride 2 is added before conv, whose stride is changed to 1.
     """
 
     def __init__(self, **kwargs):

requirements/docs.txt

@@ -0,0 +1,4 @@
+recommonmark
+sphinx
+sphinx_markdown_tables
+sphinx_rtd_theme

requirements/readthedocs.txt

@@ -0,0 +1,3 @@
+mmcv
+torch
+torchvision