mirrors/mmsegmentation
1
0
Fork 0
mirror of https://github.com/open-mmlab/mmsegmentation.git synced 2025-06-03 22:03:48 +08:00
Code Issues Projects Releases Wiki Activity

Update MMSegmentation_Tutorial.ipynb (#1281)

Browse Source
This commit is contained in:
andife 2022-02-11 06:07:46 +01:00 committed by GitHub
parent 0166616d49
commit f5ba2ea401
1 changed files with 7 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
demo/MMSegmentation_Tutorial.ipynb
View File

@ -33,7 +33,7 @@
"## Install MMSegmentation\n",
"This step may take several minutes. \n",
"\n",
"We use PyTorch 1.5.0 and CUDA 10.1 for this tutorial. You may install other versions by change the version number in pip install command. "
"We use PyTorch 1.5.0 and CUDA 10.1 for this tutorial. You may install other versions by changing the version number in pip install command. "
]
},
{
@ -214,7 +214,7 @@
"source": [
"## Train a semantic segmentation model on a new dataset\n",
"\n",
"To train on a customized dataset, the following steps are neccessary. \n",
"To train on a customized dataset, the following steps are necessary. \n",
"1. Add a new dataset class. \n",
"2. Create a config file accordingly. \n",
"3. Perform training and evaluation. "
@ -228,11 +228,11 @@
"source": [
"### Add a new dataset\n",
"\n",
"Datasets in MMSegmentation require image and semantic segmentation maps to be placed in folders with the same perfix. To support a new dataset, we may need to modify the original file structure. \n",
"Datasets in MMSegmentation require image and semantic segmentation maps to be placed in folders with the same prefix. To support a new dataset, we may need to modify the original file structure. \n",
"\n",
"In this tutorial, we give an example of converting the dataset. You may refer to [docs](https://github.com/open-mmlab/mmsegmentation/docs/en/tutorials/new_dataset.md) for details about dataset reorganization. \n",
"\n",
"We use [Standord Background Dataset](http://dags.stanford.edu/projects/scenedataset.html) as an example. The dataset contains 715 images chosen from existing public datasets [LabelMe](http://labelme.csail.mit.edu), [MSRC](http://research.microsoft.com/en-us/projects/objectclassrecognition), [PASCAL VOC](http://pascallin.ecs.soton.ac.uk/challenges/VOC) and [Geometric Context](http://www.cs.illinois.edu/homes/dhoiem/). Images from these datasets are mainly outdoor scenes, each containing approximately 320-by-240 pixels. \n",
"We use [Stanford Background Dataset](http://dags.stanford.edu/projects/scenedataset.html) as an example. The dataset contains 715 images chosen from existing public datasets [LabelMe](http://labelme.csail.mit.edu), [MSRC](http://research.microsoft.com/en-us/projects/objectclassrecognition), [PASCAL VOC](http://pascallin.ecs.soton.ac.uk/challenges/VOC) and [Geometric Context](http://www.cs.illinois.edu/homes/dhoiem/). Images from these datasets are mainly outdoor scenes, each containing approximately 320-by-240 pixels. \n",
"In this tutorial, we use the region annotations as labels. There are 8 classes in total, i.e. sky, tree, road, grass, water, building, mountain, and foreground object. "
]
},
@ -249,8 +249,8 @@
"outputs": [],
"source": [
"# download and unzip\n",
"!wget http://dags.stanford.edu/data/iccv09Data.tar.gz -O standford_background.tar.gz\n",
"!tar xf standford_background.tar.gz"
"!wget http://dags.stanford.edu/data/iccv09Data.tar.gz -O stanford_background.tar.gz\n",
"!tar xf stanford_background.tar.gz"
]
},
{
@ -423,7 +423,7 @@
"id": "1y2oV5w97jQo"
},
"source": [
"Since the given config is used to train PSPNet on cityscapes dataset, we need to modify it accordingly for our new dataset. "
"Since the given config is used to train PSPNet on the cityscapes dataset, we need to modify it accordingly for our new dataset. "
]
},
{