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)
Pascal VOC 2012 could be downloaded from [here](http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar).
Beside, most recent works on Pascal VOC dataset usually exploit extra augmentation data, which could be found [here](http://www.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/semantic_contours/benchmark.tgz).
If you would like to use augmented VOC dataset, please run following command to convert augmentation annotations into proper format.
```shell
# --nproc means 8 process for conversion, which could be omitted as well.
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.
The training and validation set of Pascal Context could be download from [here](http://host.robots.ox.ac.uk/pascal/VOC/voc2010/VOCtrainval_03-May-2010.tar). You may also download test set from [here](http://host.robots.ox.ac.uk:8080/eval/downloads/VOC2010test.tar) after registration.
To split the training and validation set from original dataset, you may download trainval_merged.json from [here](https://codalabuser.blob.core.windows.net/public/trainval_merged.json).
If you would like to use Pascal Context dataset, please install [Detail](https://github.com/ccvl/detail-api) and then run the following command to convert annotations into proper format.
-`RESULT_FILE`: Filename of the output results in pickle format. If not specified, the results will not be saved to a file.
-`EVAL_METRICS`: Items to be evaluated on the results. Allowed values depend on the dataset, e.g., `mIoU` is available for all dataset. Cityscapes could be evaluated by `cityscapes` as well as standard `mIoU` metrics.
-`--show`: If specified, segmentation results will be plotted on the images and shown in a new window. It is only applicable to single GPU testing and used for debugging and visualization. Please make sure that GUI is available in your environment, otherwise you may encounter the error like `cannot connect to X server`.
-`--show-dir`: If specified, segmentation results will be plotted on the images and saved to the specified directory. It is only applicable to single GPU testing and used for debugging and visualization. You do NOT need a GUI available in your environment for using this option.
Examples:
Assume that you have already downloaded the checkpoints to the directory `checkpoints/`.
1. Test PSPNet and visualize the results. Press any key for the next image.
A notebook demo can be found in [demo/inference_demo.ipynb](../demo/inference_demo.ipynb).
## Train a model
MMSegmentation implements distributed training and non-distributed training,
which uses `MMDistributedDataParallel` and `MMDataParallel` respectively.
All outputs (log files and checkpoints) will be saved to the working directory,
which is specified by `work_dir` in the config file.
By default we evaluate the model on the validation set after some iterations, you can change the evaluation interval by adding the interval argument in the training config.
```python
evaluation = dict(interval=4000) # This evaluate the model per 4000 iterations.
-`--no-validate` (**not suggested**): By default, the codebase will perform evaluation at every k iterations during the training. To disable this behavior, use `--no-validate`.
-`--work-dir ${WORK_DIR}`: Override the working directory specified in the config file.
If you run MMSegmentation on a cluster managed with [slurm](https://slurm.schedmd.com/), you can use the script `slurm_train.sh`. (This script also supports single machine training.)
you need to specify different ports (29500 by default) for each job to avoid communication conflict. Otherwise, there will be error message saying `RuntimeError: Address already in use`.
We provide lots of useful tools under `tools/` directory.
### Get the FLOPs and params (experimental)
We provide a script adapted from [flops-counter.pytorch](https://github.com/sovrasov/flops-counter.pytorch) to compute the FLOPs and params of a given model.
**Note**: This tool is still experimental and we do not guarantee that the number is correct. You may well use the result for simple comparisons, but double check it before you adopt it in technical reports or papers.
(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.
### Publish a model
Before you upload a model to AWS, you may want to
(1) convert model weights to CPU tensors, (2) delete the optimizer states and
(3) compute the hash of the checkpoint file and append the hash id to the filename.
We provide a script to convert model to [ONNX](https://github.com/onnx/onnx) format. The converted model could be visualized by tools like [Netron](https://github.com/lutzroeder/netron). Besides, we also support comparing the output results between Pytorch and ONNX model.
**Note**: This tool is still experimental. Some customized operators are not supported for now.
## Tutorials
Currently, we provide four tutorials for users to [add new dataset](tutorials/new_dataset.md), [design data pipeline](tutorials/data_pipeline.md) and [add new modules](tutorials/new_modules.md), [use training tricks](tutorials/training_tricks.md).
We also provide a full description about the [config system](config.md).
