Frequently Asked Questions (FAQ)¶
We list some common troubles faced by many users and their corresponding solutions here. Feel free to enrich the list if you find any frequent issues and have ways to help others to solve them. If the contents here do not cover your issue, please create an issue using the provided templates and make sure you fill in all required information in the template.
Installation¶
The compatible MMSegmentation and MMCV versions are as below. Please install the correct version of MMCV to avoid installation issues.
| MMSegmentation version | MMCV version | MMClassification version |
|---|---|---|
| master | mmcv-full>=1.5.0, \<1.7.0 | mmcls>=0.20.1, \<=1.0.0 |
| 0.28.0 | mmcv-full>=1.5.0, \<1.7.0 | mmcls>=0.20.1, \<=1.0.0 |
| 0.27.0 | mmcv-full>=1.5.0, \<1.7.0 | mmcls>=0.20.1, \<=1.0.0 |
| 0.26.0 | mmcv-full>=1.5.0, \<=1.6.0 | mmcls>=0.20.1, \<=1.0.0 |
| 0.25.0 | mmcv-full>=1.5.0, \<=1.6.0 | mmcls>=0.20.1, \<=1.0.0 |
| 0.24.1 | mmcv-full>=1.4.4, \<=1.6.0 | mmcls>=0.20.1, \<=1.0.0 |
| 0.23.0 | mmcv-full>=1.4.4, \<=1.6.0 | mmcls>=0.20.1, \<=1.0.0 |
| 0.22.0 | mmcv-full>=1.4.4, \<=1.6.0 | mmcls>=0.20.1, \<=1.0.0 |
| 0.21.1 | mmcv-full>=1.4.4, \<=1.6.0 | Not required |
| 0.20.2 | mmcv-full>=1.3.13, \<=1.6.0 | Not required |
| 0.19.0 | mmcv-full>=1.3.13, \<1.3.17 | Not required |
| 0.18.0 | mmcv-full>=1.3.13, \<1.3.17 | Not required |
| 0.17.0 | mmcv-full>=1.3.7, \<1.3.17 | Not required |
| 0.16.0 | mmcv-full>=1.3.7, \<1.3.17 | Not required |
| 0.15.0 | mmcv-full>=1.3.7, \<1.3.17 | Not required |
| 0.14.1 | mmcv-full>=1.3.7, \<1.3.17 | Not required |
| 0.14.0 | mmcv-full>=1.3.1, \<1.3.2 | Not required |
| 0.13.0 | mmcv-full>=1.3.1, \<1.3.2 | Not required |
| 0.12.0 | mmcv-full>=1.1.4, \<1.3.2 | Not required |
| 0.11.0 | mmcv-full>=1.1.4, \<1.3.0 | Not required |
| 0.10.0 | mmcv-full>=1.1.4, \<1.3.0 | Not required |
| 0.9.0 | mmcv-full>=1.1.4, \<1.3.0 | Not required |
| 0.8.0 | mmcv-full>=1.1.4, \<1.2.0 | Not required |
| 0.7.0 | mmcv-full>=1.1.2, \<1.2.0 | Not required |
| 0.6.0 | mmcv-full>=1.1.2, \<1.2.0 | Not required |
You need to run pip uninstall mmcv first if you have mmcv installed.
If mmcv and mmcv-full are both installed, there will be ModuleNotFoundError.
“No module named ‘mmcv.ops’”; “No module named ‘mmcv._ext’”.
Uninstall existing mmcv in the environment using
pip uninstall mmcv.Install mmcv-full following the installation instruction.
How to know the number of GPUs needed to train the model¶
Infer from the name of the config file of the model. You can refer to the
Config Name Stylepart of Learn about Configs. For example, for config file with namesegformer_mit-b0_8x1_1024x1024_160k_cityscapes.py,8x1means training the model corresponding to it needs 8 GPUs, and the batch size of each GPU is 1.Infer from the log file. Open the log file of the model and search
nGPUin the file. The number of figures followingnGPUis the number of GPUs needed to train the model. For instance, searching fornGPUin the log file yields the recordnGPU 0,1,2,3,4,5,6,7, which indicates that eight GPUs are needed to train the model.
What does the auxiliary head mean¶
Briefly, it is a deep supervision trick to improve the accuracy. In the training phase, decode_head is for decoding semantic segmentation output, auxiliary_head is just adding an auxiliary loss, the segmentation result produced by it has no impact to your model’s result, it just works in training. You may read this paper for more information.
Why is the log file not created¶
In the train script, we call get_root_loggerat Line 167, and get_root_logger in mmseg calls get_logger in mmcv, mmcv will return the same logger which has beed initialized in ‘mmsegmentation/tools/train.py’ with the parameter log_file. There is only one logger (initialized with log_file) during training.
Ref: https://github.com/open-mmlab/mmcv/blob/21bada32560c7ed7b15b017dc763d862789e29a8/mmcv/utils/logging.py#L9-L16
If you find the log file not been created, you might check if mmcv.utils.get_logger is called elsewhere.
How to output the image for painting the segmentation mask when running the test script¶
In the test script, we provide show-dir argument to control whether output the painted images. Users might run the following command:
python tools/test.py {config} {checkpoint} --show-dir {/path/to/save/image} --opacity 1