2022-03-28 16:50:41 +08:00
# 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 ](https://github.com/open-mmlab/mmsegmentation/blob/master/.github/ISSUE_TEMPLATE/error-report.md/ ) and make sure you fill in all required information in the template.
2022-08-31 20:54:15 +08:00
## Installation
2023-02-01 17:53:22 +08:00
The compatible MMSegmentation, MMCV and MMEngine versions are as below. Please install the correct versions of them to avoid installation issues.
2022-08-31 20:54:15 +08:00
2023-02-01 17:53:22 +08:00
| MMSegmentation version | MMCV version | MMEngine version | MMClassification (optional) version | MMDetection (optional) version |
| :--------------------: | :----------------------------: | :---------------: | :---------------------------------: | :----------------------------: |
[Fix] Fix MaskFormer and Mask2Former of MMSegmentation (#2532)
## Motivation
The DETR-related modules have been refactored in
open-mmlab/mmdetection#8763, which causes breakings of MaskFormer and
Mask2Former in both MMDetection (has been fixed in
open-mmlab/mmdetection#9515) and MMSegmentation. This pr fix the bugs in
MMSegmentation.
### TO-DO List
- [x] update configs
- [x] check and modify data flow
- [x] fix unit test
- [x] aligning inference
- [x] write a ckpt converter
- [x] write ckpt update script
- [x] update model zoo
- [x] update model link in readme
- [x] update
[faq.md](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/en/notes/faq.md#installation)
## Tips of Fixing other implementations based on MaskXFormer of mmseg
1. The Transformer modules should be built directly. The original
building with register manner has been refactored.
2. The config requires to be modified. Delete `type` and modify several
keys, according to the modifications in this pr.
3. The `batch_first` is set `True` uniformly in the new implementations.
Hence the data flow requires to be transposed and config of
`batch_first` needs to be modified.
4. The checkpoint trained on the old implementation should be converted
to be used in the new one.
### Convert script
```Python
import argparse
from copy import deepcopy
from collections import OrderedDict
import torch
from mmengine.config import Config
from mmseg.models import build_segmentor
from mmseg.utils import register_all_modules
register_all_modules(init_default_scope=True)
def parse_args():
parser = argparse.ArgumentParser(
description='MMSeg convert MaskXFormer model, by Li-Qingyun')
parser.add_argument('Mask_what_former', type=int,
help='Mask what former, can be a `1` or `2`',
choices=[1, 2])
parser.add_argument('CFG_FILE', help='config file path')
parser.add_argument('OLD_CKPT_FILEPATH', help='old ckpt file path')
parser.add_argument('NEW_CKPT_FILEPATH', help='new ckpt file path')
args = parser.parse_args()
return args
args = parse_args()
def get_new_name(old_name: str):
new_name = old_name
if 'encoder.layers' in new_name:
new_name = new_name.replace('attentions.0', 'self_attn')
new_name = new_name.replace('ffns.0', 'ffn')
if 'decoder.layers' in new_name:
if args.Mask_what_former == 2:
# for Mask2Former
new_name = new_name.replace('attentions.0', 'cross_attn')
new_name = new_name.replace('attentions.1', 'self_attn')
else:
# for Mask2Former
new_name = new_name.replace('attentions.0', 'self_attn')
new_name = new_name.replace('attentions.1', 'cross_attn')
return new_name
def cvt_sd(old_sd: OrderedDict):
new_sd = OrderedDict()
for name, param in old_sd.items():
new_name = get_new_name(name)
assert new_name not in new_sd
new_sd[new_name] = param
assert len(new_sd) == len(old_sd)
return new_sd
if __name__ == '__main__':
cfg = Config.fromfile(args.CFG_FILE)
model_cfg = cfg.model
segmentor = build_segmentor(model_cfg)
refer_sd = segmentor.state_dict()
old_ckpt = torch.load(args.OLD_CKPT_FILEPATH)
old_sd = old_ckpt['state_dict']
new_sd = cvt_sd(old_sd)
print(segmentor.load_state_dict(new_sd))
new_ckpt = deepcopy(old_ckpt)
new_ckpt['state_dict'] = new_sd
torch.save(new_ckpt, args.NEW_CKPT_FILEPATH)
print(f'{args.NEW_CKPT_FILEPATH} has been saved!')
```
Usage:
```bash
# for example
python ckpt4pr2532.py 1 configs/maskformer/maskformer_r50-d32_8xb2-160k_ade20k-512x512.py original_ckpts/maskformer_r50-d32_8xb2-160k_ade20k-512x512_20221030_182724-cbd39cc1.pth cvt_outputs/maskformer_r50-d32_8xb2-160k_ade20k-512x512_20221030_182724.pth
python ckpt4pr2532.py 2 configs/mask2former/mask2former_r50_8xb2-160k_ade20k-512x512.py original_ckpts/mask2former_r50_8xb2-160k_ade20k-512x512_20221204_000055-4c62652d.pth cvt_outputs/mask2former_r50_8xb2-160k_ade20k-512x512_20221204_000055.pth
```
---------
Co-authored-by: MeowZheng <meowzheng@outlook.com>
2023-02-01 18:58:21 +08:00
| dev-1.x branch | mmcv >= 2.0.0rc4 | MMEngine >= 0.2.0 | mmcls>=1.0.0rc0 | mmdet>3.0.0rc5> |
2023-02-01 17:53:22 +08:00
| 1.x branch | mmcv == 2.0.0rc3 | MMEngine >= 0.2.0 | mmcls>=1.0.0rc0 | mmdet>=3.0.0rc4, \<=3.0.0rc5> |
| 1.0.0rc4 | mmcv == 2.0.0rc3 | MMEngine >= 0.1.0 | mmcls>=1.0.0rc0 | mmdet>=3.0.0rc4, \<=3.0.0rc5> |
| 1.0.0rc3 | mmcv == 2.0.0rc3 | MMEngine >= 0.1.0 | mmcls>=1.0.0rc0 | mmdet>=3.0.0rc4 \<=3.0.0rc5> |
| 1.0.0rc2 | mmcv == 2.0.0rc3 | MMEngine >= 0.1.0 | mmcls>=1.0.0rc0 | mmdet>=3.0.0rc4 \<=3.0.0rc5> |
| 1.0.0rc1 | mmcv >= 2.0.0rc1, \<=2.0.0rc3> | MMEngine >= 0.1.0 | mmcls>=1.0.0rc0 | Not required |
| 1.0.0rc0 | mmcv >= 2.0.0rc1, \<=2.0.0rc3> | MMEngine >= 0.1.0 | mmcls>=1.0.0rc0 | Not required |
Notes: To install MMSegmentation 0.x and master branch, please refer to [the faq 0.x document ](https://mmsegmentation.readthedocs.io/en/latest/faq.html#installation ) to check compatible versions of MMCV.
2022-08-31 20:54:15 +08:00
2022-03-28 16:50:41 +08:00
## How to know the number of GPUs needed to train the model
2022-08-31 20:54:15 +08:00
- Infer from the name of the config file of the model. You can refer to the `Config Name Style` part of [Learn about Configs ](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/en/tutorials/config.md ). For example, for config file with name `segformer_mit-b0_8xb1-160k_cityscapes-1024x1024.py` , `8xb1` means training the model corresponding to it needs 8 GPUs, and the batch size of each GPU is 1.
2022-03-28 16:50:41 +08:00
- Infer from the log file. Open the log file of the model and search `nGPU` in the file. The number of figures following `nGPU` is the number of GPUs needed to train the model. For instance, searching for `nGPU` in the log file yields the record `nGPU 0,1,2,3,4,5,6,7` , which indicates that eight GPUs are needed to train the model.
