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

Fixed training tricks (#26)

Browse Source
This commit is contained in:
Jerry Jiarui XU 2020-07-20 15:17:59 +08:00 committed by GitHub
parent e1f5b9231e
commit 6e96bf83e5
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/getting_started.md
View File

@ -132,7 +132,7 @@ Assume that you have already downloaded the checkpoints to the directory `checkp
checkpoints/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth \
4 --out results.pkl --eval mIoU cityscapes
```
Note: There is some inconsistency between cityscapes mIoU and our mIoU. The reason is that cityscapes average each class with class size by default.
Note: There is some gap (~0.1%) between cityscapes mIoU and our mIoU. The reason is that cityscapes average each class with class size by default.
We use the simple version without average for all datasets.
5. Test PSPNet on cityscapes test split with 4 GPUs, and generate the png files to be submit to the official evaluation server.

2
docs/tutorials/training_tricks.md
View File

@ -8,7 +8,7 @@ In semantic segmentation, some methods make the LR of heads larger than backbone
In MMSegmentation, you may add following lines to config to make the LR of heads 10 times of backbone.
```python
optimizer_config=dict(
optimizer=dict(
paramwise_cfg = dict(
custom_keys={
'head': dict(lr_mult=10.)}))