mirrors/mmsegmentation
1
0
Fork 0
mirror of https://github.com/open-mmlab/mmsegmentation.git synced 2025-06-03 14:15:15 +08:00
Code Issues Projects Releases Wiki Activity
mmsegmentation/configs/dnlnet/dnl_r50-d8_4xb2-80k_cityscapes-512x1024.py

8 lines
276 B
Python
Raw Normal View History

Add "disentangled non-local (DNL) neural networks" [ECCV2020] (#37) * Add DNLHead * add configs * add weight decay mult * add norm back * Update README.md * matched inference performance * Fixed shape * sep conv_out * no norm * add norm back * complete model zoo * add tests * Add test forward * Add more test Co-authored-by: Jiarui XU <xvjiarui0826@gmail.com>
2020-09-07 16:22:00 +08:00
_base_ = [
'../_base_/models/dnl_r50-d8.py', '../_base_/datasets/cityscapes.py',
'../_base_/default_runtime.py', '../_base_/schedules/schedule_80k.py'
]
[Refactor] Refactor decode_head and segmentors and add preprocess_cfg
2022-06-10 14:02:40 +00:00
crop_size = (512, 1024)
[Refactory] Refactory BaseSegmentor based BaseModel
2022-06-19 06:32:09 +00:00
data_preprocessor = dict(size=crop_size)
model = dict(data_preprocessor=data_preprocessor)
Reference in New Issue Copy Permalink