This is the official implement for
ACNET: ATTENTION BASED NETWORK TO EXPLOIT COMPLEMENTARY FEATURES FOR RGBD SEMANTIC SEGMENTATION Xinxin Hu*, Kailun Yang, Lei Fei, Kaiwei Wang Accepted by IEEE ICIP 2019
we evaluate the mIoU of ACNet in SUN-RGBD and NYUDv2
| SUN-RGBD | NYUDv2 | |
|---|---|---|
| mIoU | 48.1% | 48.3% |
This code is NYUDv2 implement.
Python 3
Pytorch 0.4.1
TensorboardX
Tensorboard
python ACNet_train_V1_nyuv2.py --cuda -b 4
The pretrained model for NYUDv2 is avaliable at http://wangkaiwei.org/file/NYUDv2.zip .
The pre-processed NYUDv2 dataset with .npy format is avaliable at https://pan.baidu.com/s/1nxys4pdT4pacWLMScIGT4w with password：k6rv
python ACNet_eval_nyuv2.py --cuda --last-ckpt '.\model\ckpt_epoch_1195.00.pth'
Note: The code is partially based on RedNet (https://github.com/JindongJiang/RedNet) and (https://github.com/warmspringwinds/pytorch-segmentation-detection)