mmr/tkDNN
Archived
1
0
Fork 0
Code Issues 46 Pull Requests 12 Releases 4 Activity

Update READMEs

Browse Source 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
This commit is contained in:
Micaela Verucchi
2021-07-23 10:31:34 +02:00
parent 0292e21c33
commit 4f9f27152a
6 changed files with 91 additions and 149 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/README_seg.md
+1 -22
View File
@@ -2,19 +2,6 @@
Currently tkDNN supports only ShelfNet as semantic segmentation network.
## Export weights from Shelfnet
To get the weights needed to run Shelfnet tests use [this](https://git.hipert.unimore.it/mverucchi/shelfnet) fork of a Pytorch implementation of Shelfnet network.
```
git clone https://git.hipert.unimore.it/mverucchi/shelfnet
cd shelfnet
cd ShelfNet18_realtime
conda env create --file shelfnet_env.yml
conda activate shelfnet
mkdir layer debug
python export.py
```
## Run the demo
@@ -46,15 +33,7 @@ NB) The batching is not used to work on more streams, rather to work on more til
For other demo videos refer to [this playlist](https://www.youtube.com/playlist?list=PLv0nEQYDD45y5EdSiywwCGPBmJVUzIWwe).
## Existing tests and supported networks
| Test Name | Network | Dataset | N Classes | Input size | Weights |
| :---------------- | :-------------------------------------------- | :-----------------------------------------------------------: | :-------: | :-----------: | :------------------------------------------------------------------------ |
| shelfnet | ShelfNet18_realtime<sup>1</sup> | [Cityscapes](https://www.cityscapes-dataset.com/) | 19 | 1024x1024 | [weights](https://cloud.hipert.unimore.it/s/mEDZMRJaGCFWSJF/download) |
| shelfnet_berkeley | ShelfNet18_realtime<sup>1</sup> | [DeepDrive](https://bdd-data.berkeley.edu/) | 20 | 1024x1024 | [weights](https://cloud.hipert.unimore.it/s/m92e7QdD9gYMF7f/download) |
1. Zhuang, Juntang, et al. "ShelfNet for fast semantic segmentation." Proceedings of the IEEE International Conference on Computer Vision Workshops. 2019.
NB) The gif and the videos are obtained with Mapillary Vistas weights, that we cannot publicly share due to its license restrictions. However, you can train Shelfnet using Mapillary and [this](https://git.hipert.unimore.it/mverucchi/shelfnet) fork of the original repo.
## FPS Results