iicd/RAFT
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

added small 1M paramter model

Browse Source
This commit is contained in:
Zach Teed
2020-08-23 22:40:47 -06:00
parent c86b3dc8f3
commit 01ad964d94
5 changed files with 18 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
README.md
View File

@@ -24,21 +24,13 @@ Pretrained models can be downloaded by running
```Shell
./download_models.sh
```
or downloaded from [google drive](https://drive.google.com/file/d/10-BYgHqRNPGvmNUWr8razjb1xHu55pyA/view?usp=sharing)
or downloaded from [google drive](https://drive.google.com/drive/folders/1sWDsfuZ3Up38EUQt7-JDTT1HcGHuJgvT?usp=sharing)
You can demo a trained model on a sequence of frames
```Shell
python demo.py --model=models/raft-things.pth --path=demo-frames
```
## (Optional) Efficent Implementation
You can optionally use our alternate (efficent) implementation by compiling the provided cuda extension
```Shell
cd alt_cuda_corr && python setup.py install && cd ..
```
and running `demo.py` and `evaluate.py` with the `--alternate_corr` flag.Note, this implementation is somewhat slower than all-pairs, but uses significantly less GPU memory during the forward pass.
## Required Data
To evaluate/train RAFT, you will need to download the required datasets.
* [FlyingChairs](https://lmb.informatik.uni-freiburg.de/resources/datasets/FlyingChairs.en.html#flyingchairs)
@@ -83,3 +75,10 @@ If you have a RTX GPU, training can be accelerated using mixed precision. You ca
```Shell
./train_mixed.sh
```
## (Optional) Efficent Implementation
You can optionally use our alternate (efficent) implementation by compiling the provided cuda extension
```Shell
cd alt_cuda_corr && python setup.py install && cd ..
```
and running `demo.py` and `evaluate.py` with the `--alternate_corr` flag Note, this implementation is somewhat slower than all-pairs, but uses significantly less GPU memory during the forward pass.