Laurent/REVA-QCAV
1
0
Fork 0
mirror of https://github.com/Laurent2916/REVA-QCAV.git synced 2024-11-09 23:12:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update README

Browse source 
Former-commit-id: 20d8d2b9446970ac74deeb7c36a65ae9e8819a29
This commit is contained in:
milesial 2021-08-19 00:30:35 +02:00 committed by GitHub
parent c1dcc0877e
commit 4e638b47de
1 changed files with 5 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
README.md
View file

@ -46,8 +46,9 @@ python train.py --amp
``` ```
## Description ## Description
This model was trained from scratch with 5000 images (no data augmentation) and scored a [dice coefficient](https://en.wikipedia.org/wiki/S%C3%B8rensen%E2%80%93Dice_coefficient) of 0.988423 on over 100k test images. This score could be improved with more training, data augmentation, fine-tuning, CRF post-processing, and applying more weights on the edges of the masks. This model was trained from scratch with 5k images and scored a [Dice coefficient](https://en.wikipedia.org/wiki/S%C3%B8rensen%E2%80%93Dice_coefficient) of 0.988423 on over 100k test images.
It can be easily used for multiclass segmentation, portrait segmentation, medical segmentation, ...
## Usage ## Usage
@ -56,7 +57,7 @@ This model was trained from scratch with 5000 images (no data augmentation) and
### Docker ### Docker
A docker image containing the code and the dependencies is available on [DockerHub](https://hub.docker.com/repository/docker/milesial/unet). A docker image containing the code and the dependencies is available on [DockerHub](https://hub.docker.com/repository/docker/milesial/unet).
You can **download and jump in the container** with ([docker >=19.03](https://docs.docker.com/get-docker/)): You can download and jump in the container with ([docker >=19.03](https://docs.docker.com/get-docker/)):
```console ```console
docker run -it --rm --gpus all milesial/unet docker run -it --rm --gpus all milesial/unet
@ -88,7 +89,7 @@ optional arguments:
By default, the `scale` is 0.5, so if you wish to obtain better results (but use more memory), set it to 1. By default, the `scale` is 0.5, so if you wish to obtain better results (but use more memory), set it to 1.
Automatic mixed precision is also available with the `--amp` flag. [Mixed precision](https://arxiv.org/abs/1710.03740) allows the model to use less memory and to be faster on recent GPUs by using FP16 arithmetic. Automatic mixed precision is also available with the `--amp` flag. [Mixed precision](https://arxiv.org/abs/1710.03740) allows the model to use less memory and to be faster on recent GPUs by using FP16 arithmetic. Enabling AMP is recommended.
### Prediction ### Prediction
@ -155,7 +156,7 @@ bash scripts/download_data.sh
The input images and target masks should be in the `data/imgs` and `data/masks` folders respectively. For Carvana, images are RGB and masks are black and white. The input images and target masks should be in the `data/imgs` and `data/masks` folders respectively. For Carvana, images are RGB and masks are black and white.
You can also use your own dataset as long as you make sure it is loaded properly in `utils/data_loading.py`. You can use your own dataset as long as you make sure it is loaded properly in `utils/data_loading.py`.
--- ---