ENSEEIHT/projet-long
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity

Tweaked README

Browse source 
Former-commit-id: f49d66e44456731f0f10cebe8b6d9d2be985fdb2
This commit is contained in:
milesial 2017-11-30 08:30:38 +01:00
parent 6275cb8458
commit 50cbf66b21
1 changed files with 7 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
README.md
View file

@ -1,10 +1,10 @@
# Pytorch-UNet
![input and output for a random image in the test dataset](https://framapic.org/YqBT4lbLrcfc/kQcSxYDv1Pfk.png)
![input and output for a random image in the test dataset](https://framapic.org/OcE8HlU6me61/KNTt8GFQzxDR.png)
Customized implementation of the [U-Net](https://arxiv.org/pdf/1505.04597.pdf) in Pytorch for Kaggle's [Carvana Image Masking Challenge](https://www.kaggle.com/c/carvana-image-masking-challenge), with only 1 output class, from a high definition image.
Customized implementation of the [U-Net](https://arxiv.org/pdf/1505.04597.pdf) in Pytorch for Kaggle's [Carvana Image Masking Challenge](https://www.kaggle.com/c/carvana-image-masking-challenge) from a high definition image. This was used with only one output class but it can be scaled easily.
This model scored a [dice coefficient](https://en.wikipedia.org/wiki/S%C3%B8rensen%E2%80%93Dice_coefficient) of 0.988423 (511 out of 735), which is bad but could be improved with more training, data augmentation, fine tuning, and playing with CRF post-processing.
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 (511 out of 735) on over 100k test images. This score is not quite good but could be improved with more training, data augmentation, fine tuning, playing with CRF post-processing, and applying more weights on the edges of the masks.
The model used for the last submission is stored in the `MODEL.pth` file, if you wish to play with it. The data is available on the [Kaggle website](https://www.kaggle.com/c/carvana-image-masking-challenge/data).
@ -13,6 +13,7 @@ The model used for the last submission is stored in the `MODEL.pth` file, if you
### Prediction
You can easily test the output masks on your images via the CLI.
To see all options:
`python predict.py -h`
@ -28,6 +29,9 @@ You can use the cpu-only version with `--cpu`.
You can specify which model file to use with `--model MODEL.pth`.
### Training
`python train.py -h` should get you started. A proper CLI is yet to be added.
## Warning
In order to process the image, it is splitted into two squares (a left on and a right one), and each square is passed into the net. The two square masks are then merged again to produce the final image. As a consequence, the height of the image must be strictly superior than half the width. Make sure the width is even too.