PyTorch Implementation of Fully Convolutional Networks. (Training code to reproduce the original result is available.)

pytorch-fcn

PyTorch implementation of Fully Convolutional Networks.

Requirements

pytorch >= 0.2.0
torchvision >= 0.1.8
fcn >= 6.1.5
Pillow
scipy
tqdm

Installation

git clone https://github.com/wkentaro/pytorch-fcn.git
cd pytorch-fcn
pip install .

# or

pip install torchfcn

Training

See VOC example.

Accuracy

At 10fdec9.

Model	Implementation	epoch	iteration	Mean IU	Pretrained Model
FCN32s	Original	-	-	63.63	Download
FCN32s	Ours	11	96000	62.84
FCN16s	Original	-	-	65.01	Download
FCN16s	Ours	11	96000	64.91
FCN8s	Original	-	-	65.51	Download
FCN8s	Ours	7	60000	65.49
FCN8sAtOnce	Original	-	-	65.40
FCN8sAtOnce	Ours	11	96000	64.74

Visualization of validation result of FCN8s.

Cite This Project

If you use this project in your research or wish to refer to the baseline results published in the README, please use the following BibTeX entry.

@misc{pytorch-fcn2017,
  author =       {Ketaro Wada},
  title =        {{pytorch-fcn: PyTorch Implementation of Fully Convolutional Networks}},
  howpublished = {\url{https://github.com/wkentaro/pytorch-fcn}},
  year =         {2017}
}