fcn 6.4.12

Fully Convolutional Networks

fcn - Fully Convolutional Networks

Chainer implementation of Fully Convolutional Networks.

Installation

pip install fcn

Inference

Inference is done as below:

# forwaring of the networks
img_file=https://farm2.staticflickr.com/1522/26471792680_a485afb024_z_d.jpg
fcn_infer.py --img-files $img_file --gpu -1 -o /tmp  # cpu mode
fcn_infer.py --img-files $img_file --gpu 0 -o /tmp   # gpu mode

Original Image: https://www.flickr.com/photos/faceme/26471792680/

Training

cd examples/voc
./download_datasets.py
./download_models.py

./train_fcn32s.py --gpu 0
# ./train_fcn16s.py --gpu 0
# ./train_fcn8s.py --gpu 0
# ./train_fcn8s_atonce.py --gpu 0

The accuracy of original implementation is computed with (evaluate.py) after converting the caffe model to chainer one using convert_caffe_to_chainermodel.py.
You can download vgg16 model from here: vgg16_from_caffe.npz.

FCN32s

Implementation	Accuracy	Accuracy Class	Mean IU	FWAVACC	Model File
Original	90.4810	76.4824	63.6261	83.4580	fcn32s_from_caffe.npz
Ours (using vgg16_from_caffe.npz)	90.5668	76.8740	63.8180	83.5067	fcn32s_voc_iter00092000.npz

FCN16s

Implementation	Accuracy	Accuracy Class	Mean IU	FWAVACC	Model File
Original	90.9971	78.0710	65.0050	84.2614	fcn16s_from_caffe.npz
Ours (using fcn32s_from_caffe.npz)	90.9671	78.0617	65.0911	84.2604	fcn16s_voc_using_fcn32s_from_caffe_iter00032000.npz
Ours (using fcn32s_voc_iter00092000.npz)	91.1009	77.2522	65.3628	84.3675	fcn16s_voc_iter00100000.npz

FCN8s

Implementation	Accuracy	Accuracy Class	Mean IU	FWAVACC	Model File
Original	91.2212	77.6146	65.5126	84.5445	fcn8s_from_caffe.npz
Ours (using fcn16s_from_caffe.npz)	91.2513	77.1490	65.4789	84.5460	fcn8s_voc_using_fcn16s_from_caffe_iter00016000.npz
Ours (using fcn16s_voc_iter00100000.npz)	91.2608	78.1484	65.8444	84.6447	fcn8s_voc_iter00072000.npz

FCN8sAtOnce

Implementation	Accuracy	Accuracy Class	Mean IU	FWAVACC	Model File
Original	91.1288	78.4979	65.3998	84.4326	fcn8s-atonce_from_caffe.npz
Ours (using vgg16_from_caffe.npz)	91.0883	77.3528	65.3433	84.4276	fcn8s-atonce_voc_iter00056000.npz

Left to right, FCN32s, FCN16s and FCN8s, which are fully trained using this repo. See above tables to see the accuracy.

License

See LICENSE.