TensorFlow implementation of original paper : https://github.com/hszhao/PSPNet
Implemented Architecture of Pyramid Scene Parsing Network in Keras.
For the best compability please use Python3.5
pip install -r requirements.txt --upgrade
.h5 .json
format) have to be downloaded and placed into directory weights/keras
Already converted weights can be downloaded here:
(Note: this is not required if you use .h5/.json weights)
Running this needs the compiled original PSPNet caffe code and pycaffe.
python weight_converter.py <path to .prototxt> <path to .caffemodel>
python pspnet.py -m <model> -i <input_image> -o <output_path>
python pspnet.py -m pspnet101_cityscapes -i example_images/cityscapes.png -o example_results/cityscapes.jpg
python pspnet.py -m pspnet101_voc2012 -i example_images/pascal_voc.jpg -o example_results/pascal_voc.jpg
List of arguments:
-m --model - which model to use: 'pspnet50_ade20k', 'pspnet101_cityscapes', 'pspnet101_voc2012'
--id - (int) GPU Device id. Default 0
-s --sliding - Use sliding window
-f --flip - Additional prediction of flipped image
-ms --multi_scale - Predict on multiscale images
config = tf.ConfigProto()
config.gpu_options.per_process_gpu_memory_fraction = 0.3
sess = tf.Session(config=config)
ndimage.zoom
can take a long time