This is a Tensorflow implementation of semantic segmentation models on MIT ADE20K scene parsing dataset and Cityscapes dataset We re-produce the inference phase of several models, including PSPNet, FCN, and ICNet by transforming the released pre-trained weights into tensorflow format, and apply on handcraft models. Also, we refer to ENet from freg856 github. Still working on task integrated.
Get corresponding transformed pre-trained weights, and put into model directory:
| FCN | PSPNet | ICNet |
|---|---|---|
| Google drive | Google drive | Google drive |
Run following command:
python inference.py --img-path /Path/To/Image --dataset Model_Type --model - choose from "icnet"/"pspnet"/"fcn"/"enet" from model import FCN8s, PSPNet50, ICNet, ENet model = PSPNet50() # or another model model.read_input(img_path) # read image data from path sess = tf.Session(config=config) init = tf.global_variables_initializer() sess.run(init) model.load(model_path, sess) # load pretrained model preds = model.forward(sess) # Get prediction | Input Image | PSPNet | FCN |
|---|---|---|
 |  |  |
 |  |  |
| Input Image | ICNet | ENet |
|---|---|---|
 |  |  |
@inproceedings{zhao2017pspnet, author = {Hengshuang Zhao and Jianping Shi and Xiaojuan Qi and Xiaogang Wang and Jiaya Jia}, title = {Pyramid Scene Parsing Network}, booktitle = {Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2017} } Scene Parsing through ADE20K Dataset. B. Zhou, H. Zhao, X. Puig, S. Fidler, A. Barriuso and A. Torralba. Computer Vision and Pattern Recognition (CVPR), 2017. (http://people.csail.mit.edu/bzhou/publication/scene-parse-camera-ready.pdf)
@inproceedings{zhou2017scene, title={Scene Parsing through ADE20K Dataset}, author={Zhou, Bolei and Zhao, Hang and Puig, Xavier and Fidler, Sanja and Barriuso, Adela and Torralba, Antonio}, booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition}, year={2017} } Semantic Understanding of Scenes through ADE20K Dataset. B. Zhou, H. Zhao, X. Puig, S. Fidler, A. Barriuso and A. Torralba. arXiv:1608.05442. (https://arxiv.org/pdf/1608.05442.pdf)
@article{zhou2016semantic, title={Semantic understanding of scenes through the ade20k dataset}, author={Zhou, Bolei and Zhao, Hang and Puig, Xavier and Fidler, Sanja and Barriuso, Adela and Torralba, Antonio}, journal={arXiv preprint arXiv:1608.05442}, year={2016} }