Mtl Implem
| Project Name | Stars | Downloads | Repos Using This | Packages Using This | Most Recent Commit | Total Releases | Latest Release | Open Issues | License | Language |
|---|---|---|---|---|---|---|---|---|---|---|
| Pix2code | 11,584 | a month ago | 6 | apache-2.0 | Python | |||||
| pix2code: Generating Code from a Graphical User Interface Screenshot | ||||||||||
| Stylegan2 | 8,836 | a year ago | 27 | other | Python | |||||
| StyleGAN2 - Official TensorFlow Implementation | ||||||||||
| Tts | 6,557 | 2 months ago | 7 | mpl-2.0 | Jupyter Notebook | |||||
| :robot: :speech_balloon: Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts) | ||||||||||
| Transformers Tutorials | 3,823 | 23 days ago | 142 | mit | Jupyter Notebook | |||||
| This repository contains demos I made with the Transformers library by HuggingFace. | ||||||||||
| Alae | 2,850 | 2 years ago | 31 | Python | ||||||
| [CVPR2020] Adversarial Latent Autoencoders | ||||||||||
| Cnn_sentence | 1,873 | 5 years ago | 42 | Python | ||||||
| CNNs for sentence classification | ||||||||||
| Surface Defect Detection | 1,614 | 2 months ago | 11 | mit | Python | |||||
| 📈 目前最大的工业缺陷检测数据库及论文集 Constantly summarizing open source dataset and critical papers in the field of surface defect research which are of great importance. | ||||||||||
| Tacotron 2 | 1,572 | 3 years ago | 230 | mit | Python | |||||
| DeepMind's Tacotron-2 Tensorflow implementation | ||||||||||
| Faldetector | 1,416 | 19 days ago | 25 | apache-2.0 | Python | |||||
| Code for the paper: Detecting Photoshopped Faces by Scripting Photoshop | ||||||||||
| 3d Pointcloud | 1,374 | 5 days ago | 2 | Python | ||||||
| Papers and Datasets about Point Cloud. | ||||||||||
Mtl-Implem
This is a matlab implementation of the paper bellow: Learning Incoherent Sparse and Low-Rank Patterns from Multiple Tasks http://pages.cs.wisc.edu/~ji-liu/paper/Jianhui-Ji-TKDD.pdf
The script to run is called main. All the dataset, but Ar face dataset are available in the folder 'datasets'. Ar face dataset is too big to put in the archive. And also it is not public.
However one could ask for the dataset in here http://www2.ece.ohio-state.edu/~aleix/ARdatabase.html
Im the main script, the variable dataname allows one to choose the dataset to use. There is 3 choices: 'face' 'scene' 'school'
If 'face' is choosen, one should know that since we treat images, the algorithm is very time consuming. To avoid spending a day on training,'max_iter' is restrained to 1000.
The results are quite similar to the paper. However the parameters were not crossvalidated like in the paper, An heuristic choice of the parameters has been made.
The results for the feature extraction can be seen in the folder, feature extraction. Each picture shows the P (left) and Q (right) matrix learned. We can see that the sparse matrix captures details of the face. The low rank matrix on the other hand captures the general shape of the face. Example bellow:
For the classification results of the scene dataset, a screendhot is furnished bellow, however those result can be reproduced by runing main with scene dataset. We can see that those results are quite similar to the ones displayed in the paper.
