![]() Layers.py: Including the encoder layer, propagator layer, and Aggregator layer of the GMN model. It will take XXX.test_graphs in each repository directory to test the model. Note: XXX can be remove'_N1, remove_title_N1, remove_body_N1. It will take XXX.train_graphs and XXX.train_val_graphs in the data/clf directory to train the model. Then remove_XXX_N.test_graphs will be generated in the each repository directory. The N2 indicates the graph building of which repository. inpaint 8.0: hwtu-qacw-elmn-svgp-aaai-itgp. folderico 6.2.x: fkaa-hawo-mbry-fhev-ukaj-dyhv-xwwa-pafp: 5. The N1 indicates the sliding window size used to build the graph. duphunter 2.0: qrrd-odny-djei-cabc-aivn-eptp-dgat-jswb: 4. It will take xxx_pull_info_X.txt and xxx_pull_info_y.txt files from each repository directory to build the testing data graph. The program automatically detects series of photos taken with continuous shooting or locates similar images based on their content. It scans photos on a computer and gets rid of all duplicates leaving only the best images in each group of similar pictures. Where N represents the sliding window size. /rebates/&252fduphunter-20-download. DupHunter enables new smart ways of finding duplicate images. Remove_XXX_N.train_graphs, remove_XXX_N.train_val_graphs The N1 indicates the sliding window size used to build the graph, then two graph files will be generated in the data/clf directory, as follows: It will take xxx_pull_info_X.txt and xxx_pull_info_y.txt files from data/clf directory to build the training data graph. /rebates/&252fduphunter-20-download. The third parameter N1 indicates the dataset size of the non-duplicate PR pairs used for training. The GMN indicates which model to use(GMN or Adaboost). Teorex FolderIco - Folder Color Changer v5.1 (86x&64x) + Crack.rar 10.91MB Teorex DupHunter - Duplicate Photo Finder v 2.0 (86x&64x) +. It will generate xxx_pull_info_X.txt and xxx_pull_info_y.txt files which include all data needed to build graph. Third, run getGraph_repo_test_data.py to get the testing data graph įourth, run gmn/train.py to train the model įifth, run gmn/getResult.py to get the model result. Second, run getGraph_train_data.py to get the training data graph ![]() If you want to use our model quickly, five steps need to be done.įirst, run getData.py to get the data information file "A dataset of duplicate pull-requests in github." Proceedings of the 15th International Conference on Mining Software Repositories. Dup-Hunter Dup-Hunter: Detecting Duplicate Contributions in Fork-Based Development
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |