{"id":17474387,"url":"https://github.com/p-baleine/qanet-tensorflow","last_synced_at":"2026-05-10T05:03:02.196Z","repository":{"id":141455346,"uuid":"131568542","full_name":"p-baleine/QANet-Tensorflow","owner":"p-baleine","description":"An implementation of QANet with Tensorflow and Keras.","archived":false,"fork":false,"pushed_at":"2018-09-19T00:11:25.000Z","size":1815,"stargazers_count":0,"open_issues_count":1,"forks_count":0,"subscribers_count":3,"default_branch":"master","last_synced_at":"2024-10-18T20:49:41.005Z","etag":null,"topics":["keras","nlp","squad","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/p-baleine.png","metadata":{"files":{"readme":"README.org","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2018-04-30T07:42:31.000Z","updated_at":"2018-08-16T09:39:24.000Z","dependencies_parsed_at":null,"dependency_job_id":"2177c9b0-2952-4fb1-bf57-e1ac81609699","html_url":"https://github.com/p-baleine/QANet-Tensorflow","commit_stats":{"total_commits":72,"total_committers":1,"mean_commits":72.0,"dds":0.0,"last_synced_commit":"cca9794cca98d0a272b1ee0a0ff1a1d45f74f210"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/p-baleine/QANet-Tensorflow","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/p-baleine%2FQANet-Tensorflow","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/p-baleine%2FQANet-Tensorflow/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/p-baleine%2FQANet-Tensorflow/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/p-baleine%2FQANet-Tensorflow/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/p-baleine","download_url":"https://codeload.github.com/p-baleine/QANet-Tensorflow/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/p-baleine%2FQANet-Tensorflow/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":265716306,"owners_count":23816354,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["keras","nlp","squad","tensorflow"],"created_at":"2024-10-18T18:09:17.532Z","updated_at":"2026-05-10T05:03:02.079Z","avatar_url":"https://github.com/p-baleine.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"#+TITLE: QANet-Tensorflow\n\nAn implementation of [[https://arxiv.org/abs/1804.09541][QANet]] with [[https://www.tensorflow.org/][Tensorflow]] and [[https://keras.io/][Keras]].\n\nThis implementation reaches EM/F1 = 66/77 in 50k steps. (The original paper reaches EM/F1 = 73.6/82.7 in 150k steps. I think there is still room for improvement.)\n\n** Requirements\n\n- Docker\n- [[https://github.com/NVIDIA/nvidia-docker][nvidia-docker]]\n\n** Usage\n\n*** Build container\n\nFirst, clone this repository.\n\n#+BEGIN_SRC bash\ngit clone https://github.com/p-baleine/keras-QANet.git\n#+END_SRC\n\nThen build the docker image.\n\n#+BEGIN_SRC bash\ndocker build -t qanet .\n#+END_SRC\n\nThe following instructions assume that you've logged in to this container. To log in to this continer, run:\n\n#+BEGIN_SRC bash\ndocker run --runtime nvidia --rm --name qanet -it -v $(pwd):/qanet -p 6006:6006 -p 8888:8888 qanet\n#+END_SRC\n\n*** Download data\n\n**** Glove\n\nDownload and save [[https://www.kaggle.com/thanakomsn/glove6b300dtxt/version/1#_=_:][pre-trained Glove data]] in word2vec directory.\n\n**** SQuAD\n\nDownload and save train-v1.1.json and dev-1.1.json in data directory from [[https://rajpurkar.github.io/SQuAD-explorer/][SQuAD]].\n\n*** Preprocessing data\n\nTo preprocess data, run:\n\n#+BEGIN_SRC bash\nmake\n#+END_SRC\n\n*** Training\n\n#+BEGIN_SRC bash\nmake train\n#+END_SRC\n\n*** Evaluation\n\n=evaluation= target will calcurate exact-match score on =data/dev-v1.1.json=.\n\n#+BEGIN_SRC bash\nmake evaluate\n#+END_SRC\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fp-baleine%2Fqanet-tensorflow","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fp-baleine%2Fqanet-tensorflow","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fp-baleine%2Fqanet-tensorflow/lists"}