{"id":20147852,"url":"https://github.com/suragnair/im2latex","last_synced_at":"2025-04-09T19:43:21.303Z","repository":{"id":107078794,"uuid":"76098921","full_name":"suragnair/Im2LaTeX","owner":"suragnair","description":"An implementation of the Show, Attend and Tell paper in Tensorflow, for the OpenAI Im2LaTeX suggested problem","archived":false,"fork":false,"pushed_at":"2016-12-11T10:44:36.000Z","size":60,"stargazers_count":17,"open_issues_count":0,"forks_count":3,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-03-23T21:45:49.010Z","etag":null,"topics":["attention","attention-mechanism","deep-learning","show-and-tell","show-attend-and-tell","tensorflow"],"latest_commit_sha":null,"homepage":null,"language":"Python","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/suragnair.png","metadata":{"files":{"readme":"README.md","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":"2016-12-10T07:55:22.000Z","updated_at":"2025-01-12T23:23:21.000Z","dependencies_parsed_at":null,"dependency_job_id":"b543f91c-e150-48c5-b1fd-1e2ec9448d0c","html_url":"https://github.com/suragnair/Im2LaTeX","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/suragnair%2FIm2LaTeX","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/suragnair%2FIm2LaTeX/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/suragnair%2FIm2LaTeX/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/suragnair%2FIm2LaTeX/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/suragnair","download_url":"https://codeload.github.com/suragnair/Im2LaTeX/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248101449,"owners_count":21047973,"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":["attention","attention-mechanism","deep-learning","show-and-tell","show-attend-and-tell","tensorflow"],"created_at":"2024-11-13T22:32:26.516Z","updated_at":"2025-04-09T19:43:21.299Z","avatar_url":"https://github.com/suragnair.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Im2LaTeX\nAn implementation of the  Show, Attend and Tell (Xu, Kelvin et. al., 2016) paper in TensorFlow, for the OpenAI Im2LaTeX suggested problem.\n\n- The crux of the model is contained in cnn_enc_gru_dec_attn.py that uses the embedding attention decoder from TensorFlow to attend on the output of the CNN.\n\n- test_cnn_enc_gru_dec_attn.py has a method to extract the attention coefficients for each time step, for which I have overwritten some TensorFlow functions from seq2seq.py.\n\n- An example of attention map over an input LaTeX formula image, as the decoder outputs each token.\n\n![alt tag](https://raw.githubusercontent.com/suragnair/Im2LaTeX/master/attn.png)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsuragnair%2Fim2latex","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsuragnair%2Fim2latex","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsuragnair%2Fim2latex/lists"}