{"id":15222295,"url":"https://github.com/googlecloudplatform/tf-estimator-tutorials","last_synced_at":"2025-05-16T14:07:49.423Z","repository":{"id":66041360,"uuid":"117577327","full_name":"GoogleCloudPlatform/tf-estimator-tutorials","owner":"GoogleCloudPlatform","description":"This repository includes tutorials on how to use the TensorFlow estimator APIs to perform various ML tasks, in a systematic and standardised way","archived":false,"fork":false,"pushed_at":"2024-08-20T16:11:30.000Z","size":14190,"stargazers_count":670,"open_issues_count":5,"forks_count":233,"subscribers_count":69,"default_branch":"master","last_synced_at":"2025-05-16T14:07:43.118Z","etag":null,"topics":["machine-learning","python","tensorflow"],"latest_commit_sha":null,"homepage":"https://www.tensorflow.org/programmers_guide/estimators","language":"Jupyter Notebook","has_issues":false,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/GoogleCloudPlatform.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","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":"2018-01-15T17:54:01.000Z","updated_at":"2025-04-17T19:25:39.000Z","dependencies_parsed_at":"2024-11-21T09:02:27.370Z","dependency_job_id":"4ea6ac4c-fec2-494b-9f9d-1c81aa2e8f2d","html_url":"https://github.com/GoogleCloudPlatform/tf-estimator-tutorials","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/GoogleCloudPlatform%2Ftf-estimator-tutorials","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GoogleCloudPlatform%2Ftf-estimator-tutorials/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GoogleCloudPlatform%2Ftf-estimator-tutorials/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GoogleCloudPlatform%2Ftf-estimator-tutorials/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/GoogleCloudPlatform","download_url":"https://codeload.github.com/GoogleCloudPlatform/tf-estimator-tutorials/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254544146,"owners_count":22088807,"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":["machine-learning","python","tensorflow"],"created_at":"2024-09-28T15:11:29.191Z","updated_at":"2025-05-16T14:07:44.415Z","avatar_url":"https://github.com/GoogleCloudPlatform.png","language":"Jupyter Notebook","readme":"# TensorFlow Estimator APIs Tutorials\n\n## Setup\nPlease follow the directions in INSTALL if you need help setting up your environment.\n\n## Theses tutorials use the TF estimator APIs to cover:\n\n* Various ML tasks, currently covering:\n  * Classification\n  * Regression\n  * Clustering (k-means)\n  * Time-series Analysis (AR Models)\n  * Dimensionality Reduction (Autoencoding)\n  * Sequence Models (RNN and LSTMs)\n  * Image Analysis (CNN for Image Classification)\n  * Text Analysis (Text Classification with embeddings, CNN, and RNN)\n*  How to use **canned estimators**  to train ML models.\n\n* How to use **tf.Transform** for preprocessing and feature engineering (TF v1.7)\n\n* Implement **TensorFlow Model Analysis (TFMA)** to assess the quality of the mode (TF v1.7)\n\n* How to use **tf.Hub** text feature column embeddings (TF v1.7)\n\n* How to implement **custom estimators** (model_fn \u0026 EstimatorSpec).\n\n* A standard **metadata-driven** approach to build the model **feature_column**(s) including:\n  * **numerical** features\n  * **categorical** features with **vocabulary**,\n  * **categorical** features **hash bucket**, and\n  * **categorical** features with **identity**\n\n* Data **input pipelines** (input_fn) using:\n  * tf.estimator.inputs.**pandas_input_fn**,\n  * tf.train.**string_input_producer**, and\n  * tf.data.**Dataset** APIs to read both **.csv** and **.tfrecords** (tf.example) data files\n  * tf.contrib.timeseries.**RandomWindowInputFn** and **WholeDatasetInputFn** for time-series data\n  * Feature **preprocessing** and **creation** as part of reading data (input_fn), for example, sin, sqrt, polynomial expansion, fourier transform, log, boolean comparisons, euclidean distance, custom formulas, etc.\n\n* A standard approach to prepare **wide** (sparse) and **deep** (dense) feature_column(s) for Wide and Deep **DNN Liner Combined Models**\n\n* The use of **normalizer_fn** in numeric_column() to **scale** the numeric features using pre-computed statistics (for Min-Max or Standard scaling)\n\n* The use of **weight_column** in the canned estimators, as well as in **loss function** in custom estimators.\n\n* Implicit **Feature Engineering** as part of defining feature_colum(s), including:\n  * crossing\n  * embedding\n  * indicators (encoding categorical features), and\n  * bucketization\n\n*  How to use the  tf.contrib.learn.**experiment** APIs to train, evaluate, and export models\n\n* Howe to use the tf.estimator.**train_and_evaluate** function (along with trainSpec \u0026 evalSpec) train, evaluate, and export models\n\n* How to use **tf.train.exponential_decay** function as a learning rate scheduler\n\n* How to **serve** exported model (export_savedmodel) using **csv** and **json** inputs\n\n## Coming Soon:\n* Early-stopping implementation\n* DynamicRnnEstimator and the use of variable-length sequences\n* Collaborative Filtering for Recommendation Models\n* Text Analysis (Topic Models, etc.)\n* Keras examples\n\n\n\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgooglecloudplatform%2Ftf-estimator-tutorials","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgooglecloudplatform%2Ftf-estimator-tutorials","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgooglecloudplatform%2Ftf-estimator-tutorials/lists"}