{"id":26574281,"url":"https://github.com/avanishd-3/tf-neural-nets","last_synced_at":"2026-06-15T05:33:19.460Z","repository":{"id":279171466,"uuid":"937925584","full_name":"avanishd-3/tf-neural-nets","owner":"avanishd-3","description":"Neural networks written in TensorFlow","archived":false,"fork":false,"pushed_at":"2025-04-22T06:06:26.000Z","size":102219,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-05-05T22:40:09.534Z","etag":null,"topics":["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/avanishd-3.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,"zenodo":null}},"created_at":"2025-02-24T06:15:47.000Z","updated_at":"2025-12-20T01:56:14.000Z","dependencies_parsed_at":"2025-04-22T07:32:41.840Z","dependency_job_id":null,"html_url":"https://github.com/avanishd-3/tf-neural-nets","commit_stats":null,"previous_names":["avanishd-3/tf-neural-networks","avanishd-3/tf-neural-nets"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/avanishd-3/tf-neural-nets","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/avanishd-3%2Ftf-neural-nets","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/avanishd-3%2Ftf-neural-nets/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/avanishd-3%2Ftf-neural-nets/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/avanishd-3%2Ftf-neural-nets/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/avanishd-3","download_url":"https://codeload.github.com/avanishd-3/tf-neural-nets/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/avanishd-3%2Ftf-neural-nets/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34349925,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-15T02:00:07.085Z","response_time":63,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["tensorflow"],"created_at":"2025-03-23T01:39:55.324Z","updated_at":"2026-06-15T05:33:19.438Z","avatar_url":"https://github.com/avanishd-3.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# tf-neural-nets\nCollection of neural netwworks made with TensorFlow and Keras.\n\nEach network also includes the model weights in a .keras file.\n\n\n## Usage Instructions\n\n```\ngit clone https://github.com/avanishd-3/tf-neural-networks.git\n```\n\nThen run the notebooks\n\nModels can also be loaded with\n\n```\nmodel = tf.keras.models.load_model(\"model_filename.keras\")\n```\n\n## Model Quality\n\nModel positions the best models (for their respective tasks) would have on the [Papers with Code](https://paperswithcode.com/) leaderboard as of April 7, 2025\n\n\n| Model             | Accuracy (%) | Ranking |\n| ----------------- | ------------ | ------------- |\n| Fashion MNIST CNN | 91.78        | 15          |\n| MNIST ANN         | 98.44        | 53          |\n| CIFAR-10 CNN      | 81.12        | 245         |\n\n\n## ANNs\n\nThere are 3 models here.\n\n1. Classification model based on the Fashion MNIST dataset (~88.43% accuracy).\n2. Regression model based on the Auto MPG dataset.\n3. High-accuracy classification model based on the MNIST dataset (~98.44% accuracy).\n4. Classification model based on the CIFAR-10 dataset (~49.20% accuracy, which is pretty high for a non-CNN model on an image-recognition dataset).\n\n## CNNs\n\nThere are 3 models here.\n\n1. Classification model based on the Fashion MNIST dataset (~91.78% accuracy).\n2. Classification model based on the CIFAR-10 dataset (~81.12% accuracy).\n   - Note: I made a [Transformer-based model](https://huggingface.co/avanishd/vit-base-patch16-224-in21k-finetuned-cifar10) that has a 97.93% accuray after only 1 epoch of training.\n4. Transfer learning (based on Xception) binary classification model trained on TensorFlow cat or dog dataset (~95.53% accuracy).\n    - No weight for this one, because it exceeds the GitHub file size.\n    - Training is pretty quick, though, because most of the training has already been done.\n\n## VAE\n\nThere is 1 model here.\n\n1. Image generation VAE model trained on Fashion MNIST\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Favanishd-3%2Ftf-neural-nets","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Favanishd-3%2Ftf-neural-nets","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Favanishd-3%2Ftf-neural-nets/lists"}