hub / github.com/tensorflow/models

github.com/tensorflow/models @v2.20.0 sqlite

repository ↗ · DeepWiki ↗ · release v2.20.0 ↗

13,275 symbols 41,438 edges 1,738 files 7,137 documented · 54%

README

Logo

Welcome to the Model Garden for TensorFlow

The TensorFlow Model Garden is a repository with a number of different implementations of state-of-the-art (SOTA) models and modeling solutions for TensorFlow users. We aim to demonstrate the best practices for modeling so that TensorFlow users can take full advantage of TensorFlow for their research and product development.

Directory	Description
official	• A collection of example implementations for SOTA models using the latest TensorFlow 2's high-level APIs

• Officially maintained, supported, and kept up to date with the latest TensorFlow 2 APIs by TensorFlow

• Reasonably optimized for fast performance while still being easy to read | | research | • A collection of research model implementations in TensorFlow 1 or 2 by researchers

• Maintained and supported by researchers | | community | • A curated list of the GitHub repositories with machine learning models and implementations powered by TensorFlow 2 |

Announcements

Date	News
June 17, 2020	Context R-CNN: Long Term Temporal Context for Per-Camera Object Detection released
May 21, 2020	Unifying Deep Local and Global Features for Image Search (DELG) code released
May 19, 2020	MobileDets: Searching for Object Detection Architectures for Mobile Accelerators released
May 7, 2020	MnasFPN with MobileNet-V2 backbone released for object detection
May 1, 2020	DELF: DEep Local Features updated to support TensorFlow 2.1
March 31, 2020	Introducing the Model Garden for TensorFlow 2 (Tweet)

Milestones

Date	Milestone
July 7, 2020

Contributions

If you want to contribute, please review the contribution guidelines.

License

Apache License 2.0

Core symbols most depended-on inside this repo

join

called by 906

official/core/base_trainer.py

info

called by 839

official/legacy/image_classification/dataset_factory.py

get

called by 481

official/projects/yolo/configs/yolo.py

update

called by 473

official/legacy/detection/evaluation/coco_evaluator.py

run

called by 231

official/core/train_lib.py

predict

called by 191

official/legacy/transformer/transformer.py

_setup

called by 185

official/benchmark/bert_benchmark.py

from_args

called by 171

official/modeling/hyperparams/base_config.py

Shape

Method 7,902

Function 2,891

Class 2,373

Route 109

Languages

Python100%

TypeScript1%

Modules by API surface

official/benchmark/keras_imagenet_benchmark.py157 symbols

official/nlp/data/classifier_data_lib.py140 symbols

official/vision/ops/augment.py116 symbols

official/vision/modeling/layers/nn_blocks.py91 symbols

official/projects/yolo/modeling/layers/nn_blocks.py82 symbols

official/vision/modeling/layers/nn_layers.py79 symbols

official/nlp/modeling/models/t5.py62 symbols

orbit/controller_test.py60 symbols

official/projects/qat/nlp/quantization/configs.py60 symbols

official/legacy/xlnet/xlnet_modeling.py57 symbols

official/benchmark/bert_squad_benchmark.py55 symbols

official/legacy/image_classification/augment.py54 symbols

Dependencies from manifests, versioned

@babel/core7.22.10 · 1×

@babel/plugin-transform-runtime7.22.10 · 1×

@babel/preset-env7.22.10 · 1×

autoprefixer10.4.15 · 1×

babel-eslint10.1.0 · 1×

babel-loader9.1.3 · 1×

browser-sync2.29.3 · 1×

chokidar-cli3.0.0 · 1×

core-js3.32.1 · 1×

cross-env7.0.3 · 1×

cssnano6.0.1 · 1×

es6-promise4.2.8 · 1×

For agents

$ claude mcp add models \
  -- python -m otcore.mcp_server <graph>

⬇ download graph artifact