tensorflow /models
Models and examples built with TensorFlow
★ 77,629⑂ 44,734👁 2,633⑃ 3,905● 7,319▤ 51
-2
日增长
-7
周增长
77,629
stars
44,734
forks
2,633
watchers
3,905
prs
7,319
issues
51
releases
README
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. To improve the transparency and reproducibility of our models, training logs on TensorBoard.dev are also provided for models to the extent possible though not all models are suitable. | 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 For more details on the capabilities, check the guide on the Model-garden| | 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 | | orbit | • A flexible and lightweight library that users can easily use or fork when writing customized training loop code in TensorFlow 2.x. It seamlessly integrates with tf.distribute and supports running on different device types (CPU, GPU, and TPU). | Installation To install the current release of tensorflow-models, please follow any one of the methods described below. Method 1: Install the TensorFlow Model Garden pip package tf-models-official is the stable Model Garden package. Please check out the releases to see what are available modules. pip3 will install all models and dependencies automatically. shell pip3 install tf-models-official Please check out our examples: - basic library import - nlp model building to learn how to use a PIP package. Note that tf-models-official may not include the latest changes in the master branch of this github repo. To include latest changes, you may install tf-models-nightly, which is the nightly Model Garden package created daily automatically. shell pip3 install tf-models-nightly Method 2: Clone the source 1. Clone the GitHub repository: shell git clone https://github.com/tensorflow/models.git 2. Add the top-level /models folder to the Python path. shell export PYTHONPATH=$PYTHONPATH:/path/to/models If you are using in a Windows environment, you may need to use the following command with PowerShell: shell $env:PYTHONPATH += ":\path\to\models" If you are using a Colab notebook, please set the Python path with os.environ. python import os os.environ['PYTHONPATH'] += ":/path/to/models" 3. Install other dependencies shell pip3 install --user -r models/official/requirements.txt Finally, if you are using nlp packages, please also inst
Top issues
#3730[deeplab] Training deeplab model with ADE20K dataset99 comments · 2018-03-24#3196[SSD] Small object detection96 comments · 2018-01-18#7640 Invoking ptxas not supported on Windows89 comments · 2019-10-10#6253LSTM Object Detection Model Does Not Run79 comments · 2019-02-22#9371[TF2 Object Detection] Converting SSD models into .tflite uint8 format69 comments · 2020-10-13#9706NotImplementedError: Cannot convert a symbolic Tensor (strided_slice:0) to a numpy array.67 comments · 2021-02-05#3739deeplab doesn't predict correctly the segmentation masks66 comments · 2018-03-25#5421Multiple GPU in model_main.py (since there is no more train.py)63 comments · 2018-10-02
Discussions
#13577Feasibility to evaluate DeepLab-MobileNetV3 model(s)0 comments · 2025-07-10#13570Is Tensorflow Model Garden Deprecated?2 comments · 2025-05-16#13549How can we load the checkpoint from movinet to fine tune?2 comments · 2025-03-19#13546!protoc object_detection/protos/*.proto --python_out=. !pip install .0 comments · 2025-03-05#11388where to find the sample input and the expected output data for the v3-small_224_1.0_uint8.tflite model?2 comments · 2024-11-24#11338ultralytics 8.0.232 has requirement numpy>=1.22.2, but you'll have numpy 1.19.5 which is incompatible.2 comments · 2024-11-19#11272Model Garden : How to continue training with tfm.core.train_lib.run_experiment()?1 comments · 2024-10-29#11262where to find quantized mobilenet v2 with a width of 0.25 or 0.51 comments · 2024-09-24
Latest release
TensorFlow Official Models 2.20.0 v2.20.0 2026-02-11This release of the Official Models targets TensorFlow 2.20.0 Note that Research/tutorial/sample models have been removed. Release branch is: https://github.com/tensorflow/models/tree/r2.20.0