Top AI Repos — open-source AI, indexed and scored

Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.

leondgarse/keras_cv_attention_models

Keras beit,caformer,CMT,CoAtNet,convnext,davit,dino,efficientdet,edgenext,efficientformer,efficientnet,eva,fasternet,fastervit,fastvit,flexivit,gcvit,ghostnet,gpvit,hornet,hiera,iformer,inceptionnext,lcnet,levit,maxvit,mobilevit,moganet,nat,nfnets,pvt,swin,tinynet,tinyvit,uniformer,volo,vanillanet,yolor,yolov7,yolov8,yolox,gpt2,llama2, alias kecam

54MITPython

View on GitHub

Stars: 627
Forks: 97
Watchers: 21
Open issues: 8
Contributors: 5

Star history, last 90 days— over 5 snapshots

2026-07-24 · 6272026-08-06 · 627

Star history, last 90 days
Date	Stars
2026-07-24	627
2026-07-25	627
2026-07-28	627
2026-07-30	627
2026-08-06	627

Today

— stars today

This week

— stars this week

This month

— stars this month

Momentum

0.0

growth rate 0.00%/day

From the README

# ___Keras_cv_attention_models___
***
- **WARNING: currently NOT compatible with `keras 3.x`, if using `tensorflow>=2.16.0`, needs to install `pip install tf-keras~=$(pip show tensorflow | awk -F ': ' '/Version/{print $2}')` manually. While importing, import this package ahead of Tensorflow, or set `export TF_USE_LEGACY_KERAS=1`.**
- **It's not recommended downloading and loading model from h5 file directly, better building model and loading weights like `import kecam; mm = kecam.models.LCNet050()`.**
- **coco_train_script.py for TF is still under testing...**
<!-- TOC depthFrom:1 depthTo:6 withLinks:1 updateOnSave:1 orderedList:0 -->

- [___>>>> Roadmap and todo list <<<<___](https://github.com/leondgarse/keras_cv_attention_models/wiki/Roadmap)
- [General Usage](#general-usage)
  - [Basic](#basic)
  - [T4 Inference](#t4-inference)
  - [Layers](#layers)
  - [Model surgery](#model-surgery)
  - [ImageNet training and evaluating](#imagenet-training-and-evaluating)
  - [COCO training and evaluating](#coco-training-and-evaluating)
  - [CLIP training and evaluating](#clip-training-and-evaluating)
  - [Text training](#text-training)
  - [DDPM training](#ddpm-training)
  - [Visualizing](#visualizing)
  - [TFLite Conversion](#tflite-conversion)
  - [Using PyTorch as backend](#using-pytorch-as-backend)
  - [Using keras core as backend](#using-keras-core-as-backend)
- [Recognition Models](#recognition-models)
  - [AotNet](#aotnet)
  - [BEiT](#beit)
  - [BEiTV2](#beitv2)
  - [BotNet](#botnet)
  - [CAFormer](#caformer)
  - [CMT](#cmt)
  - [CoaT](#coat)
  - [CoAtNet](#coatnet)
  - [ConvNeXt](#convnext)
  - [ConvNeXtV2](#convnextv2)
  - [CoTNet](#cotnet)
  - [CSPNeXt](#cspnext)
  - [DaViT](#davit)
  - [DiNAT](#dinat)
  - [DINOv2](#dinov2)
  - [EdgeNeXt](#edgenext)
  - [EfficientFormer](#efficientformer)
  - [EfficientFormerV2](#efficientformerv2)
  - [EfficientNet](#efficientnet)
  - [EfficientNetEdgeTPU](#efficientnetedgetpu)
  - [EfficientNetV2](#efficientnetv2)
  - [EfficientViT_B](#efficientvit_b)
  - [EfficientViT_M](#efficientvit_m)
  - [EVA](#eva)
  - [EVA02](#eva02)
  - [FasterNet](#fasternet)
  - [FasterViT](#fastervit)
  - [FastViT](#fastvit)
  - [FBNetV3](#fbnetv3)
  - [FlexiViT](#flexivit)
  - [GCViT](#gcvit)
  - [GhostNet](#ghostnet)
  - [GhostNetV2](#ghostnetv2)
  - [GMLP](#gmlp)
  - [GPViT](#gpvit)
  - [HaloNet](#halonet)
  - [Hiera](#hiera)
  - [HorNet](#hornet)
  - [IFormer](#iformer)
  - [InceptionNeXt](#inceptionnext)
  - [LCNet](#lcnet)
  - [LeViT](#levit)
  - [MaxViT](#maxvit)
  - [MetaTransFormer](#metatransformer)
  - [MLP mixer](#mlp-mixer)
  - [MobileNetV3](#mobilenetv3)
  - [MobileViT](#mobilevit)
  - [MobileViT_V2](#mobilevit_v2)
  - [MogaNet](#moganet)
  - [NAT](#nat)
  - [NFNets](#nfnets)
  - [PVT_V2](#pvt_v2)
  - [RegNetY](#regnety)
  - [RegNetZ](#regnetz)
  - [RepViT](#repvit)
  - [ResMLP](#resmlp)
  - [ResNeSt](#resnest)
  - [ResNetD](#resnetd)
  - [ResNetQ](#resnetq)
  - [ResNeXt](#resnext)
  - [SwinTransformerV2](#swintransformerv2)
  - [TinyNet](#tinynet)
  - [TinyViT](#tinyvit)
  - [UniFormer](#uniformer)
  - [VanillaNet](#vanillanet)
  - [ViT-5](#vit-5)
  - [VOLO](#volo)
  - [WaveMLP](#wavemlp)
- [Detection Models](#detection-models)
  - [EfficientDet](#efficientdet)
  - [YOLO_NAS](#yolo_nas)
  - [YOLOR](#yolor)
  - [YOLOV7](#yolov7)
  - [YOLOV8](#yolov8)
  - [YOLOX](#yolox)
- [Language Models](#language-models)
  - [GPT2](#gpt2)
  - [LLaMA2](#llama2)
- [Stable Diffusion](#stable-diffusion)
- [Segmentation Models](#segmentation-models)
  - [YOLOV8 Segmentation](#yolov8-segmentation)
  - [Segment Anything](#segment-anything)
- [Licenses](#licenses)
- [Citing](#citing)

<!-- /TOC -->
***

# General Usage
## Basic
  - **Default import** will not specific these while using them in READMEs.
    ```py
    import os
    import sys
    import tensorflow as tf
    import numpy as np
    import pandas as pd
    import matplotlib.pyplot as plt
    from tensorflow import keras
    ```
  - Install as pip package. `kec

Excerpt of 183,720 characters

Read on GitHub

Top contributors5 shown

leondgarse
1.1k
awsaf49
3
dcleres
2
AminHP
Mohammad Amin Haghpanah · @koala-team
1
gjp4tw
1

Quality score

Would you bet a product on this? Bounded 0–100 and slow moving.

54/10054

Maintenance: 45%; How recently the default branch was pushed to
Releases: 10%; Recency and cadence of tagged releases
Community: 18%; Contributor breadth and bus factor
Issue backlog: 85%; Open issues measured against the size of the audience
Documentation: 100%; README depth, plus a homepage and topics
Licensing: 100%; How freely the code can be adopted

What to know before adopting

No release in over a year
Bus factor of 1 — one contributor dominates
Usable in commercial products with attribution.

Details

Created: 5 years ago
Last push: 6 months ago
Last release: 3 years ago
Release tag: cspnext
Releases in the last year: 0
Default branch: main
Size: 4.2k KB
Owner type: User
Owner location: —
Discovered via: topic:tensorflow
First indexed: 13 days ago
Last synced: 12 days ago

leondgarse/keras_cv_attention_models

54MITPython

View on GitHub

Stars: 627
Forks: 97
Watchers: 21
Open issues: 8
Contributors: 5

Star history, last 90 days— over 5 snapshots

2026-07-24 · 6272026-08-06 · 627

Star history, last 90 days
Date	Stars
2026-07-24	627
2026-07-25	627
2026-07-28	627
2026-07-30	627
2026-08-06	627

Today

— stars today

This week

— stars this week

This month

— stars this month

Momentum

0.0

growth rate 0.00%/day

From the README

# ___Keras_cv_attention_models___
***
- **WARNING: currently NOT compatible with `keras 3.x`, if using `tensorflow>=2.16.0`, needs to install `pip install tf-keras~=$(pip show tensorflow | awk -F ': ' '/Version/{print $2}')` manually. While importing, import this package ahead of Tensorflow, or set `export TF_USE_LEGACY_KERAS=1`.**
- **It's not recommended downloading and loading model from h5 file directly, better building model and loading weights like `import kecam; mm = kecam.models.LCNet050()`.**
- **coco_train_script.py for TF is still under testing...**
<!-- TOC depthFrom:1 depthTo:6 withLinks:1 updateOnSave:1 orderedList:0 -->

- [___>>>> Roadmap and todo list <<<<___](https://github.com/leondgarse/keras_cv_attention_models/wiki/Roadmap)
- [General Usage](#general-usage)
  - [Basic](#basic)
  - [T4 Inference](#t4-inference)
  - [Layers](#layers)
  - [Model surgery](#model-surgery)
  - [ImageNet training and evaluating](#imagenet-training-and-evaluating)
  - [COCO training and evaluating](#coco-training-and-evaluating)
  - [CLIP training and evaluating](#clip-training-and-evaluating)
  - [Text training](#text-training)
  - [DDPM training](#ddpm-training)
  - [Visualizing](#visualizing)
  - [TFLite Conversion](#tflite-conversion)
  - [Using PyTorch as backend](#using-pytorch-as-backend)
  - [Using keras core as backend](#using-keras-core-as-backend)
- [Recognition Models](#recognition-models)
  - [AotNet](#aotnet)
  - [BEiT](#beit)
  - [BEiTV2](#beitv2)
  - [BotNet](#botnet)
  - [CAFormer](#caformer)
  - [CMT](#cmt)
  - [CoaT](#coat)
  - [CoAtNet](#coatnet)
  - [ConvNeXt](#convnext)
  - [ConvNeXtV2](#convnextv2)
  - [CoTNet](#cotnet)
  - [CSPNeXt](#cspnext)
  - [DaViT](#davit)
  - [DiNAT](#dinat)
  - [DINOv2](#dinov2)
  - [EdgeNeXt](#edgenext)
  - [EfficientFormer](#efficientformer)
  - [EfficientFormerV2](#efficientformerv2)
  - [EfficientNet](#efficientnet)
  - [EfficientNetEdgeTPU](#efficientnetedgetpu)
  - [EfficientNetV2](#efficientnetv2)
  - [EfficientViT_B](#efficientvit_b)
  - [EfficientViT_M](#efficientvit_m)
  - [EVA](#eva)
  - [EVA02](#eva02)
  - [FasterNet](#fasternet)
  - [FasterViT](#fastervit)
  - [FastViT](#fastvit)
  - [FBNetV3](#fbnetv3)
  - [FlexiViT](#flexivit)
  - [GCViT](#gcvit)
  - [GhostNet](#ghostnet)
  - [GhostNetV2](#ghostnetv2)
  - [GMLP](#gmlp)
  - [GPViT](#gpvit)
  - [HaloNet](#halonet)
  - [Hiera](#hiera)
  - [HorNet](#hornet)
  - [IFormer](#iformer)
  - [InceptionNeXt](#inceptionnext)
  - [LCNet](#lcnet)
  - [LeViT](#levit)
  - [MaxViT](#maxvit)
  - [MetaTransFormer](#metatransformer)
  - [MLP mixer](#mlp-mixer)
  - [MobileNetV3](#mobilenetv3)
  - [MobileViT](#mobilevit)
  - [MobileViT_V2](#mobilevit_v2)
  - [MogaNet](#moganet)
  - [NAT](#nat)
  - [NFNets](#nfnets)
  - [PVT_V2](#pvt_v2)
  - [RegNetY](#regnety)
  - [RegNetZ](#regnetz)
  - [RepViT](#repvit)
  - [ResMLP](#resmlp)
  - [ResNeSt](#resnest)
  - [ResNetD](#resnetd)
  - [ResNetQ](#resnetq)
  - [ResNeXt](#resnext)
  - [SwinTransformerV2](#swintransformerv2)
  - [TinyNet](#tinynet)
  - [TinyViT](#tinyvit)
  - [UniFormer](#uniformer)
  - [VanillaNet](#vanillanet)
  - [ViT-5](#vit-5)
  - [VOLO](#volo)
  - [WaveMLP](#wavemlp)
- [Detection Models](#detection-models)
  - [EfficientDet](#efficientdet)
  - [YOLO_NAS](#yolo_nas)
  - [YOLOR](#yolor)
  - [YOLOV7](#yolov7)
  - [YOLOV8](#yolov8)
  - [YOLOX](#yolox)
- [Language Models](#language-models)
  - [GPT2](#gpt2)
  - [LLaMA2](#llama2)
- [Stable Diffusion](#stable-diffusion)
- [Segmentation Models](#segmentation-models)
  - [YOLOV8 Segmentation](#yolov8-segmentation)
  - [Segment Anything](#segment-anything)
- [Licenses](#licenses)
- [Citing](#citing)

<!-- /TOC -->
***

# General Usage
## Basic
  - **Default import** will not specific these while using them in READMEs.
    ```py
    import os
    import sys
    import tensorflow as tf
    import numpy as np
    import pandas as pd
    import matplotlib.pyplot as plt
    from tensorflow import keras
    ```
  - Install as pip package. `kec

Excerpt of 183,720 characters

Read on GitHub

Top contributors5 shown

leondgarse
1.1k
awsaf49
3
dcleres
2
AminHP
Mohammad Amin Haghpanah · @koala-team
1
gjp4tw
1

Quality score

Would you bet a product on this? Bounded 0–100 and slow moving.

54/10054

Maintenance: 45%; How recently the default branch was pushed to
Releases: 10%; Recency and cadence of tagged releases
Community: 18%; Contributor breadth and bus factor
Issue backlog: 85%; Open issues measured against the size of the audience
Documentation: 100%; README depth, plus a homepage and topics
Licensing: 100%; How freely the code can be adopted

What to know before adopting

No release in over a year
Bus factor of 1 — one contributor dominates
Usable in commercial products with attribution.

Details

Created: 5 years ago
Last push: 6 months ago
Last release: 3 years ago
Release tag: cspnext
Releases in the last year: 0
Default branch: main
Size: 4.2k KB
Owner type: User
Owner location: —
Discovered via: topic:tensorflow
First indexed: 13 days ago
Last synced: 12 days ago

Top AI Repos — open-source AI, indexed and scored

leondgarse/keras_cv_attention_models

From the README

Top contributors5 shown

Quality score

What to know before adopting

Categories

Details

leondgarse/keras_cv_attention_models

From the README

Top contributors5 shown

Quality score

What to know before adopting

Categories

Details

Top AI Repos — open-source AI, indexed and scored

Trend

From the README

Top contributors5 shown

Quality score

What to know before adopting

Categories

Details

Trend

From the README

Top contributors5 shown

Quality score

What to know before adopting

Categories

Details