balavenkatesh3322

Professional software vendor delivering innovative solutions on the Softono platform. Specialized in both open-source and proprietary software development.

Visit Website

Total Products

Software by balavenkatesh3322

Open Source

CV-pretrained-model

![Maintenance](https://img.shields.io/badge/Maintained%3F-YES-green.svg) ![GitHub](https://img.shields.io/badge/Release-PROD-yellow.svg) ![GitHub](https://img.shields.io/badge/Languages-MULTI-blue.svg) ![GitHub](https://img.shields.io/badge/License-MIT-lightgrey.svg) # Computer Vision Pretrained Models ![CV logo](https://github.com/balavenkatesh3322/CV-pretrained-model/blob/master/logo.jpg) ## What is pre-trained Model? A pre-trained model is a model created by some one else to solve a similar problem. Instead of building a model from scratch to solve a similar problem, we can use the model trained on other problem as a starting point. A pre-trained model may not be 100% accurate in your application. For example, if you want to build a self learning car. You can spend years to build a decent image recognition algorithm from scratch or you can take inception model (a pre-trained model) from Google which was built on [ImageNet](http://www.image-net.org/) data to identify images in those pictures. ## Other Pre-trained Models * [NLP Pre-trained Models](https://github.com/balavenkatesh3322/NLP-pretrained-model). * [Audio and Speech Pre-trained Models](https://github.com/balavenkatesh3322/audio-pretrained-model) ## Model Deployment library * [Model Serving](https://github.com/balavenkatesh3322/model_deployment) ### Framework * [Tensorflow](#tensorflow) * [Keras](#keras) * [PyTorch](#pytorch) * [Caffe](#caffe) * [MXNet](#mxnet) ### Model visualization You can see visualizations of each model's network architecture by using [Netron](https://github.com/lutzroeder/Netron). ![CV logo](https://github.com/balavenkatesh3322/CV-pretrained-model/blob/master/netron.png) ### Tensorflow <a name="tensorflow"/> | Model Name | Description | Framework | License | | :---: | :---: | :---: | :---: | | [ObjectDetection]( https://github.com/tensorflow/models/tree/master/research/object_detection) | Localizing and identifying multiple objects in a single image.| `Tensorflow`| [Apache License]( https://raw.githubusercontent.com/tensorflow/models/master/LICENSE ) | [Mask R-CNN]( https://github.com/matterport/Mask_RCNN) | The model generates bounding boxes and segmentation masks for each instance of an object in the image. It's based on Feature Pyramid Network (FPN) and a ResNet101 backbone. | `Tensorflow`| [The MIT License (MIT)]( https://raw.githubusercontent.com/matterport/Mask_RCNN/master/LICENSE ) | [Faster-RCNN]( https://github.com/smallcorgi/Faster-RCNN_TF) | This is an experimental Tensorflow implementation of Faster RCNN - a convnet for object detection with a region proposal network. | `Tensorflow`| [MIT License]( https://raw.githubusercontent.com/smallcorgi/Faster-RCNN_TF/master/LICENSE ) | [YOLO TensorFlow]( https://github.com/gliese581gg/YOLO_tensorflow) | This is tensorflow implementation of the YOLO:Real-Time Object Detection. | `Tensorflow`| [Custom]( https://raw.githubusercontent.com/gliese581gg/YOLO_tensorflow/master/LICENSE ) | [YOLO TensorFlow ++]( https://github.com/thtrieu/darkflow) | TensorFlow implementation of 'YOLO: Real-Time Object Detection', with training and an actual support for real-time running on mobile devices. | `Tensorflow`| [GNU GENERAL PUBLIC LICENSE]( https://raw.githubusercontent.com/thtrieu/darkflow/master/LICENSE ) | [MobileNet]( https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet_v1.md) | MobileNets trade off between latency, size and accuracy while comparing favorably with popular models from the literature. | `Tensorflow`| [The MIT License (MIT)]( https://raw.githubusercontent.com/tensorflow/models/master/LICENSE ) | [DeepLab]( https://github.com/tensorflow/models/tree/master/research/deeplab) | Deep labeling for semantic image segmentation. | `Tensorflow`| [Apache License]( https://raw.githubusercontent.com/tensorflow/models/master/LICENSE ) | [Colornet]( https://github.com/pavelgonchar/colornet) | Neural Network to colorize grayscale images. | `Tensorflow`| Not Found | [SRGAN]( https://github.com/tensorlayer/srgan) | Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network. | `Tensorflow`| Not Found | [DeepOSM]( https://github.com/trailbehind/DeepOSM) | Train TensorFlow neural nets with OpenStreetMap features and satellite imagery. | `Tensorflow`| [The MIT License (MIT)]( https://raw.githubusercontent.com/trailbehind/DeepOSM/master/LICENSE ) | [Domain Transfer Network]( https://github.com/yunjey/domain-transfer-network) | Implementation of Unsupervised Cross-Domain Image Generation. | `Tensorflow`| [MIT License]( https://raw.githubusercontent.com/yunjey/domain-transfer-network/master/LICENSE ) | [Show, Attend and Tell]( https://github.com/yunjey/show-attend-and-tell) | Attention Based Image Caption Generator. | `Tensorflow`| [MIT License]( https://raw.githubusercontent.com/yunjey/show-attend-and-tell/master/LICENSE ) | [android-yolo]( https://github.com/natanielruiz/android-yolo) | Real-time object detection on Android using the YOLO network, powered by TensorFlow. | `Tensorflow`| [Apache License]( https://raw.githubusercontent.com/natanielruiz/android-yolo/master/LICENSE ) | [DCSCN Super Resolution]( https://github.com/jiny2001/dcscn-super-resolutiont) | This is a tensorflow implementation of "Fast and Accurate Image Super Resolution by Deep CNN with Skip Connection and Network in Network", a deep learning based Single-Image Super-Resolution (SISR) model. | `Tensorflow`| Not Found | [GAN-CLS]( https://github.com/zsdonghao/text-to-image) | This is an experimental tensorflow implementation of synthesizing images. | `Tensorflow`| Not Found | [U-Net]( https://github.com/zsdonghao/u-net-brain-tumor) | For Brain Tumor Segmentation. | `Tensorflow`| Not Found | [Improved CycleGAN]( https://github.com/luoxier/CycleGAN_Tensorlayer) |Unpaired Image to Image Translation. | `Tensorflow`| [MIT License]( https://raw.githubusercontent.com/luoxier/CycleGAN_Tensorlayer/master/LICENSE ) | [Im2txt]( https://github.com/tensorflow/models/tree/master/research/im2txt) | Image-to-text neural network for image captioning. | `Tensorflow`| [Apache License]( https://raw.githubusercontent.com/tensorflow/models/master/LICENSE ) | [SLIM]( https://github.com/tensorflow/models/tree/master/research/slim) | Image classification models in TF-Slim. | `Tensorflow`| [Apache License]( https://raw.githubusercontent.com/tensorflow/models/master/LICENSE ) | [DELF]( https://github.com/tensorflow/models/tree/master/research/delf) | Deep local features for image matching and retrieval. | `Tensorflow`| [Apache License]( https://raw.githubusercontent.com/tensorflow/models/master/LICENSE ) | [Compression]( https://github.com/tensorflow/models/tree/master/research/compression) | Compressing and decompressing images using a pre-trained Residual GRU network. | `Tensorflow`| [Apache License]( https://raw.githubusercontent.com/tensorflow/models/master/LICENSE ) | [AttentionOCR]( https://github.com/tensorflow/models/tree/master/research/attention_ocr) | A model for real-world image text extraction. | `Tensorflow`| [Apache License]( https://raw.githubusercontent.com/tensorflow/models/master/LICENSE ) <div align="right"> <b><a href="#framework">↥ Back To Top</a></b> </div> *** ### Keras <a name="keras"/> | Model Name | Description | Framework | License | | :---: | :---: | :---: | :---: | | [Mask R-CNN]( https://github.com/matterport/Mask_RCNN) | The model generates bounding boxes and segmentation masks for each instance of an object in the image. It's based on Feature Pyramid Network (FPN) and a ResNet101 backbone.| `Keras`| [The MIT License (MIT)]( https://raw.githubusercontent.com/matterport/Mask_RCNN/master/LICENSE ) | [VGG16]( https://github.com/keras-team/keras-applications/blob/master/keras_applications/vgg16.py) | Very Deep Convolutional Networks for Large-Scale Image Recognition. | `Keras`| [The MIT License (MIT)]( https://raw.githubusercontent.com/keras-team/keras-applications/master/LICENSE ) | [VGG19]( https://github.com/keras-team/keras-applications/blob/master/keras_applications/vgg19.py) | Very Deep Convolutional Networks for Large-Scale Image Recognition. | `Keras`| [The MIT License (MIT)]( https://raw.githubusercontent.com/keras-team/keras-applications/master/LICENSE ) | [ResNet]( https://github.com/keras-team/keras-applications/blob/master/keras_applications/resnet_common.py) | Deep Residual Learning for Image Recognition. | `Keras`| [The MIT License (MIT)]( https://raw.githubusercontent.com/keras-team/keras-applications/master/LICENSE ) | [ResNet50](https://github.com/keras-team/keras-applications/blob/master/keras_applications/resnet50.py) | Deep Residual Learning for Image Recognition. | `Keras`| [The MIT License (MIT)]( https://raw.githubusercontent.com/keras-team/keras-applications/master/LICENSE ) | [Nasnet](https://github.com/keras-team/keras-applications/blob/master/keras_applications/nasnet.py) | NASNet refers to Neural Architecture Search Network, a family of models that were designed automatically by learning the model architectures directly on the dataset of interest. | `Keras`| [The MIT License (MIT)]( https://raw.githubusercontent.com/keras-team/keras-applications/master/LICENSE ) | [MobileNet]( https://github.com/keras-team/keras-applications/blob/master/keras_applications/mobilenet.py) | MobileNet v1 models for Keras. | `Keras`| [The MIT License (MIT)]( https://raw.githubusercontent.com/keras-team/keras-applications/master/LICENSE ) | [MobileNet V2]( https://github.com/keras-team/keras-applications/blob/master/keras_applications/mobilenet_v2.py) | MobileNet v2 models for Keras. | `Keras`| [The MIT License (MIT)]( https://raw.githubusercontent.com/keras-team/keras-applications/master/LICENSE ) | [MobileNet V3]( https://github.com/keras-team/keras-applications/blob/master/keras_applications/mobilenet_v3.py) | MobileNet v3 models for Keras. | `Keras`| [The MIT License (MIT)]( https://raw.githubusercontent.com/keras-team/keras-applications/master/LICENSE ) | [efficientnet]( https://github.com/keras-team/keras-applications/blob/master/keras_applications/efficientnet.py) | Rethinking Model Scaling for Convolutional Neural Networks. | `Keras`| [The MIT License (MIT)]( https://raw.githubusercontent.com/keras-team/keras-applications/master/LICENSE ) | [Image analogies]( https://github.com/awentzonline/image-analogies) | Generate image analogies using neural matching and blending. | `Keras`| [The MIT License (MIT)]( https://raw.githubusercontent.com/awentzonline/image-analogies/master/LICENSE.txt ) | [Popular Image Segmentation Models]( https://github.com/divamgupta/image-segmentation-keras) | Implementation of Segnet, FCN, UNet and other models in Keras. | `Keras`| [MIT License]( https://raw.githubusercontent.com/divamgupta/image-segmentation-keras/master/LICENSE ) | [Ultrasound nerve segmentation]( https://github.com/jocicmarko/ultrasound-nerve-segmentation) | This tutorial shows how to use Keras library to build deep neural network for ultrasound image nerve segmentation. | `Keras`| [MIT License]( https://raw.githubusercontent.com/jocicmarko/ultrasound-nerve-segmentation/master/LICENSE.md ) | [DeepMask object segmentation]( https://github.com/abbypa/NNProject_DeepMask) | This is a Keras-based Python implementation of DeepMask- a complex deep neural network for learning object segmentation masks. | `Keras`| Not Found | [Monolingual and Multilingual Image Captioning]( https://github.com/elliottd/GroundedTranslation) | This is the source code that accompanies Multilingual Image Description with Neural Sequence Models. | `Keras`| [BSD-3-Clause License]( https://raw.githubusercontent.com/elliottd/GroundedTranslation/master/LICENSE ) | [pix2pix]( https://github.com/tdeboissiere/DeepLearningImplementations/tree/master/pix2pix) | Keras implementation of Image-to-Image Translation with Conditional Adversarial Networks by Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, Alexei A. | `Keras`| Not Found | [Colorful Image colorization]( https://github.com/tdeboissiere/DeepLearningImplementations/tree/master/Colorful) | B&W to color. | `Keras`| Not Found | [CycleGAN]( https://github.com/eriklindernoren/Keras-GAN/blob/master/cyclegan/cyclegan.py) | Implementation of _Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks_. | `Keras`| [MIT License]( https://raw.githubusercontent.com/eriklindernoren/Keras-GAN/master/LICENSE ) | [DualGAN](https://github.com/eriklindernoren/Keras-GAN/blob/master/dualgan/dualgan.py) | Implementation of _DualGAN: Unsupervised Dual Learning for Image-to-Image Translation_. | `Keras`| [MIT License]( https://raw.githubusercontent.com/eriklindernoren/Keras-GAN/master/LICENSE ) | [Super-Resolution GAN]( https://github.com/eriklindernoren/Keras-GAN/blob/master/srgan/srgan.py) | Implementation of _Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network_. | `Keras`| [MIT License]( https://raw.githubusercontent.com/eriklindernoren/Keras-GAN/master/LICENSE ) <div align="right"> <b><a href="#framework">↥ Back To Top</a></b> </div> *** ### PyTorch <a name="pytorch"/> | Model Name | Description | Framework | License | | :---: | :---: | :---: | :---: | |[detectron2](https://github.com/facebookresearch/detectron2) | Detectron2 is Facebook AI Research's next generation software system that implements state-of-the-art object detection algorithms | `PyTorch` | [Apache License 2.0](https://raw.githubusercontent.com/facebookresearch/detectron2/master/LICENSE) | [FastPhotoStyle]( https://github.com/NVIDIA/FastPhotoStyle) | A Closed-form Solution to Photorealistic Image Stylization. | `PyTorch`| [Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International Public Licens]( https://raw.githubusercontent.com/NVIDIA/FastPhotoStyle/master/LICENSE.md ) | [pytorch-CycleGAN-and-pix2pix]( https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix) | A Closed-form Solution to Photorealistic Image Stylization. | `PyTorch`| [BSD License]( https://raw.githubusercontent.com/junyanz/pytorch-CycleGAN-and-pix2pix/master/LICENSE ) | [maskrcnn-benchmark]( https://github.com/facebookresearch/maskrcnn-benchmark) | Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch. | `PyTorch`| [MIT License]( https://raw.githubusercontent.com/facebookresearch/maskrcnn-benchmark/master/LICENSE ) | [deep-image-prior]( https://github.com/DmitryUlyanov/deep-image-prior) | Image restoration with neural networks but without learning. | `PyTorch`| [Apache License 2.0]( https://raw.githubusercontent.com/DmitryUlyanov/deep-image-prior/master/LICENSE ) | [StarGAN]( https://github.com/yunjey/StarGAN) | StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation. | `PyTorch`| [MIT License]( https://raw.githubusercontent.com/yunjey/StarGAN/master/LICENSE ) | [faster-rcnn.pytorch]( https://github.com/jwyang/faster-rcnn.pytorch) | This project is a faster faster R-CNN implementation, aimed to accelerating the training of faster R-CNN object detection models. | `PyTorch`| [MIT License]( https://raw.githubusercontent.com/jwyang/faster-rcnn.pytorch/master/LICENSE ) | [pix2pixHD]( https://github.com/NVIDIA/pix2pixHD) | Synthesizing and manipulating 2048x1024 images with conditional GANs. | `PyTorch`| [BSD License]( https://raw.githubusercontent.com/NVIDIA/pix2pixHD/master/LICENSE.txt ) | [Augmentor]( https://github.com/mdbloice/Augmentor) | Image augmentation library in Python for machine learning. | `PyTorch`| [MIT License]( https://raw.githubusercontent.com/mdbloice/Augmentor/master/LICENSE.md ) | [albumentations]( https://github.com/albumentations-team/albumentations) | Fast image augmentation library. | `PyTorch`| [MIT License]( https://raw.githubusercontent.com/albumentations-team/albumentations/master/LICENSE ) | [Deep Video Analytics]( https://github.com/AKSHAYUBHAT/DeepVideoAnalytics) | Deep Video Analytics is a platform for indexing and extracting information from videos and images | `PyTorch`| [Custom]( https://raw.githubusercontent.com/AKSHAYUBHAT/DeepVideoAnalytics/master/LICENSE ) | [semantic-segmentation-pytorch]( https://github.com/CSAILVision/semantic-segmentation-pytorch) | Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset. | `PyTorch`| [BSD 3-Clause License]( https://raw.githubusercontent.com/CSAILVision/semantic-segmentation-pytorch/master/LICENSE ) | [An End-to-End Trainable Neural Network for Image-based Sequence Recognition]( https://github.com/bgshih/crnn) | This software implements the Convolutional Recurrent Neural Network (CRNN), a combination of CNN, RNN and CTC loss for image-based sequence recognition tasks, such as scene text recognition and OCR. | `PyTorch`| [The MIT License (MIT)]( https://raw.githubusercontent.com/bgshih/crnn/master/LICENSE ) | [UNIT]( https://github.com/mingyuliutw/UNIT) | PyTorch Implementation of our Coupled VAE-GAN algorithm for Unsupervised Image-to-Image Translation. | `PyTorch`| [Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International Public License]( https://raw.githubusercontent.com/mingyuliutw/UNIT/master/LICENSE.md ) | [Neural Sequence labeling model]( https://github.com/jiesutd/NCRFpp) | Sequence labeling models are quite popular in many NLP tasks, such as Named Entity Recognition (NER), part-of-speech (POS) tagging and word segmentation. | `PyTorch`| [Apache License]( https://raw.githubusercontent.com/jiesutd/NCRFpp/master/LICENCE ) | [faster rcnn]( https://github.com/longcw/faster_rcnn_pytorch) | This is a PyTorch implementation of Faster RCNN. This project is mainly based on py-faster-rcnn and TFFRCNN. For details about R-CNN please refer to the paper Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks by Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun. | `PyTorch`| [MIT License]( https://raw.githubusercontent.com/longcw/faster_rcnn_pytorch/master/LICENSE ) | [pytorch-semantic-segmentation]( https://github.com/ZijunDeng/pytorch-semantic-segmentation) | PyTorch for Semantic Segmentation. | `PyTorch`| [MIT License]( https://raw.githubusercontent.com/ZijunDeng/pytorch-semantic-segmentation/master/LICENSE ) | [EDSR-PyTorch]( https://github.com/thstkdgus35/EDSR-PyTorch) | PyTorch version of the paper 'Enhanced Deep Residual Networks for Single Image Super-Resolution'. | `PyTorch`| [MIT License]( https://raw.githubusercontent.com/thstkdgus35/EDSR-PyTorch/master/LICENSE ) | [image-classification-mobile]( https://github.com/osmr/imgclsmob) | Collection of classification models pretrained on the ImageNet-1K. | `PyTorch`| [MIT License]( https://raw.githubusercontent.com/osmr/imgclsmob/master/LICENSE ) | [FaderNetworks]( https://github.com/facebookresearch/FaderNetworks) | Fader Networks: Manipulating Images by Sliding Attributes - NIPS 2017. | `PyTorch`| [Creative Commons Attribution-NonCommercial 4.0 International Public License]( https://raw.githubusercontent.com/facebookresearch/FaderNetworks/master/LICENSE ) | [neuraltalk2-pytorch]( https://github.com/ruotianluo/ImageCaptioning.pytorch) | Image captioning model in pytorch (finetunable cnn in branch with_finetune). | `PyTorch`| [MIT License]( https://raw.githubusercontent.com/ruotianluo/ImageCaptioning.pytorch/master/LICENSE ) | [RandWireNN]( https://github.com/seungwonpark/RandWireNN) | Implementation of: "Exploring Randomly Wired Neural Networks for Image Recognition". | `PyTorch`| Not Found | [stackGAN-v2]( https://github.com/hanzhanggit/StackGAN-v2) |Pytorch implementation for reproducing StackGAN_v2 results in the paper StackGAN++. | `PyTorch`| [MIT License]( https://raw.githubusercontent.com/hanzhanggit/StackGAN-v2/master/LICENSE ) | [Detectron models for Object Detection]( https://github.com/ignacio-rocco/detectorch) | This code allows to use some of the Detectron models for object detection from Facebook AI Research with PyTorch. | `PyTorch`| [Apache License]( https://raw.githubusercontent.com/ignacio-rocco/detectorch/master/LICENSE ) | [DEXTR-PyTorch]( https://github.com/scaelles/DEXTR-PyTorch) | This paper explores the use of extreme points in an object (left-most, right-most, top, bottom pixels) as input to obtain precise object segmentation for images and videos. | `PyTorch`| [GNU GENERAL PUBLIC LICENSE]( https://raw.githubusercontent.com/scaelles/DEXTR-PyTorch/master/LICENSE ) | [pointnet.pytorch]( https://github.com/fxia22/pointnet.pytorch) | Pytorch implementation for "PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. | `PyTorch`| [MIT License]( https://raw.githubusercontent.com/fxia22/pointnet.pytorch/master/LICENSE ) | [self-critical.pytorch]( https://github.com/ruotianluo/self-critical.pytorch) | This repository includes the unofficial implementation Self-critical Sequence Training for Image Captioning and Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering. | `PyTorch`| [MIT License]( https://raw.githubusercontent.com/ruotianluo/self-critical.pytorch/master/LICENSE ) | [vnet.pytorch]( https://github.com/mattmacy/vnet.pytorch) | A Pytorch implementation for V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation. | `PyTorch`| [BSD 3-Clause License]( https://raw.githubusercontent.com/mattmacy/vnet.pytorch/master/LICENSE ) | [piwise]( https://github.com/bodokaiser/piwise) | Pixel-wise segmentation on VOC2012 dataset using pytorch. | `PyTorch`| [BSD 3-Clause License]( https://raw.githubusercontent.com/bodokaiser/piwise/master/LICENSE.md ) | [pspnet-pytorch]( https://github.com/Lextal/pspnet-pytorch) | PyTorch implementation of PSPNet segmentation network. | `PyTorch`| Not Found | [pytorch-SRResNet]( https://github.com/twtygqyy/pytorch-SRResNet) | Pytorch implementation for Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network. | `PyTorch`| [The MIT License (MIT)]( https://raw.githubusercontent.com/twtygqyy/pytorch-SRResNet/master/LICENSE ) | [PNASNet.pytorch]( https://github.com/chenxi116/PNASNet.pytorch) | PyTorch implementation of PNASNet-5 on ImageNet. | `PyTorch`| [Apache License]( https://raw.githubusercontent.com/chenxi116/PNASNet.pytorch/master/LICENSE ) | [img_classification_pk_pytorch]( https://github.com/felixgwu/img_classification_pk_pytorch) | Quickly comparing your image classification models with the state-of-the-art models. | `PyTorch`| Not Found | [Deep Neural Networks are Easily Fooled]( https://github.com/utkuozbulak/pytorch-cnn-adversarial-attacks) | High Confidence Predictions for Unrecognizable Images. | `PyTorch`| [MIT License]( https://raw.githubusercontent.com/utkuozbulak/pytorch-cnn-adversarial-attacks/master/LICENSE ) | [pix2pix-pytorch]( https://github.com/mrzhu-cool/pix2pix-pytorch) | PyTorch implementation of "Image-to-Image Translation Using Conditional Adversarial Networks". | `PyTorch`| Not Found | [NVIDIA/semantic-segmentation]( https://github.com/NVIDIA/semantic-segmentation) | A PyTorch Implementation of Improving Semantic Segmentation via Video Propagation and Label Relaxation, In CVPR2019. | `PyTorch`| [CC BY-NC-SA 4.0 license]( https://raw.githubusercontent.com/NVIDIA/semantic-segmentation/master/LICENSE ) | [Neural-IMage-Assessment]( https://github.com/kentsyx/Neural-IMage-Assessment) | A PyTorch Implementation of Neural IMage Assessment. | `PyTorch`| Not Found | [torchxrayvision](https://github.com/mlmed/torchxrayvision) | Pretrained models for chest X-ray (CXR) pathology predictions. Medical, Healthcare, Radiology | `PyTorch` | [Apache License]( https://raw.githubusercontent.com/mlmed/torchxrayvision/master/LICENSE ) | | [pytorch-image-models](https://github.com/rwightman/pytorch-image-models) | PyTorch image models, scripts, pretrained weights -- (SE)ResNet/ResNeXT, DPN, EfficientNet, MixNet, MobileNet-V3/V2, MNASNet, Single-Path NAS, FBNet, and more | `PyTorch` | [Apache License 2.0]( https://github.com/rwightman/pytorch-image-models/blob/master/LICENSE ) | <div align="right"> <b><a href="#framework">↥ Back To Top</a></b> </div> *** ### Caffe <a name="caffe"/> | Model Name | Description | Framework | License | | :---: | :---: | :---: | :---: | | [OpenPose]( https://github.com/CMU-Perceptual-Computing-Lab/openpose) | OpenPose represents the first real-time multi-person system to jointly detect human body, hand, and facial keypoints (in total 130 keypoints) on single images. | `Caffe`| [Custom]( https://raw.githubusercontent.com/CMU-Perceptual-Computing-Lab/openpose/master/LICENSE ) | [Fully Convolutional Networks for Semantic Segmentation]( https://github.com/shelhamer/fcn.berkeleyvision.org) | Fully Convolutional Models for Semantic Segmentation. | `Caffe`| Not Found | [Colorful Image Colorization]( https://github.com/richzhang/colorization) | Colorful Image Colorization. | `Caffe`| [BSD-2-Clause License]( https://raw.githubusercontent.com/richzhang/colorization/master/LICENSE ) | [R-FCN]( https://github.com/YuwenXiong/py-R-FCN) | R-FCN: Object Detection via Region-based Fully Convolutional Networks. | `Caffe`| [MIT License]( https://raw.githubusercontent.com/YuwenXiong/py-R-FCN/master/LICENSE ) | [cnn-vis]( https://github.com/jcjohnson/cnn-vis) |Inspired by Google's recent Inceptionism blog post, cnn-vis is an open-source tool that lets you use convolutional neural networks to generate images. | `Caffe`| [The MIT License (MIT)]( https://raw.githubusercontent.com/jcjohnson/cnn-vis/master/LICENSE ) | [DeconvNet]( https://github.com/HyeonwooNoh/DeconvNet) | Learning Deconvolution Network for Semantic Segmentation. | `Caffe`| [Custom]( https://raw.githubusercontent.com/HyeonwooNoh/DeconvNet/master/LICENSE ) <div align="right"> <b><a href="#framework">↥ Back To Top</a></b> </div> *** ### MXNet <a name="mxnet"/> | Model Name | Description | Framework | License | | :---: | :---: | :---: | :---: | | [Faster RCNN]( https://github.com/ijkguo/mx-rcnn) | Region Proposal Network solves object detection as a regression problem. | `MXNet`| [Apache License, Version 2.0]( https://raw.githubusercontent.com/ijkguo/mx-rcnn/master/LICENSE ) | [SSD]( https://github.com/zhreshold/mxnet-ssd) | SSD is an unified framework for object detection with a single network. | `MXNet`| [MIT License]( https://raw.githubusercontent.com/zhreshold/mxnet-ssd/master/LICENSE ) | [Faster RCNN+Focal Loss]( https://github.com/unsky/focal-loss) | The code is unofficial version for focal loss for Dense Object Detection. | `MXNet`| Not Found | [CNN-LSTM-CTC]( https://github.com/oyxhust/CNN-LSTM-CTC-text-recognition) |I realize three different models for text recognition, and all of them consist of CTC loss layer to realize no segmentation for text images. | `MXNet`| Not Found | [Faster_RCNN_for_DOTA]( https://github.com/jessemelpolio/Faster_RCNN_for_DOTA) | This is the official repo of paper _DOTA: A Large-scale Dataset for Object Detection in Aerial Images_. | `MXNet`| [Apache License]( https://raw.githubusercontent.com/jessemelpolio/Faster_RCNN_for_DOTA/master/LICENSE ) | [RetinaNet]( https://github.com/unsky/RetinaNet) | Focal loss for Dense Object Detection. | `MXNet`| Not Found | [MobileNetV2]( https://github.com/liangfu/mxnet-mobilenet-v2) | This is a MXNet implementation of MobileNetV2 architecture as described in the paper _Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation_. | `MXNet`| [Apache License]( https://raw.githubusercontent.com/liangfu/mxnet-mobilenet-v2/master/LICENSE ) | [neuron-selectivity-transfer]( https://github.com/TuSimple/neuron-selectivity-transfer) | This code is a re-implementation of the imagenet classification experiments in the paper _Like What You Like: Knowledge Distill via Neuron Selectivity Transfer_. | `MXNet`| [Apache License]( https://raw.githubusercontent.com/TuSimple/neuron-selectivity-transfer/master/LICENSE ) | [MobileNetV2]( https://github.com/chinakook/MobileNetV2.mxnet) | This is a Gluon implementation of MobileNetV2 architecture as described in the paper _Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation_. | `MXNet`| [Apache License]( https://raw.githubusercontent.com/chinakook/MobileNetV2.mxnet/master/LICENSE ) | [sparse-structure-selection]( https://github.com/TuSimple/sparse-structure-selection) | This code is a re-implementation of the imagenet classification experiments in the paper _Data-Driven Sparse Structure Selection for Deep Neural Networks_. | `MXNet`| [Apache License]( https://raw.githubusercontent.com/TuSimple/sparse-structure-selection/master/LICENSE ) | [FastPhotoStyle]( https://github.com/NVIDIA/FastPhotoStyle) | A Closed-form Solution to Photorealistic Image Stylization. | `MXNet`| [Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International Public License]( https://raw.githubusercontent.com/NVIDIA/FastPhotoStyle/master/LICENSE.md ) <div align="right"> <b><a href="#framework">↥ Back To Top</a></b> </div> *** ## Contributions Your contributions are always welcome!! Please have a look at `contributing.md` ## License [MIT License](LICENSE)

Design & Creative ML Frameworks

1.4K Github Stars

Open Source

awesome-AI-toolkit

# Awesome Open-Source AI Toolkit ## Stop searching. This is the only AI toolkit a developer will ever need! This toolkit covers all areas of AI, from machine learning basics to specialized fields like computer vision, NLP, reinforcement learning, and MLOps. Updated with 2025 trends for building, learning, and experimenting efficiently. ![banner-image](ai-toolkit.png) A curated, comprehensive collection of open-source AI tools, frameworks, datasets, courses, and seminal papers. Organized by AI domains and segregated for beginners (foundational, easy-to-use tools/courses) and advanced users (complex, production-ready resources). Whether you're a beginner starting your AI journey or an advanced engineer deploying scalable systems, this repo provides essential resources to accelerate your work. Contribute to keep it growing. ## Table of Contents - [Why This Toolkit?](#why-this-toolkit) - [🆕 2025 Trending Tools](#-2025-trending-tools) - [AI Domains and Tools](#ai-domains-and-tools) - [Machine Learning Frameworks](#machine-learning-frameworks) - [Data Processing & Management](#data-processing--management) - [Vector Databases](#vector-databases) - [Orchestration & Workflow Frameworks](#orchestration--workflow-frameworks) - [Computer Vision](#computer-vision) - [Natural Language Processing (NLP)](#natural-language-processing-nlp) - [Reinforcement Learning (RL)](#reinforcement-learning-rl) - [MLOps](#mlops) - [PDF Extraction Tools](#pdf-extraction-tools) - [Retrieval-Augmented Generation (RAG)](#retrieval-augmented-generation-rag) - [Evaluation & Testing](#evaluation--testing) - [Monitoring & Observability](#monitoring--observability) - [AI Agents](#ai-agents) - [Generative AI](#generative-ai) - [Deep Learning](#deep-learning) - [Advanced LLM Architectures](#advanced-llm-architectures) - [🆕 AI Development Assistants](#-ai-development-assistants) - [🆕 Multimodal AI](#-multimodal-ai) - [🆕 Edge AI & Mobile](#-edge-ai--mobile) - [🆕 Audio & Speech Processing](#-audio--speech-processing) - [🆕 Deployment & Containerization](#-deployment--containerization) - [🆕 DevOps & Infrastructure](#-devops--infrastructure) - [Datasets](#datasets) - [Courses](#courses) - [Papers](#papers) - [How to Contribute](#how-to-contribute) - [License](#license) ## Why This Toolkit? - **Broad Coverage**: Spans all AI domains with detailed category separation. - **Open-Source Only**: Exclusively free, community-driven tools and resources. - **Skill-Level Segregation**: Beginner-friendly entries for quick starts; advanced for deep dives. - **Beyond Tools**: Includes top datasets for exploration, free courses, and key papers. - **Up-to-Date**: Trending resources as of August 2025, with GitHub stars for popularity insights. - **Community-Driven**: Add new entries via PRs to make it more comprehensive and viral! ## 🆕 2025 Trending Tools The latest trending open-source AI tools that are shaping 2025, focusing on smaller, smarter models and improved collaboration: ### 🔥 Hot New Releases | Tool | Description | URL | Stars | Trend | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------|-------| | Claude Code | Command-line AI coding assistant from Anthropic | https://docs.anthropic.com/en/docs/claude-code | New | 🚀 | | Aider | AI pair programming in your terminal | https://github.com/paul-gauthier/aider | 15k | 📈 | | Cursor | AI-powered code editor with advanced completion | https://cursor.sh/ | - | 🔥 | | Windsurf | Next-gen AI development environment | https://github.com/codeium/windsurf | 8k | 📈 | | Zed | High-performance multiplayer code editor with AI | https://github.com/zed-industries/zed | 45k | 🚀 | ### 🎯 Most Starred in 2025 | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | LLaMA 4 | Latest open-source large language model from Meta | https://github.com/facebookresearch/llama | 180k | | Gemma 3 | Google's advanced lightweight language model | https://github.com/google/gemma | 25k | | Mixtral-8x22B | Sparse mixture of experts model | https://github.com/mistralai/mistral-src | 40k | ## AI Domains and Tools Tools are categorized by domain. Each includes a brief description, GitHub URL, and approximate stars (as of August 2025). Segregated into Beginner (simple setup, tutorials-focused) and Advanced (scalable, customizable) sub-sections. ### Machine Learning Frameworks Foundational libraries for building and training ML models. #### Beginner | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | scikit-learn | Simple machine learning in Python for classification, regression, and clustering | https://github.com/scikit-learn/scikit-learn | 60k | | Keras | User-friendly neural networks API on top of TensorFlow or PyTorch | https://github.com/keras-team/keras | 61k | #### Advanced | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | TensorFlow | End-to-end platform for large-scale ML with strong ecosystem support | https://github.com/tensorflow/tensorflow | 183k | | PyTorch | Dynamic neural networks with GPU acceleration for research and production | https://github.com/pytorch/pytorch | 81k | ### Data Processing & Management Tools for handling and preparing data. #### Beginner | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | Pandas | Easy data manipulation and analysis with DataFrames | https://github.com/pandas-dev/pandas | 43k | | NumPy | Fundamental array computing and linear algebra operations | https://github.com/numpy/numpy | 28k | #### Advanced | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | Dask | Parallel computing for large datasets, integrates with Pandas/NumPy | https://github.com/dask/dask | 12k | ### Vector Databases Open-source storage for embeddings and similarity search. #### Beginner | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | Chroma | Simple embedding database for local LLM apps | https://github.com/chroma-core/chroma | 15k | | FAISS | Efficient similarity search library from Facebook AI | https://github.com/facebookresearch/faiss | 35k | #### Advanced | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | Weaviate | Vector database with GraphQL and modular plugins | https://github.com/weaviate/weaviate | 15k | | Qdrant | High-performance vector search with filtering support | https://github.com/qdrant/qdrant | 20k | | Milvus | Scalable vector database for billion-scale similarity search | https://github.com/milvus-io/milvus | 30k | ### Orchestration & Workflow Frameworks For building AI pipelines and agents. #### Beginner | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | Langflow | No-code visual builder for LLM workflows | https://github.com/langflow-ai/langflow | 15k | | Flowise | Drag-and-drop UI for LLM chains | https://github.com/FlowiseAI/Flowise | 25k | #### Advanced | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | LangChain | Modular framework for LLM apps and agents | https://github.com/langchain-ai/langchain | 120k | | LlamaIndex | Data ingestion and querying for LLMs | https://github.com/run-llama/llama_index | 50k | | Haystack | Production-ready NLP pipelines | https://github.com/deepset-ai/haystack | 18k | | DSPy | Programmatic prompt optimization | https://github.com/stanfordnlp/dspy | 15k | | Semantic Kernel | AI integration SDK for .NET/Python/Java | https://github.com/microsoft/semantic-kernel | 8k | ### Computer Vision Libraries for image processing and vision tasks. #### Beginner | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | OpenCV | Core library for image/video processing and basic CV tasks | https://github.com/opencv/opencv | 75k | #### Advanced | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | Ultralytics YOLO | State-of-the-art object detection and segmentation models | https://github.com/ultralytics/ultralytics | 30k | | Detectron2 | Facebook AI's framework for object detection and segmentation | https://github.com/facebookresearch/detectron2 | 30k | ### Natural Language Processing (NLP) Tools for text analysis and language models. #### Beginner | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | NLTK | Toolkit for basic NLP tasks like tokenization and stemming | https://github.com/nltk/nltk | 13k | | spaCy | Efficient NLP library for entity recognition and dependency parsing | https://github.com/explosion/spaCy | 29k | #### Advanced | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | Transformers | Hugging Face library for state-of-the-art NLP models | https://github.com/huggingface/transformers | 130k | | Flair | Framework for advanced NLP with pre-trained embeddings | https://github.com/flairNLP/flair | 14k | ### Reinforcement Learning (RL) Frameworks for agent training and decision-making. #### Beginner | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | Stable-Baselines3 | Reliable RL algorithms built on PyTorch | https://github.com/DLR-RM/stable-baselines3 | 8k | #### Advanced | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | Ray RLlib | Scalable RL library for distributed training | https://github.com/ray-project/ray | 32k | | OpenRL | Unified framework for single/multi-agent RL | https://github.com/OpenRL-Lab/openrl | 1k | ### MLOps Tools for ML operations, deployment, and monitoring. #### Beginner | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | MLflow | Track experiments, package code, and deploy models | https://github.com/mlflow/mlflow | 18k | #### Advanced | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | Kubeflow | Kubernetes-native platform for ML pipelines | https://github.com/kubeflow/kubeflow | 14k | | DVC | Version control for data and ML models | https://github.com/iterative/dvc | 13k | ### PDF Extraction Tools For extracting data from PDFs. #### Beginner | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | pdfplumber | Extract text and tables from PDFs | https://github.com/jsvine/pdfplumber | 6k | | Camelot | Tabular data extraction from PDFs | https://github.com/camelot-dev/camelot | 2k | #### Advanced | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | Docling | AI-powered PDF to JSON/Markdown conversion | https://github.com/docling-project/docling | 1k | | PyMuPDF | High-performance PDF parsing | https://github.com/pymupdf/PyMuPDF | 5k | | PDF.js | JavaScript-based PDF rendering and extraction | https://github.com/mozilla/pdf.js | 50k | ### Retrieval-Augmented Generation (RAG) For enhancing LLMs with external data. #### Beginner | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | PrivateGPT | Local document interaction with LLMs | https://github.com/imartinez/privateGPT | 50k | | AnythingLLM | All-in-one local LLM app for RAG | https://github.com/Mintplex-Labs/anything-llm | 20k | #### Advanced | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | RAGFlow | Deep document understanding for RAG | https://github.com/infiniflow/ragflow | 15k | | Verba | RAG chatbot with Weaviate integration | https://github.com/weaviate/Verba | 5k | | Quivr | GenAI second brain for document management | https://github.com/QuivrHQ/quivr | 35k | | Jina | Multimodal neural search for RAG | https://github.com/jina-ai/jina | 25k | | txtai | Embeddings database for semantic search | https://github.com/neuml/txtai | 10k | ### Evaluation & Testing For assessing AI models. #### Beginner | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | Ragas | Framework for evaluating RAG pipelines | https://github.com/explodinggradients/ragas | 8k | #### Advanced | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | Phoenix | Observability for LLMs and vision models | https://github.com/Arize-ai/phoenix | 5k | | DeepEval | Unit testing for LLM outputs | https://github.com/confident-ai/deepeval | 8k | | TruLens | Tracking and evaluation for LLM experiments | https://github.com/truera/trulens | 2k | ### Monitoring & Observability For production AI systems. #### Beginner | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | Phoenix | ML observability tool | https://github.com/Arize-ai/phoenix | 5k | #### Advanced | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | Evidently AI | Monitoring for ML model performance | https://github.com/evidentlyai/evidently | 5k | ### AI Agents Frameworks for building autonomous AI agents. #### Beginner | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | AutoGPT | Autonomous AI agent for task automation using LLMs | https://github.com/Significant-Gravitas/AutoGPT | 160k | | BabyAGI | Task-driven autonomous agent inspired by BabyAGI | https://github.com/yoheinakajima/babyagi | 18k | #### Advanced | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | CrewAI | Framework for orchestrating role-playing AI agents | https://github.com/joaomdmoura/crewAI | 20k | | MetaGPT | Multi-agent framework simulating a software company | https://github.com/geekan/MetaGPT | 40k | | OpenHands | AI agents for software development tasks | https://github.com/All-Hands-AI/OpenHands | 10k | ### Generative AI Tools for generating text, images, and other content. #### Beginner | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | Ollama | Run and manage local LLMs easily | https://github.com/ollama/ollama | 70k | | Stable Diffusion WebUI | User-friendly web interface for Stable Diffusion image generation | https://github.com/AUTOMATIC1111/stable-diffusion-webui | 130k | #### Advanced | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | Diffusers | State-of-the-art diffusion models for image and audio generation | https://github.com/huggingface/diffusers | 25k | | llama.cpp | Efficient LLM inference in C/C++ | https://github.com/ggerganov/llama.cpp | 60k | | InvokeAI | Creative engine for Stable Diffusion models | https://github.com/invoke-ai/InvokeAI | 22k | ### Deep Learning Libraries for advanced neural network development. #### Beginner | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | fastai | High-level deep learning library on PyTorch for quick results | https://github.com/fastai/fastai | 26k | #### Advanced | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | JAX | Composable transformations for high-performance ML | https://github.com/google/jax | 30k | | tinygrad | Minimalist deep learning framework | https://github.com/tinygrad/tinygrad | 25k | | Deeplearning4j | JVM-based deep learning suite for enterprise | https://github.com/deeplearning4j/deeplearning4j | 13k | ### Advanced LLM Architectures Frameworks for optimizing and architecting large language models. #### Beginner | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | PEFT | Parameter-efficient fine-tuning for large models | https://github.com/huggingface/peft | 15k | | bitsandbytes | K-bit quantization for accessible LLMs | https://github.com/TimDettmers/bitsandbytes | 5k | #### Advanced | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | vLLM | High-throughput LLM inference engine | https://github.com/vllm-project/vllm | 25k | | Flash Attention | Fast and memory-efficient attention mechanism | https://github.com/Dao-AILab/flash-attention | 12k | | exllamav2 | Fast inference library for LLMs on consumer GPUs | https://github.com/turboderp/exllamav2 | 6k | ## 🆕 AI Development Assistants Tools that help developers write, debug, and optimize code using AI. #### Beginner | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | GitHub Copilot | AI pair programmer from GitHub (free for students/open source) | https://github.com/features/copilot | - | | Cody | AI coding assistant from Sourcegraph | https://github.com/sourcegraph/cody | 2k | | Tabnine | AI code completion tool | https://github.com/codota/TabNine | 2k | #### Advanced | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | Aider | AI pair programming in your terminal | https://github.com/paul-gauthier/aider | 20k | | Continue | Open-source autopilot for VS Code and JetBrains | https://github.com/continuedev/continue | 18k | | CodeT5 | Identifier-aware unified pre-trained encoder-decoder models | https://github.com/salesforce/CodeT5 | 2k | | WizardCoder | Code generation model | https://github.com/nlpxucan/WizardLM | 10k | | StarCoder | Code generation model from BigCode | https://github.com/bigcode-project/starcoder | 8k | ## 🆕 Multimodal AI Tools for processing multiple types of data (text, image, audio, video). #### Beginner | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | CLIP | Connecting text and images from OpenAI | https://github.com/openai/CLIP | 25k | | BLIP | Bootstrapping language-image pre-training | https://github.com/salesforce/BLIP | 5k | | ImageBind | One embedding space to bind them all | https://github.com/facebookresearch/ImageBind | 8k | #### Advanced | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | LLaVA | Large language and vision assistant | https://github.com/haotian-liu/LLaVA | 20k | | MiniGPT-4 | Enhancing vision-language understanding | https://github.com/Vision-CAIR/MiniGPT-4 | 25k | | Video-ChatGPT | Video conversation capabilities | https://github.com/mbzuai-oryx/Video-ChatGPT | 4k | | GPT4Vision | OpenAI's vision capabilities (API integration tools) | https://github.com/microsoft/autogen | 30k | | Flamingo | Few-shot learning for vision and language | https://github.com/mlfoundations/open_flamingo | 4k | ## 🆕 Edge AI & Mobile Tools for deploying AI on edge devices and mobile platforms. #### Beginner | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | TensorFlow Lite | Lightweight solution for mobile and embedded devices | https://github.com/tensorflow/tensorflow | 183k | | ONNX Runtime | Cross-platform machine learning model accelerator | https://github.com/microsoft/onnxruntime | 14k | | Core ML Tools | Convert models to Core ML format for Apple devices | https://github.com/apple/coremltools | 4k | #### Advanced | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | OpenVINO | Intel's toolkit for optimizing and deploying AI inference | https://github.com/openvinotoolkit/openvino | 7k | | TensorRT | NVIDIA's platform for high-performance deep learning inference | https://github.com/NVIDIA/TensorRT | 10k | | Neural Compressor | Intel's neural network compression framework | https://github.com/intel/neural-compressor | 2k | | MediaPipe | Framework for building multimodal applied ML pipelines | https://github.com/google/mediapipe | 27k | | ncnn | High-performance neural network inference on mobile | https://github.com/Tencent/ncnn | 20k | ## 🆕 Audio & Speech Processing Tools for audio processing, speech recognition, and generation. #### Beginner | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | librosa | Audio and music analysis in Python | https://github.com/librosa/librosa | 7k | | SpeechRecognition | Simple speech recognition library | https://github.com/Uberi/speech_recognition | 8k | | pydub | Audio manipulation with simple interface | https://github.com/jiaaro/pydub | 9k | #### Advanced | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | Whisper | Robust speech recognition via large-scale weak supervision | https://github.com/openai/whisper | 69k | | Bark | Text-prompted generative audio model | https://github.com/suno-ai/bark | 35k | | Coqui TTS | Deep learning toolkit for text-to-speech | https://github.com/coqui-ai/TTS | 34k | | ESPnet | End-to-end speech processing toolkit | https://github.com/espnet/espnet | 8k | | fairseq | Facebook AI sequence-to-sequence toolkit | https://github.com/facebookresearch/fairseq | 30k | | Silero Models | Pre-trained speech-to-text, text-to-speech, and voice activity detection | https://github.com/snakers4/silero-models | 5k | ## 🆕 Deployment & Containerization Tools for deploying AI models in production environments. #### Beginner | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | Docker | Containerization platform for consistent deployments | https://github.com/docker/docker-ce | 7k | | Streamlit | Turn data scripts into shareable web apps | https://github.com/streamlit/streamlit | 35k | | Gradio | Build and share machine learning apps | https://github.com/gradio-app/gradio | 33k | #### Advanced | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | BentoML | Unified model serving framework | https://github.com/bentoml/BentoML | 7k | | Seldon Core | Machine learning deployment on Kubernetes | https://github.com/SeldonIO/seldon-core | 4k | | KServe | Kubernetes native model serving | https://github.com/kserve/kserve | 3k | | Triton | NVIDIA's inference serving software | https://github.com/triton-inference-server/server | 8k | | TorchServe | Serve PyTorch models at scale | https://github.com/pytorch/serve | 4k | | FastAPI | Modern web framework for building APIs | https://github.com/tiangolo/fastapi | 76k | ## 🆕 DevOps & Infrastructure Tools for managing AI infrastructure and operations. #### Beginner | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | Jupyter | Interactive computing environment | https://github.com/jupyter/jupyter | 18k | | JupyterLab | Next-generation web-based UI for Project Jupyter | https://github.com/jupyterlab/jupyterlab | 14k | | VS Code | Popular code editor with AI extensions | https://github.com/microsoft/vscode | 163k | #### Advanced | Tool | Description | URL | Stars | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|-------| | Kubernetes | Container orchestration platform | https://github.com/kubernetes/kubernetes | 110k | | Terraform | Infrastructure as code software tool | https://github.com/hashicorp/terraform | 42k | | Ansible | Automation platform for configuration management | https://github.com/ansible/ansible | 62k | | Prometheus | Monitoring system and time series database | https://github.com/prometheus/prometheus | 55k | | Grafana | Open observability platform | https://github.com/grafana/grafana | 64k | | Apache Airflow | Platform to programmatically author, schedule, and monitor workflows | https://github.com/apache/airflow | 36k | ## Datasets Top open datasets for AI exploration. Segregated by skill level. #### Beginner Datasets (Small, Easy to Use) | Dataset | Description | URL | Domain | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|--------| | MNIST | Handwritten digits for classification | https://yann.lecun.com/exdb/mnist/ | CV/ML | | Iris | Flower species classification | https://archive.ics.uci.edu/dataset/53/iris | ML | | Boston Housing | House price regression | https://www.kaggle.com/datasets/vikrishnan/boston-house-prices | ML | #### Advanced Datasets (Large-Scale, Complex) | Dataset | Description | URL | Domain | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------|--------| | ImageNet | Large image dataset for object recognition | https://www.image-net.org/ | CV | | COCO | Common objects in context for detection/segmentation | https://cocodataset.org/ | CV | | LAION-5B | Massive multimodal dataset for generative models | https://laion.ai/blog/laion-5b/ | GenAI | | Common Crawl | Web-scale text corpus for NLP | https://commoncrawl.org/ | NLP | | GLUE | Benchmark for NLP tasks | https://gluebenchmark.com/ | NLP | ## Courses Free online courses for learning AI. Segregated by level. #### Beginner Courses | Course | Description | URL | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------| | Elements of AI | Introduction to AI concepts for non-experts | https://www.elementsofai.com/ | | Introduction to AI (Coursera) | Basics of AI from IBM | https://www.coursera.org/learn/introduction-to-ai | | Google AI Essentials | Practical AI skills from Google | https://grow.google/ai/ | #### Advanced Courses | Course | Description | URL | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------| | Deep Learning Specialization (Coursera) | Advanced neural networks by Andrew Ng | https://www.coursera.org/specializations/deep-learning | | CS224N: NLP with Deep Learning (Stanford) | State-of-the-art NLP techniques | https://web.stanford.edu/class/cs224n/ | | Reinforcement Learning (DeepMind) | RL fundamentals and algorithms | https://www.deepmind.com/learning-resources/reinforcement-learning-lecture-series-2021 | ## Papers Seminal and trending AI papers, with repositories for collections. #### Beginner-Friendly Papers (Foundational) | Paper/Repo | Description | URL | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------| | Attention Is All You Need (Transformer) | Introduced Transformers for NLP | https://arxiv.org/abs/1706.03762 | | A Few Useful Things to Know About ML | Practical ML advice | https://homes.cs.washington.edu/~pedrod/papers/cacm12.pdf | #### Advanced Papers (Cutting-Edge) | Paper/Repo | Description | URL | |---------------|-----------------------------------------------------------------------------|---------------------------------------------------| | ML Papers of the Week | Weekly curated ML papers | https://github.com/dair-ai/ML-Papers-of-the-Week | | Awesome AI Research Papers | Influential papers in AI domains | https://github.com/awesomelistsio/awesome-ai-research-papers | | Landmark Papers in ML | Key historical papers | https://github.com/daturkel/learning-papers | ## How to Contribute Fork, add to tables (include description, URL, stars), and PR. Focus on open-source only. See CONTRIBUTING.md. ## License MIT License

Education & Learning AI Agents

210 Github Stars