Model Deployment library

Caffe <a name="caffe"/>

• OpenPose - time multi-person system to jointly detect human body, hand, and facial keypoints (in total 130 keypoints) on single images. | Caffe| Custom
• Fully Convolutional Networks for Semantic Segmentation
• Colorful Image Colorization - 2-Clause License]( https://raw.githubusercontent.com/richzhang/colorization/master/LICENSE )
• R-FCN - FCN: Object Detection via Region-based Fully Convolutional Networks. | Caffe| MIT License
• cnn-vis - vis is an open-source tool that lets you use convolutional neural networks to generate images. | Caffe| The MIT License (MIT)
• DeconvNet

Keras <a name="keras"/>

• ResNet50 - team/keras-applications/master/LICENSE )
• Nasnet - team/keras-applications/master/LICENSE )
• DualGAN - to-Image Translation_. | Keras| MIT License
• VGG16 - Scale Image Recognition. | Keras| The MIT License (MIT)
• VGG19 - Scale Image Recognition. | Keras| The MIT License (MIT)
• ResNet - team/keras-applications/master/LICENSE )
• MobileNet - team/keras-applications/master/LICENSE )
• MobileNet V2 - team/keras-applications/master/LICENSE )
• MobileNet V3 - team/keras-applications/master/LICENSE )
• efficientnet - team/keras-applications/master/LICENSE )
• pix2pix - to-Image Translation with Conditional Adversarial Networks by Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, Alexei A. | Keras| Not Found
• Colorful Image colorization
• CycleGAN - to-Image Translation using Cycle-Consistent Adversarial Networks_. | Keras| MIT License
• Super-Resolution GAN - Realistic Single Image Super-Resolution Using a Generative Adversarial Network_. | Keras| MIT License
• Image analogies - analogies/master/LICENSE.txt )
• Popular Image Segmentation Models - segmentation-keras/master/LICENSE )
• Ultrasound nerve segmentation - nerve-segmentation/master/LICENSE.md )
• DeepMask object segmentation - based Python implementation of DeepMask- a complex deep neural network for learning object segmentation masks. | Keras| Not Found
• Monolingual and Multilingual Image Captioning - 3-Clause License]( https://raw.githubusercontent.com/elliottd/GroundedTranslation/master/LICENSE )

Model visualization

• Netron

MXNet <a name="mxnet"/>

• Faster RCNN - rcnn/master/LICENSE )
• SSD - ssd/master/LICENSE )
• Faster RCNN+Focal Loss
• CNN-LSTM-CTC
• Faster_RCNN_for_DOTA - scale Dataset for Object Detection in Aerial Images_. | MXNet| Apache License
• RetinaNet
• MobileNetV2 - mobilenet-v2/master/LICENSE )
• neuron-selectivity-transfer - implementation of the imagenet classification experiments in the paper Like What You Like: Knowledge Distill via Neuron Selectivity Transfer. | MXNet| Apache License
• MobileNetV2
• sparse-structure-selection - implementation of the imagenet classification experiments in the paper Data-Driven Sparse Structure Selection for Deep Neural Networks. | MXNet| Apache License

PyTorch <a name="pytorch"/>

• Deep Video Analytics
• detectron2 - of-the-art object detection algorithms | PyTorch | Apache License 2.0
• FastPhotoStyle - form Solution to Photorealistic Image Stylization. | PyTorch| Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International Public Licens
• pytorch-CycleGAN-and-pix2pix - form Solution to Photorealistic Image Stylization. | PyTorch| BSD License
• maskrcnn-benchmark - benchmark/master/LICENSE )
• deep-image-prior - image-prior/master/LICENSE )
• StarGAN - Domain Image-to-Image Translation. | PyTorch| MIT License
• faster-rcnn.pytorch - CNN implementation, aimed to accelerating the training of faster R-CNN object detection models. | PyTorch| MIT License
• pix2pixHD
• Augmentor
• albumentations - team/albumentations/master/LICENSE )
• semantic-segmentation-pytorch - Clause License]( https://raw.githubusercontent.com/CSAILVision/semantic-segmentation-pytorch/master/LICENSE )
• An End-to-End Trainable Neural Network for Image-based Sequence Recognition - based sequence recognition tasks, such as scene text recognition and OCR. | PyTorch| The MIT License (MIT)
• UNIT - GAN algorithm for Unsupervised Image-to-Image Translation. | PyTorch| Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International Public License
• Neural Sequence labeling model - of-speech (POS) tagging and word segmentation. | PyTorch| Apache License
• faster rcnn - 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
• pytorch-semantic-segmentation - semantic-segmentation/master/LICENSE )
• image-classification-mobile - 1K. | PyTorch| MIT License
• FaderNetworks - NIPS 2017. | PyTorch| Creative Commons Attribution-NonCommercial 4.0 International Public License
• neuraltalk2-pytorch
• RandWireNN
• stackGAN-v2 - v2/master/LICENSE )
• Detectron models for Object Detection - rocco/detectorch/master/LICENSE )
• DEXTR-PyTorch - most, right-most, top, bottom pixels) as input to obtain precise object segmentation for images and videos. | PyTorch| GNU GENERAL PUBLIC LICENSE
• pointnet.pytorch
• self-critical.pytorch - critical Sequence Training for Image Captioning and Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering. | PyTorch| MIT License
• vnet.pytorch - Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation. | PyTorch| BSD 3-Clause License
• piwise - wise segmentation on VOC2012 dataset using pytorch. | PyTorch| BSD 3-Clause License
• pspnet-pytorch
• pytorch-SRResNet - Realistic Single Image Super-Resolution Using a Generative Adversarial Network. | PyTorch| The MIT License (MIT)
• PNASNet.pytorch - 5 on ImageNet. | PyTorch| Apache License
• img_classification_pk_pytorch - of-the-art models. | PyTorch| Not Found
• Deep Neural Networks are Easily Fooled - cnn-adversarial-attacks/master/LICENSE )
• pix2pix-pytorch - to-Image Translation Using Conditional Adversarial Networks". | PyTorch| Not Found
• NVIDIA/semantic-segmentation - NC-SA 4.0 license]( https://raw.githubusercontent.com/NVIDIA/semantic-segmentation/master/LICENSE )
• Neural-IMage-Assessment
• torchxrayvision - ray (CXR) pathology predictions. Medical, Healthcare, Radiology | PyTorch | Apache License |
• EDSR-PyTorch - Resolution'. | PyTorch| MIT License
• pytorch-image-models - (SE)ResNet/ResNeXT, DPN, EfficientNet, MixNet, MobileNet-V3/V2, MNASNet, Single-Path NAS, FBNet, and more | PyTorch | Apache License 2.0 |
• Neural-IMage-Assessment

Tensorflow <a name="tensorflow"/>

• ObjectDetection
• MobileNet
• DeepLab
• DCSCN Super Resolution - Image Super-Resolution (SISR) model. | Tensorflow| Not Found
• Im2txt - to-text neural network for image captioning. | Tensorflow| Apache License
• SLIM - Slim. | Tensorflow| Apache License
• DELF
• Compression - trained Residual GRU network. | Tensorflow| Apache License
• AttentionOCR - world image text extraction. | Tensorflow| Apache License
• Mask R-CNN
• Faster-RCNN - a convnet for object detection with a region proposal network. | Tensorflow| MIT License
• YOLO TensorFlow - Time Object Detection. | Tensorflow| Custom
• YOLO TensorFlow ++ - Time Object Detection', with training and an actual support for real-time running on mobile devices. | Tensorflow| GNU GENERAL PUBLIC LICENSE
• Colornet
• SRGAN - Realistic Single Image Super-Resolution Using a Generative Adversarial Network. | Tensorflow| Not Found
• DeepOSM
• Domain Transfer Network - Domain Image Generation. | Tensorflow| MIT License
• Show, Attend and Tell - attend-and-tell/master/LICENSE )
• android-yolo - time object detection on Android using the YOLO network, powered by TensorFlow. | Tensorflow| Apache License
• GAN-CLS
• U-Net
• Improved CycleGAN

• Model Serving

Other Pre-trained Models

• NLP Pre-trained Models
• Audio and Speech Pre-trained Models

What is pre-trained Model?

• ImageNet