内容简介：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%
Computer Vision Pretrained Models
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 data to identify images in those pictures.
Framework
Model visualization
You can see visualizations of each model's network architecture by using Netron .
Tensorflow
| Model Name | Description | Framework |
|---|---|---|
| ObjectDetection | Localizing and identifying multiple objects in a single image. | Tensorflow |
| Mask R-CNN | 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 |
| Faster-RCNN | This is an experimental Tensorflow implementation of Faster RCNN - a convnet for object detection with a region proposal network. | Tensorflow |
| YOLO TensorFlow | This is tensorflow implementation of the YOLO:Real-Time Object Detection. | Tensorflow |
| YOLO TensorFlow ++ | TensorFlow implementation of 'YOLO: Real-Time Object Detection', with training and an actual support for real-time running on mobile devices. | Tensorflow |
| MobileNet | MobileNets trade off between latency, size and accuracy while comparing favorably with popular models from the literature. | Tensorflow |
| DeepLab | Deep labeling for semantic image segmentation. | Tensorflow |
| Colornet | Neural Network to colorize grayscale images. | Tensorflow |
| SRGAN | Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network. | Tensorflow |
| DeepOSM | Train TensorFlow neural nets with OpenStreetMap features and satellite imagery. | Tensorflow |
| Domain Transfer Network | Implementation of Unsupervised Cross-Domain Image Generation. | Tensorflow |
| Show, Attend and Tell | Attention Based Image Caption Generator. | Tensorflow |
| android-yolo | Real-time object detection on Android using the YOLO network, powered by TensorFlow. | Tensorflow |
| DCSCN Super Resolution | 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 |
| GAN-CLS | This is an experimental tensorflow implementation of synthesizing images. | Tensorflow |
| U-Net | For Brain Tumor Segmentation. | Tensorflow |
| Improved CycleGAN | Unpaired Image to Image Translation. | Tensorflow |
| Im2txt | Image-to-text neural network for image captioning. | Tensorflow |
| Street | Identify the name of a street (in France) from an image using a Deep RNN. | Tensorflow |
| SLIM | Image classification models in TF-Slim. | Tensorflow |
| DELF | Deep local features for image matching and retrieval. | Tensorflow |
| Compression | Compressing and decompressing images using a pre-trained Residual GRU network. | Tensorflow |
| AttentionOCR | A model for real-world image text extraction. | Tensorflow |
Keras
| Model Name | Description | Framework |
|---|---|---|
| Mask R-CNN | 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 |
| VGG16 | Very Deep Convolutional Networks for Large-Scale Image Recognition. | Keras |
| VGG19 | Very Deep Convolutional Networks for Large-Scale Image Recognition. | Keras |
| ResNet | Deep Residual Learning for Image Recognition. | Keras |
| Image analogies | Generate image analogies using neural matching and blending. | Keras |
| Popular Image Segmentation Models | Implementation of Segnet, FCN, UNet and other models in Keras. | Keras |
| Ultrasound nerve segmentation | This tutorial shows how to use Keras library to build deep neural network for ultrasound image nerve segmentation. | Keras |
| DeepMask object segmentation | This is a Keras-based Python implementation of DeepMask- a complex deep neural network for learning object segmentation masks. | Keras |
| Monolingual and Multilingual Image Captioning | AThis is the source code that accompanies Multilingual Image Description with Neural Sequence Models . | Keras |
| pix2pix | Keras implementation of Image-to-Image Translation with Conditional Adversarial Networks by Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, Alexei A. | Keras |
| Colorful Image colorization | B&W to color. | Keras |
| CycleGAN | Implementation of _Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks. | Keras |
| DualGAN | Implementation of _DualGAN: Unsupervised Dual Learning for Image-to-Image Translation. | Keras |
| Super-Resolution GAN | Implementation of _Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network. | Keras |
PyTorch
| Model Name | Description | Framework |
|---|---|---|
| FastPhotoStyle | A Closed-form Solution to Photorealistic Image Stylization. | PyTorch |
| pytorch-CycleGAN-and-pix2pix | A Closed-form Solution to Photorealistic Image Stylization. | PyTorch |
| maskrcnn-benchmark | Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch. | PyTorch |
| deep-image-prior | Image restoration with neural networks but without learning. | PyTorch |
| StarGAN | StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Tranlsation. | PyTorch |
| 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 |
| pix2pixHD | Synthesizing and manipulating 2048x1024 images with conditional GANs. | PyTorch |
| Augmentor | Image augmentation library in Python for machine learning. | PyTorch |
| albumentations | Fast image augmentation library. | PyTorch |
| Deep Video Analytics | Deep Video Analytics is a platform for indexing and extracting information from videos and images | PyTorch |
| semantic-segmentation-pytorch | Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset. | PyTorch |
| An End-to-End Trainable Neural Network for Image-based Sequence Recognition | 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 |
| UNIT | PyTorch Implementation of our Coupled VAE-GAN algorithm for Unsupervised Image-to-Image Translation. | PyTorch |
| Neural Sequence labeling model | 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 |
| faster rcnn | 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 |
| pytorch-semantic-segmentation | PyTorch for Semantic Segmentation. | PyTorch |
| EDSR-PyTorch | PyTorch version of the paper 'Enhanced Deep Residual Networks for Single Image Super-Resolution. | PyTorch |
| image-classification-mobile | Collection of classification models pretrained on the ImageNet-1K. | PyTorch |
| FaderNetworks | Fader Networks: Manipulating Images by Sliding Attributes - NIPS 2017. | PyTorch |
| neuraltalk2-pytorch | Image captioning model in pytorch(finetunable cnn in branch with_finetune). | PyTorch |
| RandWireNN | Implementation of: "Exploring Randomly Wired Neural Networks for Image Recognition". | PyTorch |
| stackGAN-v2 | Pytorch implementation for reproducing StackGAN_v2 results in the paper StackGAN++. | PyTorch |
| Detectron models for Object Detection | This code allows to use some of the Detectron models for object detection from Facebook AI Research with PyTorch. | PyTorch |
| 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 |
| pointnet.pytorch | Pytorch implementation for "PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. | PyTorch |
| 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 |
| vnet.pytorch | A Pytorch implementation for V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation. | PyTorch |
| piwise | Pixel-wise segmentation on VOC2012 dataset using pytorch. | PyTorch |
| pspnet-pytorch | PyTorch implementation of PSPNet segmentation network. | PyTorch |
| pytorch-SRResNet | Pytorch implementation for Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network. | PyTorch |
| PNASNet.pytorch | PyTorch implementation of PNASNet-5 on ImageNet. | PyTorch |
| img_classification_pk_pytorch | Quickly comparing your image classification models with the state-of-the-art models. | PyTorch |
| Deep Neural Networks are Easily Fooled | AHigh Confidence Predictions for Unrecognizable Images. | PyTorch |
| pix2pix-pytorch | PyTorch implementation of "Image-to-Image Translation Using Conditional Adversarial Networks". | PyTorch |
| NVIDIA/semantic-segmentation | A PyTorch Implementation of Improving Semantic Segmentation via Video Propagation and Label Relaxation, In CVPR2019. | PyTorch |
| Neural-IMage-Assessment | A PyTorch Implementation of Neural IMage Assessment. | PyTorch |
Caffe
| Model Name | Description | Framework |
|---|---|---|
| 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 |
| Fully Convolutional Networks for Semantic Segmentation | Fully Convolutional Models for Semantic Segmentation. | Caffe |
| Colorful Image Colorization | Colorful Image Colorization. | Caffe |
| R-FCN | R-FCN: Object Detection via Region-based Fully Convolutional Networks. | Caffe |
| 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 |
| DeconvNet | Learning Deconvolution Network for Semantic Segmentation. | Caffe |
MXNet
| Model Name | Description | Framework |
|---|---|---|
| Faster RCNN | Region Proposal Network solves object detection as a regression problem. | MXNet |
| SSD | SSD is an unified framework for object detection with a single network. | MXNet |
| Faster RCNN+Focal Loss | The code is unofficial version for focal loss for Dense Object Detection. | MXNet |
| CNN-LSTM-CTC | 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 |
| Faster_RCNN_for_DOTA | This is the official repo of paper _DOTA: A Large-scale Dataset for Object Detection in Aerial Images. | MXNet |
| RetinaNet | Focal loss for Dense Object Detection. | MXNet |
| MobileNetV2 | 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 |
| 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 |
| MobileNetV2 | 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 |
| 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 |
| FastPhotoStyle | A Closed-form Solution to Photorealistic Image Stylization. | MXNet |
| FastPhotoStyle | A Closed-form Solution to Photorealistic Image Stylization. | MXNet |
Contributions
Contributions are also very welcome.
License
以上所述就是小编给大家介绍的《List of computer vision pre-trained model》，希望对大家有所帮助，如果大家有任何疑问请给我留言，小编会及时回复大家的。在此也非常感谢大家对 码农网 的支持！
猜你喜欢:
本站部分资源来源于网络，本站转载出于传递更多信息之目的，版权归原作者或者来源机构所有，如转载稿涉及版权问题，请联系我们。
文本上的算法——深入浅出自然语言处理
路彦雄 / 人民邮电出版社 / 2018-3-1 / 69.00元
本书结合作者多年学习和从事自然语言处理相关工作的经验，力图用生动形象的方式深入浅出地介绍自然语言处理的理论、方法和技术。本书抛弃掉繁琐的证明，提取出算法的核心，帮助读者尽快地掌握自然语言处理所必备的知识和技能。本书主要分两大部分。第一部分是理论篇，包含前3章内容，主要介绍一些基础的数学知识、优化理论知识和一些机器学习的相关知识。第二部分是应用篇，包含第4章到第8章，分别针对计算性能、文本处理的术语......一起来看看 《文本上的算法——深入浅出自然语言处理》 这本书的介绍吧!
