All Projects → 1044197988 → Awesome-Tensorflow2

1044197988 / Awesome-Tensorflow2

Licence: Apache-2.0 license
基于Tensorflow2开发的优秀扩展包及项目

Projects that are alternatives of or similar to Awesome-Tensorflow2

Imgclsmob
Sandbox for training deep learning networks
Stars: ✭ 2,405 (+5244.44%)
Mutual labels:  classification, segmentation, tensorflow2
Android-Machine-Learning-With-TensorFlow
Tensor Flow implementation for Android
Stars: ✭ 17 (-62.22%)
Mutual labels:  tensorflow-experiments, tensorflow-models, tensorflow-examples
Tensorflow-Wide-Deep-Local-Prediction
This project demonstrates how to run and save predictions locally using exported tensorflow estimator model
Stars: ✭ 28 (-37.78%)
Mutual labels:  tensorflow-experiments, tensorflow-models, tensorflow-examples
FineGrainedVisualRecognition
Fine grained visual recognition tensorflow baseline on CUB, Stanford Cars, Dogs, Aircrafts, and Flower102.
Stars: ✭ 19 (-57.78%)
Mutual labels:  classification, tensorflow-experiments, tensorflow-models
Age-Gender Estimation TF-Android
Age + Gender Estimation on Android with TensorFlow Lite
Stars: ✭ 34 (-24.44%)
Mutual labels:  tensorflow-experiments, tensorflow-models, tensorflow-examples
gans-2.0
Generative Adversarial Networks in TensorFlow 2.0
Stars: ✭ 76 (+68.89%)
Mutual labels:  tensorflow-models, tensorflow-examples, tensorflow2
Math object detection
An image recognition/object detection model that detects handwritten digits and simple math operators. The output of the predicted objects (numbers & math operators) is then evaluated and solved.
Stars: ✭ 52 (+15.56%)
Mutual labels:  tensorflow-experiments, tensorflow-models, tensorflow-examples
Deep Learning For Image Processing
deep learning for image processing including classification and object-detection etc.
Stars: ✭ 5,808 (+12806.67%)
Mutual labels:  classification, segmentation, tensorflow2
TF2-GAN
🐳 GAN implemented as Tensorflow 2.X
Stars: ✭ 61 (+35.56%)
Mutual labels:  tf2, tensorflow-examples, tensorflow2
Dive Into Dl Tensorflow2.0
本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为TensorFlow 2.0实现,项目已得到李沐老师的认可
Stars: ✭ 3,380 (+7411.11%)
Mutual labels:  tutorials, tensorflow2
Awesome Carla
👉 CARLA resources such as tutorial, blog, code and etc https://github.com/carla-simulator/carla
Stars: ✭ 246 (+446.67%)
Mutual labels:  tutorials, segmentation
EEG-Motor-Imagery-Classification-CNNs-TensorFlow
EEG Motor Imagery Tasks Classification (by Channels) via Convolutional Neural Networks (CNNs) based on TensorFlow
Stars: ✭ 125 (+177.78%)
Mutual labels:  tensorflow-experiments, tensorflow-models
Yolov3 Tf2
YoloV3 Implemented in Tensorflow 2.0
Stars: ✭ 2,327 (+5071.11%)
Mutual labels:  tf2, tensorflow-examples
keras efficientnet v2
self defined efficientnetV2 according to official version. Including converted ImageNet/21K/21k-ft1k weights.
Stars: ✭ 56 (+24.44%)
Mutual labels:  tf2, tensorflow2
TensorFlow-Binary-Image-Classification-using-CNN-s
Binary Image Classification in TensorFlow
Stars: ✭ 26 (-42.22%)
Mutual labels:  tensorflow-models, tensorflow-examples
tf-faster-rcnn
Tensorflow 2 Faster-RCNN implementation from scratch supporting to the batch processing with MobileNetV2 and VGG16 backbones
Stars: ✭ 88 (+95.56%)
Mutual labels:  tf2, tensorflow2
manning tf2 in action
The official code repository for "TensorFlow in Action" by Manning.
Stars: ✭ 61 (+35.56%)
Mutual labels:  tf2, tensorflow2
TensorFlow-Multiclass-Image-Classification-using-CNN-s
Balanced Multiclass Image Classification with TensorFlow on Python.
Stars: ✭ 57 (+26.67%)
Mutual labels:  tensorflow-experiments, tensorflow-models
CRNN.tf2
Convolutional Recurrent Neural Network(CRNN) for End-to-End Text Recognition - TensorFlow 2
Stars: ✭ 131 (+191.11%)
Mutual labels:  tf2, tensorflow2
Machine-Learning
🌎 I created this repository for educational purposes. It will host a number of projects as part of the process .
Stars: ✭ 38 (-15.56%)
Mutual labels:  tensorflow-experiments, tensorflow-models

Awesome-Tensorflow2 💛 Awesome

基于Tensorflow2开发的优秀扩展包及项目 Tensorflow

Tensorflow2说明

2019 谷歌开发者大会于 9 月 10 日和 11 日在上海举办,大会将分享众多开发经验与工具。在第一天的 KeyNote 中,谷歌发布了很多开发工具新特性,并介绍而它们是如何构建更好的应用。值得注意的是,TensorFlow 刚刚发布了 2.0 RC01 版和 1.15,谷歌表示 1.15 是 1.x 的最后一次更新了。TensorFlow 2.0 相信大家已经非常熟悉了,它重点还是放在优化 Keras 和 Eager Execution 的能力,它希望通过这两种 API 简化整个开发流程。所以,未来的趋势肯定是Tensorflow2.0,在此我整合了许多的优秀库及项目到这个贡献库里。

提示

有些项目目前仍在进行中,将在未来支持Tensorflow2,这样的项目也包含在下面列表中。(意味着目前并不支持二版本)

Contents 👈

Tutorials 💛💛💛💛💛

Model 💛💛💛💛💛

Classification 分类

  • tensorflow/models
    该存储库包含在TensorFlow中实现的许多不同模型。
  • 1044197988/TF.Keras-Commonly-used-models
    该贡献库为我整理的一些常用的分类、分割模型,包含分割的一些指标、损失函数,但不提供预训练模型的载入。分割模型列表如下:
    Segmentation

Large library 大型库

Model 模型

Capsnet model 胶囊网络模型
Semi-supervised learning 半监督学习
Generative-models and Self encoder 生成模型和自编码

Segmentation 分割

Large library 大型库

Model 模型

Super resolution 超分辨率

Model 模型

  • krasserm/super-resolution
    包含以下模型:
    用于单图像超分辨率(EDSR)的增强型深度残留网络,是NTIRE 2017超分辨率挑战赛的冠军。
    广泛激活以实现高效,准确的图像超分辨率(WDSR),是NTIRE 2018超分辨率挑战赛(真实轨道)的获胜者。
    使用生成对抗网络(SRGAN)的逼真的单图像超分辨率。
  • HasnainRaz/Fast-SRGAN
  • gs18113/ESPCN-TensorFlow2

Object detection 目标检测

Model 模型

NLP Model 自然语言处理模型

Large library 大型库

  • tensorflow/tensor2tensor
    Tensor2Tensor或简称T2T,是一个深度学习模型和数据集的库,旨在使深度学习更易于访问并加速ML研究。Google Brain团队和用户社区的研究人员和工程师积极使用和维护T2T 。
  • huggingface/transformers
    TensorFlow 2.0和PyTorch的最新自然语言处理,(以前称为pytorch-transformers和pytorch-pretrained-bert)提供用于自然语言理解(NLU)和自然语言生成(NLG)的最新通用架构(BERT,GPT-2,RoBERTa,XLM,DistilBert,XLNet ...) )包含超过32种以100多种语言编写的预训练模型,以及TensorFlow 2.0和PyTorch之间的深层互操作性。

Model 模型

Point Model 点云模型

Projects 💛💛💛💛💛

视觉较大项目

分割

NLP

目标检测

验证码识别

文字检测、识别

人脸识别

Other 💛💛💛💛💛

脚本

解释性工具

推荐系统和CTR预测模型

用于分布式培训,评估,模型选择和快速原型制作

AutoML

元学习

强化学习

神经结构化学习

强大的扩展

迭代矩阵平方根归一化网络(称为快速MPN-COV),该网络非常有效,适合大规模数据集

TF-GAN是用于培训和评估生成对抗网络GAN的轻量级库

官方数据集包

NLP

大型基于TF2的封装扩展库

TF2项目模板

GCN图神经网络

RBF径向基

新型的高性能可解释的深表格式数据学习网络TabNet

优化器

用于单通道语音分离的双路径RNN

新型数据处理技术

使用tensorflow 2构建的多任务学习包

TensowFlow2.0上的CBAM(卷积块注意模块)实现

Spektral是一个基于Keras API和TensorFlow 2的用于图深度学习的Python库。该项目的主要目标是提供一个简单而灵活的框架来创建图神经网络(GNN)。

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].