Deep Learning as a Cloud API Service.

Overview

Deep API

Deep Learning as Cloud APIs.

This project provides pre-trained deep learning models as a cloud API service. A web interface is available as well.

Quick Start

Python 3:

$ pip3 install -r requirements.txt
$ python main.py

Anaconda:

$ conda env create -f environment.yml
$ conda activate cloudapi
$ python main.py

Using Docker:

docker run -p 8080:8080 wuhanstudio/deep-api

Navigate to https://localhost:8080

API Client

It's possible to get predictions by sending a POST request to http://127.0.0.1:8080/vgg16_cifar10.

Using curl:

```
export IMAGE_FILE=test/cat.jpg
(echo -n '{"file": "'; base64 $IMAGE_FILE; echo '"}') | \
curl -H "Content-Type: application/json" \
     -d @- http://127.0.0.1:8080/vgg16_cifar10
```

Using Python:

def classification(url, file):
    # Load the input image and construct the payload for the request
    image = Image.open(file)
    buff = BytesIO()
    image.save(buff, format="JPEG")

    data = {'file': base64.b64encode(buff.getvalue()).decode("utf-8")}
    return requests.post(url, json=data).json()

res = classification('http://127.0.0.1:8080/vgg', 'cat.jpg')

This python script is available in the test folder. You should see prediction results by running python3 minimal.py:

cat            0.99804
deer           0.00156
truck          0.00012
airplane       0.00010
dog            0.00009
bird           0.00005
ship           0.00003
frog           0.00001
horse          0.00001
automobile     0.00001

Concurrent clients

Sending 5 concurrent requests to the api server:

$ python3 multi-client.py --num_workers 5 cat.jpg

You should see the result:

----- start -----
Sending requests
Sending requests
Sending requests
Sending requests
Sending requests
------ end ------
Concurrent Requests: 5
Total Runtime: 2.441638708114624

Full APIs

Post URLs:

Model Dataset Post URL
VGG-16 Cifar10 http://127.0.0.1:8080/vgg16_cifar10
VGG-16 ImageNet http://127.0.0.1:8080/vgg16
Resnet-50 ImageNet http://127.0.0.1:8080/resnet50
Inception v3 ImageNet http://127.0.0.1:8080/inceptionv3

Post Data (JSON):

{
  "file": ""
}

Query Parameters:

Name Type Default Value
top integer 10 One of [1, 3, 5, 10], top=5 returns top 5 predictions.
no-prob integer 0 no-prob=1 returns labels without probabilities. no-prob=0 returns labels and probabilities.

Example post urls (returns top 10 predictions with probabilities):

http://127.0.0.1:8080/vgg16?top=10&no-prob=0

Returns (JSON):

Key Value
success True / False
Predictions Array of prediction results, each element contains {"labels": "cat", "probability": 0.99}
error The error message if any

Example returned json:

{
  "success": true,
  "predictions": [
    {
      "label": "cat",
      "probability": 0.9996376037597656
    },
    {
      "label": "dog",
      "probability": 0.0002855948405340314
    },
    {
      "label": "deer",
      "probability": 0.000021985460989526473
    },
    {
      "label": "bird",
      "probability": 0.000021391952031990513
    },
    {
      "label": "horse",
      "probability": 0.000013297495570441242
    },
    {
      "label": "airplane",
      "probability": 0.000006046993803465739
    },
    {
      "label": "ship",
      "probability": 0.0000044226785576029215
    },
    {
      "label": "frog",
      "probability": 0.0000036349929359857924
    },
    {
      "label": "truck",
      "probability": 0.0000035354278224986047
    },
    {
      "label": "automobile",
      "probability": 0.000002384880417594104
    }
  ],
}

References

You might also like...
 Deep Learning: Architectures & Methods Project: Deep Learning for Audio Super-Resolution
Deep Learning: Architectures & Methods Project: Deep Learning for Audio Super-Resolution

Deep Learning: Architectures & Methods Project: Deep Learning for Audio Super-Resolution Figure: Example visualization of the method and baseline as a

A simple rest api serving a deep learning model that classifies human gender based on their faces. (vgg16 transfare learning)
A simple rest api serving a deep learning model that classifies human gender based on their faces. (vgg16 transfare learning)

this is a simple rest api serving a deep learning model that classifies human gender based on their faces. (vgg16 transfare learning)

Pytorch implementation of Straight Sampling Network For Point Cloud Learning (ICIP2021).

Pytorch code for SS-Net This is a pytorch implementation of Straight Sampling Network For Point Cloud Learning (ICIP2021). Environment Code is tested

Deploy a ML inference service on a budget in less than 10 lines of code.
Deploy a ML inference service on a budget in less than 10 lines of code.

BudgetML is perfect for practitioners who would like to quickly deploy their models to an endpoint, but not waste a lot of time, money, and effort trying to figure out how to do this end-to-end.

An air quality monitoring service with a Raspberry Pi and a SDS011 sensor.

Raspberry Pi Air Quality Monitor A simple air quality monitoring service for the Raspberry Pi. Installation Clone the repository and run the following

Web service for facial landmark detection, head pose estimation, facial action unit recognition, and eye-gaze estimation based on OpenFace 2.0
Web service for facial landmark detection, head pose estimation, facial action unit recognition, and eye-gaze estimation based on OpenFace 2.0

OpenGaze: Web Service for OpenFace Facial Behaviour Analysis Toolkit Overview OpenFace is a fantastic tool intended for computer vision and machine le

Space-event-trace - Tracing service for spaceteam events
Space-event-trace - Tracing service for spaceteam events

space-event-trace Tracing service for TU Wien Spaceteam events. This service is

Black-Box-Tuning - Black-Box Tuning for Language-Model-as-a-Service

Black-Box-Tuning Source code for paper "Black-Box Tuning for Language-Model-as-a

PyTorch implementation of the Deep SLDA method from our CVPRW-2020 paper
PyTorch implementation of the Deep SLDA method from our CVPRW-2020 paper "Lifelong Machine Learning with Deep Streaming Linear Discriminant Analysis"

Lifelong Machine Learning with Deep Streaming Linear Discriminant Analysis This is a PyTorch implementation of the Deep Streaming Linear Discriminant

Releases(v0.1.0)
  • v0.1.0(Oct 26, 2021)

    Deep Learning as a Cloud API Service that supports:

    • Pretrained VGG16 model on Cifar10 dataset
    • Pretrained VGG16 model on ImageNet dataset
    • Pretrained Resnet50 model on ImageNet dataset
    • Pretrained Inceptionv3 model on ImageNet dataset
    • Automatic python client code generation
    • Automatic curl client code generation
    • A web interface for the api service

    A minimal version is deployed here:

    http://api.wuhanstudio.uk/

    Source code(tar.gz)
    Source code(zip)
Owner
Wu Han
Ph.D. Student at the University of Exeter in the U.K. for Autonomous System Security. Prior research experience at RT-Thread, LAIX, Xilinx.
Wu Han
TreeSubstitutionCipher - Encryption system based on trees and substitution

Tree Substitution Cipher Generation Algorithm: Generate random tree. Tree nodes

stepa 1 Jan 08, 2022
Free like Freedom

This is all very much a work in progress! More to come! ( We're working on it though! Stay tuned!) Installation Open an Anaconda Prompt (in Windows, o

2.3k Jan 04, 2023
PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice (『飞桨』核心框架,深度学习&机器学习高性能单机、分布式训练和跨平台部署)

English | 简体中文 Welcome to the PaddlePaddle GitHub. PaddlePaddle, as the only independent R&D deep learning platform in China, has been officially open

19.4k Jan 04, 2023
Large-scale Hyperspectral Image Clustering Using Contrastive Learning, CIKM 21 Workshop

Spectral-spatial contrastive clustering (SSCC) Yaoming Cai, Yan Liu, Zijia Zhang, Zhihua Cai, and Xiaobo Liu, Large-scale Hyperspectral Image Clusteri

Yaoming Cai 4 Nov 02, 2022
Implementing yolov4 target detection and tracking based on nao robot

Implementing yolov4 target detection and tracking based on nao robot

6 Apr 19, 2022
Baseline and template code for node21 detection track

Nodule Detection Algorithm This codebase implements a baseline model, Faster R-CNN, for the nodule detection track in NODE21. It contains all necessar

node21challenge 11 Jan 15, 2022
This is an official implementation for "PlaneRecNet".

PlaneRecNet This is an official implementation for PlaneRecNet: A multi-task convolutional neural network provides instance segmentation for piece-wis

yaxu 50 Nov 17, 2022
Code of TIP2021 Paper《SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition》. We provide both MxNet and Pytorch versions.

SFace Code of TIP2021 Paper 《SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition》. We provide both MxNet, PyTorch and Jittor versi

Zhong Yaoyao 47 Nov 25, 2022
Code for CPM-2 Pre-Train

CPM-2 Pre-Train Pre-train CPM-2 此分支为110亿非 MoE 模型的预训练代码,MoE 模型的预训练代码请切换到 moe 分支 CPM-2技术报告请参考link。 0 模型下载 请在智源资源下载页面进行申请,文件介绍如下: 文件名 描述 参数大小 100000.tar

Tsinghua AI 136 Dec 28, 2022
Implement of "Training deep neural networks via direct loss minimization" in PyTorch for 0-1 loss

This is the implementation of "Training deep neural networks via direct loss minimization" published at ICML 2016 in PyTorch. The implementation targe

Cuong Nguyen 1 Jan 18, 2022
Official Repository for "Robust On-Policy Data Collection for Data Efficient Policy Evaluation" (NeurIPS 2021 Workshop on OfflineRL).

Robust On-Policy Data Collection for Data-Efficient Policy Evaluation Source code of Robust On-Policy Data Collection for Data-Efficient Policy Evalua

Autonomous Agents Research Group (University of Edinburgh) 2 Oct 09, 2022
Learning to trade under the reinforcement learning framework

Trading Using Q-Learning In this project, I will present an adaptive learning model to trade a single stock under the reinforcement learning framework

Uirá Caiado 470 Nov 28, 2022
Self-supervised Product Quantization for Deep Unsupervised Image Retrieval - ICCV2021

Self-supervised Product Quantization for Deep Unsupervised Image Retrieval Pytorch implementation of SPQ Accepted to ICCV 2021 - paper Young Kyun Jang

Young Kyun Jang 71 Dec 27, 2022
scAR (single-cell Ambient Remover) is a package for data denoising in single-cell omics.

scAR scAR (single cell Ambient Remover) is a package for denoising multiple single cell omics data. It can be used for multiple tasks, such as, sgRNA

19 Nov 28, 2022
This repo contains the implementation of the algorithm proposed in Off-Belief Learning, ICML 2021.

Off-Belief Learning Introduction This repo contains the implementation of the algorithm proposed in Off-Belief Learning, ICML 2021. Environment Setup

Facebook Research 32 Jan 05, 2023
Keyword-BERT: Keyword-Attentive Deep Semantic Matching

project discription An implementation of the Keyword-BERT model mentioned in my paper Keyword-Attentive Deep Semantic Matching (Plz cite this github r

1 Nov 14, 2021
LightNet++: Boosted Light-weighted Networks for Real-time Semantic Segmentation

LightNet++ !!!New Repo.!!! ⇒ EfficientNet.PyTorch: Concise, Modular, Human-friendly PyTorch implementation of EfficientNet with Pre-trained Weights !!

linksense 237 Jan 05, 2023
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

DLR-RM 4.7k Jan 01, 2023
YOLOv5 detection interface - PyQt5 implementation

所有代码已上传,直接clone后,运行yolo_win.py即可开启界面。 2021/9/29:加入置信度选择 界面是在ultralytics的yolov5基础上建立的,界面使用pyqt5实现,内容较简单,娱乐而已。 功能: 模型选择 本地文件选择(视频图片均可) 开关摄像头

487 Dec 27, 2022
Using fully convolutional networks for semantic segmentation with caffe for the cityscapes dataset

Using fully convolutional networks for semantic segmentation (Shelhamer et al.) with caffe for the cityscapes dataset How to get started Download the

Simon Guist 27 Jun 06, 2022