Deep Learning as a Cloud API Service.

Last update: Jan 06, 2023

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
API Client
- Using curl
- Using Python
Concurrent clients
Full APIs

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 Figure: Example visualization of the method and baseline as a

16 Dec 23, 2022

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)

5 Dec 9, 2021

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

1 May 18, 2022

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.

1.3k Dec 25, 2022

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

24 Dec 9, 2022

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

4 Nov 3, 2022

Space-event-trace - Tracing service for spaceteam events

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

2 Jan 4, 2022

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

149 Jan 4, 2023

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

41 Dec 25, 2022

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)

Deep Learning as a Cloud API Service.

Related tags

Overview

Deep API

Quick Start

Python 3:

Anaconda:

Using Docker:

API Client

Using curl:

Using Python:

Concurrent clients

Full APIs

Post URLs:

Post Data (JSON):

Query Parameters:

Returns (JSON):

References

You might also like...

Deep Learning: Architectures & Methods Project: Deep Learning for Audio Super-Resolution

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).

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

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

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

Space-event-trace - Tracing service for spaceteam events

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

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

Releases(v0.1.0)

v0.1.0(Oct 26, 2021)

Owner

Wu Han

Codes and models of NeurIPS2021 paper - DominoSearch: Find layer-wise fine-grained N:M sparse schemes from dense neural networks

SVG Icon processing tool for C++

Deploying PyTorch Model to Production with FastAPI in CUDA-supported Docker

Learning from Synthetic Shadows for Shadow Detection and Removal [Inoue+, IEEE TCSVT 2020].

Bottleneck Transformers for Visual Recognition

[CVPR 2022] Deep Equilibrium Optical Flow Estimation

GAN example for Keras. Cuz MNIST is too small and there should be something more realistic.

This repository is based on Ultralytics/yolov5, with adjustments to enable rotate prediction boxes.

A treasure chest for visual recognition powered by PaddlePaddle

Statsmodels: statistical modeling and econometrics in Python

The official implementation of CVPR 2021 Paper: Improving Weakly Supervised Visual Grounding by Contrastive Knowledge Distillation.

Collection of Docker images for ML/DL and video processing projects

Random-Afg - Afghanistan Random Old Idz Cloner Tools

Source code for the plant extraction workflow introduced in the paper “Agricultural Plant Cataloging and Establishment of a Data Framework from UAV-based Crop Images by Computer Vision”

Oriented Response Networks, in CVPR 2017

Transformers based fully on MLPs

KinectFusion implemented in Python with PyTorch

code for TCL: Vision-Language Pre-Training with Triple Contrastive Learning, CVPR 2022

YOLOv5 🚀 is a family of object detection architectures and models pretrained on the COCO dataset

MLSpace: Hassle-free machine learning & deep learning development