Deep Learning as a Cloud API Service.
Quick Start:
Using docker
docker run -p 8080:8080 wuhanstudio/deepapi
Using python3
pip install deepapi
python -m deepapi
Serving on port 8080...
The cloud service is available at http://localhost:8080
Changelog
Supported models for research on black-box adversarial attacks,:
- Pretrained VGG16 model on Cifar10 dataset
- Pretrained VGG16 model on ImageNet dataset
- Pretrained Resnet50 model on ImageNet dataset
- Pretrained Inceptionv3 model on ImageNet dataset
The Web UI:
- Upload and recognize an image
- Automatic python client code generation
- Automatic curl client code generation
The Python API:
import numpy as np
from PIL import Image
from deepapi.api import DeepAPI_VGG16_Cifar10
Load the image
x = Image.open("dog.jpg")
x = np.array(x)
Initialize the model
model = DeepAPI_VGG16_Cifar10('http://localhost:8080', concurrency=8)
Predict
y = model.predict(np.array([x]))[0]
Print the result
model.print(y)