inference_deployment

• Export model
  • Catalogue
  • 1. Environmental preparation
  • 2. Export classification model
  • 3. Export mainbody detection model
  • 4. Export recognition model
  • 5. Parameter description
• Infering based on Python prediction engine
  • Catalogue
  • 1. Image classification inference
  • 2. Mainbody detection model inference
  • 3. Feature Extraction model inference
  • 4. Concatenation of mainbody detection, feature extraction and vector search
• Server-side C++ inference
  • Catalogue
  • 1. Prepare the environment
  • 2. Compile
  • 3. Run the demo
• Service deployment based on PaddleHub Serving
  • Catalogue
  • 1 Introduction
  • 2. Prepare the environment
  • 3. Download the inference model
  • 4. Install the service module
  • 5. Start service
  • 6. Send prediction requests
  • 7. User defined service module modification
• Tutorial of PaddleClas Mobile Deployment
  • Catalogue
  • 1. Preparation
  • 1.2 Download inference library for Android or iOS
  • 2. Start running
  • 2.1 Inference Model Optimization
  • 2.2 Run optimized model on Phone
  • 3. FAQ
• PaddleClas wheel package
  • Catalogue
  • 1. Installation
  • 2. Quick Start
  • 3. Definition of Parameters
  • 4. Usage