Qualcomm® AI HubAI Hub
HomeIoT ModelsMidas-V2-Quantized

Midas-V2-Quantized

Quantized Deep Convolutional Neural Network model for depth estimation.

Midas is designed for estimating depth at each point in an image.

Model RepositoryHugging FaceResearch Paper

Technical Details

Model checkpoint:MiDaS_small
Input resolution:256x256
Number of parameters:16.6M
Model size:16.6 MB

Applicable Scenarios

  • Anomaly Detection
  • Inventory Management

Licenses

Source Model:MIT
Deployable Model:AI Model Hub License

Tags

  • quantized
    A “quantized” model can run in low or mixed precision, which can substantially reduce inference latency.

Supported IoT Devices

  • QCS8250 (Proxy)
  • QCS8550 (Proxy)
  • RB5 (Proxy)

Supported IoT Chipsets

  • Qualcomm® QCS8250
  • Qualcomm® QCS8550