AOT-GAN

High resolution image in-painting on-device.

AOT-GAN is a machine learning model that allows to erase and in-paint part of given input image.

Qualcomm® QCS8550
QCS8550 (Proxy)
161ms
Inference Time
3-13MB
Memory Usage
235NPU
Layers

Technical Details

Model checkpoint:CelebAHQ
Input resolution:512x512
Number of parameters:15.2M
Model size:58.0 MB

Applicable Scenarios

  • Image editing

Licenses

Source Model:MIT
Deployable Model:AI Model Hub License

Supported IoT Devices

  • QCS8550 (Proxy)

Supported IoT Chipsets

  • Qualcomm® QCS8550