Rain removal model lightweight method, system, equipment and medium
The invention discloses a rain removal model lightweight method, system, device and medium, and belongs to the field of deep learning, and the method comprises the steps: obtaining an original rain removal model, and setting a self-adaptive down-sampling module at the input side of the original rain...
Saved in:
Main Authors | , , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
07.04.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention discloses a rain removal model lightweight method, system, device and medium, and belongs to the field of deep learning, and the method comprises the steps: obtaining an original rain removal model, and setting a self-adaptive down-sampling module at the input side of the original rain removal model to form a self-adaptive down-sampling acceleration module; dynamically constructing a feature extraction module, wherein the calculated amount of the feature extraction module is matched with the calculated amount of the adaptive down-sampling acceleration module; designing a feature fusion module for performing feature fusion on the output of the adaptive down-sampling acceleration module and the output of the feature extraction module; and carrying out optimization training on a lightweight rain removal model, wherein the lightweight rain removal model comprises an adaptive downsampling acceleration module, a feature extraction module and a feature fusion module. On the basis of ensuring the rain r |
---|---|
Bibliography: | Application Number: CN202310157343 |