DeepLab-V3 (ResNet): Semantic Segmentation
DeepLab-V3(ResNet) is a powerful semantic segmentation model that combines the DeepLab-V3 architecture with a ResNet backbone. DeepLab-V3 enhances segmentation accuracy by using Atrous Spatial Pyramid Pooling (ASPP) and an encoder-decoder structure, which are effective in extracting multi-scale features and performing precise segmentation in complex scenes. ResNet, serving as the backbone, leverages residual connections to mitigate the vanishing gradient problem in deep networks, enabling efficient learning of deep image features. This combined model excels in semantic segmentation tasks and is widely applied in areas like autonomous driving, medical image segmentation, and urban scene understanding, providing accurate segmentation in challenging images.
Source model
- Input shape: 520x520
- Number of parameters: 40.06M
- Model size: 160.16M
- Output shape: 1x21x520x520
Source model repository: DeepLab-V3 (ResNet)
Performance Reference
Please search model by model name in Model Farm
Inference & Model Conversion
Please search model by model name in Model Farm
License
Source Model: BSD-3-CLAUSE
Deployable Model: APLUX-MODEL-FARM-LICENSE
- Downloads last month
- 5