| library_name: pytorch | |
|  | |
| DeepLabV3+ extends atrous convolution–based semantic segmentation with an encoder–decoder structure that refines object boundaries while preserving rich contextual information. | |
| Original paper: [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation (DeepLabV3+)](https://arxiv.org/abs/1802.02611) | |
| # DeepLabV3Plus-ResNet50 | |
| This model uses DeepLabV3+ with a ResNet-50 backbone, combining multi-scale context aggregation from atrous spatial pyramid pooling (ASPP) with a lightweight decoder for sharper segmentation outputs. It is well suited for semantic segmentation tasks in applications such as autonomous driving, robotics, and scene understanding, where accuracy and robustness are critical. | |
| Model Configuration: | |
| - Reference implementation: [DeepLabV3Plus_ResNet50_v1](https://github.com/VainF/DeepLabV3Plus-Pytorch) | |
| - Original Weight: [DeepLabV3Plus_ResNet50_Weights.Pascal_VOC2012_Aug](https://www.dropbox.com/scl/fi/c9rjpskx4clzfupkhn5cr/best_deeplabv3plus_resnet50_voc_os16.pth?rlkey=h066ot2cbg27qqou21ynow5nb&e=1&dl=0%2Fbest_deeplabv3plus_resnet50_voc_os16.pth) | |
| - Resolution: 3x513x513 | |
| - Support Cooper version: | |
| - Cooper SDK: [2.5.2] | |
| - Cooper Foundry: [2.2] | |
| | Model | Device | Model Link | | |
| | :----------------------: | :------: | :----------------------------------------------------------------------------------------------------------------------: | | |
| | DeepLabV3Plus-ResNet50 | N1-655 | [Model_Link](https://huggingface.co/Ambarella/DeepLabV3Plus/blob/main/n1-655_deeplab_v3plus_resnet50.bin) | | |
| | DeepLabV3Plus-ResNet50 | CV72 | [Model_Link](https://huggingface.co/Ambarella/DeepLabV3Plus/blob/main/cv72_deeplab_v3plus_resnet50.bin) | | |
| | DeepLabV3Plus-ResNet50 | CV75 | [Model_Link](https://huggingface.co/Ambarella/DeepLabV3Plus/blob/main/cv75_deeplab_v3plus_resnet50.bin) | | |