DeepLabV3-ResNet50

简介

Deep Convolutional Neural Network model for semantic segmentation.
DeepLabV3 is designed for semantic segmentation at multiple scales, trained on the COCO dataset. It uses ResNet50 as a backbone.

效果视频

规格与下载

技术细节

Model checkpoint:COCO_WITH_VOC_LABELS_V1
Input resolution:513x513
Number of output classes:21
Number of parameters:39.6M
Model size (float):151 MB

应用领域

Anomaly Detection
Inventory Management

授权信息

Source Model: BSD-3-CLAUSE
Deployable Model: AI-HUB-MODELS-LICENSE