Deeplabv3 | PyTorch
pytorch.org › hub › pytorch_vision_deeplabv3_resnet101Deeplabv3-MobileNetV3-Large is constructed by a Deeplabv3 model using the MobileNetV3 large backbone. The pre-trained model has been trained on a subset of COCO train2017, on the 20 categories that are present in the Pascal VOC dataset. Their accuracies of the pre-trained models evaluated on COCO val2017 dataset are listed below. Model structure.
For Researchers - PyTorch
https://pytorch.org/hub/research-modelsPyTorch HubFor Researchers. PyTorch. Hub. For Researchers. Resnet Style Video classification networks pretrained on the Kinetics 400 dataset. MiDaS models for computing relative depth from a single image. Silero Speech-To-Text ... A set of compact enterprise-grade pre-trained STT Models for multiple languages.