Res2Net-PretrainedModels

The Backbone Framework

Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.

??? 专注于YOLO11，YOLOv8、TYOLOv12、YOLOv10、RT-DETR、YOLOv7、YOLOv5改进模型，Support to improve backbone, neck, head, loss, IoU, NMS and other modules?

[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with Hierarchical Attention

The Tensorflow, Keras implementation of U-net, V-net, U-net++, UNET 3+, Attention U-net, R2U-net, ResUnet-a, U^2-Net, TransUNET, and Swin-UNET with optional ImageNet-trained backbones.

More readable and flexible yolov5 with more backbone(gcn, resnet, shufflenet, moblienet, efficientnet, hrnet, swin-transformer, etc) and (cbam，dcn and so on), and tensorrt

TensorLayerX: A Unified Deep Learning and Reinforcement Learning Framework for All Hardwares, Backends and OS.

ConvMAE: Masked Convolution Meets Masked Autoencoders

Fast text based video editing, node Electron Os X desktop app, with Backbone front end.

[ICML 2023] Official PyTorch implementation of Global Context Vision Transformers