Nanodet⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥
EfficientnetImplementation of EfficientNet model. Keras and TensorFlow Keras.
Pytorch Image ModelsPyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more
flexible-yolov5More readable and flexible yolov5 with more backbone(resnet, shufflenet, moblienet, efficientnet, hrnet, swin-transformer) and (cbam,dcn and so on), and tensorrt
detectron2 backbonedetectron2 backbone: resnet18, efficientnet, hrnet, mobilenet v2, resnest, bifpn
TensorMONKA collection of deep learning models (PyTorch implemtation)
efficientnet-jaxEfficientNet, MobileNetV3, MobileNetV2, MixNet, etc in JAX w/ Flax Linen and Objax
efficientdetPyTorch Implementation of the state-of-the-art model for object detection EfficientDet [pre-trained weights provided]
food-detection-yolov5🍔🍟🍗 Food analysis baseline with Theseus. Integrate object detection, image classification and multi-class semantic segmentation. 🍞🍖🍕
MixNet-PyTorchConcise, Modular, Human-friendly PyTorch implementation of MixNet with Pre-trained Weights.
EfficientUNetPlusPlusDecoder architecture based on the UNet++. Combining residual bottlenecks with depthwise convolutions and attention mechanisms, it outperforms the UNet++ in a coronary artery segmentation task, while being significantly more computationally efficient.