Comparing YOLO and MixNet architectures for image-based human detection

tf-keras-implemented YOLOv2

Using a pre-trained efficientnet (for experimental purposes) to classifier plant diseases given an image. Plant village challenge dataset.

Extremely light-weight MixNet with Top-1 75.7% and 2.5M params

twisted python mix network library

tf-keras-implemented YOLOv3

Concise, Modular, Human-friendly PyTorch implementation of MixNet with Pre-trained Weights.

python sphinx mix net cryptography

Submission name: QualcommAI-EfficientNet. MicroNet Challenge (NeurIPS 2019) submission - Qualcomm AI Research

3rd place solution for NeurIPS 2019 MicroNet challenge

Implementing MixNet: Mixed Depthwise Convolutional Kernels using Pytorch

EfficientNet, MobileNetV3, MobileNetV2, MixNet, etc in JAX w/ Flax Linen and Objax

基于tf.keras的多标签多分类模型

A PyTorch Implementation of MixNet

LightNet++: Boosted Light-weighted Networks for Real-time Semantic Segmentation

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more