Implementation of popular deep learning networks with TensorRT network definition API

DeepLab v3+ model in PyTorch. Support different backbones.

MobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB:fire::fire::fire:

This is a pytorch repository of YOLOv4, attentive YOLOv4 and mobilenet YOLOv4 with PASCAL VOC and COCO

Face Mask Detection system based on computer vision and deep learning using OpenCV and Tensorflow/Keras

Caffe Implementation of Google's MobileNets (v1 and v2)

Code for our CVPR2021 paper coordinate attention

High level network definitions with pre-trained weights in TensorFlow

MobileNetV3 in pytorch and ImageNet pretrained models

🔥 (yolov3 yolov4 yolov5 unet ...)A mini pytorch inference framework which inspired from darknet.

72.8% MobileNetV2 1.0 model on ImageNet and a spectrum of pre-trained MobileNetV2 models

LightNet: Light-weight Networks for Semantic Image Segmentation (Cityscapes and Mapillary Vistas Dataset)

Real-time portrait segmentation for mobile devices

Light-weight Single Person Pose Estimator

A PyTorch implementation of "MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer"

Caffe implementation of SSD and SSDLite detection on MobileNetv2, converted from tensorflow.

A PyTorch implementation of "CoAtNet: Marrying Convolution and Attention for All Data Sizes"

A Keras implementation of MobileNetV2.

yolov3 with mobilenetv2 and efficientnet

Yolov5/Yolov4/ Yolov3/ Yolo_tiny in tensorflow

基于CenterNet训练的目标检测&人脸对齐&姿态估计模型

RetinaFace (Single-stage Dense Face Localisation in the Wild, 2019) implemented (ResNet50, MobileNetV2 trained on single GPU) in Tensorflow 2.0+. This is an unofficial implementation. With Colab.

A PyTorch implementation of Mnasnet: MnasNet: Platform-Aware Neural Architecture Search for Mobile.

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

适用于移动端的人脸识别模型，计算量与mobilefacenet相同，但megaface上提升了2%+

Learning and Building Convolutional Neural Networks using PyTorch

A Complete and Simple Implementation of MobileNet-V2 in PyTorch

RM Operation can equivalently convert ResNet to VGG, which is better for pruning; and can help RepVGG perform better when the depth is large.

基于MobileNetV2/EfficientNet-b0/... + LSTM + CTC的不定长图像识别训练pytorch框架

yolov3 by pytorch