60 Open source projects that are alternatives of or similar to Centermulti

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

Tensorflow 2 Faster-RCNN implementation from scratch supporting to the batch processing with MobileNetV2 and VGG16 backbones

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

DeepLabv3, DeepLabv3+ and pretrained weights on VOC & Cityscapes

No description or website provided.

Train and predict your model on pre-trained deep learning models through the GUI (web app). No more many parameters, no more data preprocessing.

yolo3 implement by tensorflow， including mobilenet_v1, mobilenet_v2

No description or website provided.

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

Real-time portrait segmentation for mobile devices

MobilePose deployment for Raspberry Pi

[ICCV 2019] Harmonious Bottleneck on Two Orthogonal Dimensions

yolov3 with mobilenetv2 and efficientnet

基于深度学习图片鉴黄 Caffe implementation of Not Suitable for Work (NSFW)

Benchmark for DeepLearning anomaly detection

Repository for "Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation".

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

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 collection of deep learning models (PyTorch implemtation)

High level network definitions with pre-trained weights in TensorFlow

Light-weight Single Person Pose Estimator

Object localization in images using simple CNNs and Keras

Try to implement deeplab v3+ on pytorch according to offical demo.

🔥Improve yolo with latest paper

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

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

[5 FPS - 150 FPS] Learning Deep Features for One-Class Classification (AnomalyDetection). Corresponds RaspberryPi3. Convert to Tensorflow, ONNX, Caffe, PyTorch. Implementation by Python + OpenVINO/Tensorflow Lite.

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

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

A Keras implementation of MobileNetV2.

MobileNet-v2 experimental network description for caffe

A real-time face mask detector based on computer vision and deep learning, created using Pytorch and OpenCV

DeepLab v3+ model in PyTorch. Support different backbones.

Image Forgery Detection using Deep Learning, implemented in PyTorch.

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

Deep learning model to estimate the depth of image.

yolov3 by pytorch

Computer vision library for wildfire detection

Multiple basenet MobileNet v1,v2, ResNet combined with SSD detection method and it's variants such as RFB, FSSD etc.

Inspired from Mask R-CNN to build a multi-task learning, two-branch architecture: one branch based on YOLOv2 for object detection, the other branch for instance segmentation. Simply tested on Rice and Shapes. MobileNet supported.

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

No description or website provided.

Train/Eval the popular network by TF-Slim,include mobilenet/shufflenet/squeezenet/resnet/inception/vgg/alexnet

caffe based mobilenet v2 deploy

Reproduction of MobileNetV2 using MXNet

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

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

[ECCV 2020] Scale Adaptive Network: Learning to Learn Parameterized Classification Networks for Scalable Input Images

Yolov5/Yolov4/ Yolov3/ Yolo_tiny in tensorflow

Edge TPU Accelerator / Multi-TPU + MobileNet-SSD v2 + Python + Async + LattePandaAlpha/RaspberryPi3/LaptopPC

MobileNetV3 in pytorch and ImageNet pretrained models

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

A PyTorch Implementation of MobileNetv2+DeepLabv3

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

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%+

A Complete and Simple Implementation of MobileNet-V2 in PyTorch

Implementation of popular deep learning networks with TensorRT network definition API

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

Light-weight Single Person Pose Estimator