Displaying 1 to 17 from 17 results

tf-pose-estimation - Deep Pose Estimation implemented using Tensorflow with Custom Architectures for fast inference

  •    PureBasic

'Openpose' for human pose estimation have been implemented using Tensorflow. It also provides several variants that have made some changes to the network structure for real-time processing on the CPU or low-power embedded devices. 2018.5.21 Post-processing part is implemented in c++. It is required compiling the part. See: https://github.com/ildoonet/tf-pose-estimation/tree/master/src/pafprocess 2018.2.7 Arguments in run.py script changed. Support dynamic input size.

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

  •    Python

We provide pretrained MobileNet models on ImageNet, which achieve slightly better accuracy rates than the original ones reported in the paper.

tf-faster-rcnn - Tensorflow Faster RCNN for Object Detection

  •    Python

For a good and more up-to-date implementation for faster/mask RCNN with multi-gpu support, please see the example in TensorPack here. A Tensorflow implementation of faster RCNN detection framework by Xinlei Chen (xinleic@cs.cmu.edu). This repository is based on the python Caffe implementation of faster RCNN available here.

MobileNet-CoreML - The MobileNet neural network using Apple's new CoreML framework

  •    Swift

This is the MobileNet neural network architecture from the paper MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications implemented using Apple's shiny new CoreML framework. This uses the pretrained weights from shicai/MobileNet-Caffe.




tensornets - High level network definitions with pre-trained weights in TensorFlow

  •    Python

High level network definitions with pre-trained weights in TensorFlow (tested with >= 1.1.0). You can install TensorNets from PyPI (pip install tensornets) or directly from GitHub (pip install git+https://github.com/taehoonlee/tensornets.git).

DepthwiseConvolution - A personal depthwise convolution layer implementation on caffe by liuhao

  •    Cuda

[^nocudnn]: When turn on cudnn, the memory consuming of mobilenet would increase to unbelievable level. You may try.

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

  •    Python

This repository contains the code (in PyTorch) for: "LightNet: Light-weight Networks for Semantic Image Segmentation " (underway) by Huijun Liu @ TU Braunschweig. Semantic Segmentation is a significant part of the modern autonomous driving system, as exact understanding the surrounding scene is very important for the navigation and driving decision of the self-driving car. Nowadays, deep fully convolutional networks (FCNs) have a very significant effect on semantic segmentation, but most of the relevant researchs have focused on improving segmentation accuracy rather than model computation efficiency. However, the autonomous driving system is often based on embedded devices, where computing and storage resources are relatively limited. In this paper we describe several light-weight networks based on MobileNetV2, ShuffleNet and Mixed-scale DenseNet for semantic image segmentation task, Additionally, we introduce GAN for data augmentation[17] (pix2pixHD) concurrent Spatial-Channel Sequeeze & Excitation (SCSE) and Receptive Field Block (RFB) to the proposed network. We measure our performance on Cityscapes pixel-level segmentation, and achieve up to 70.72% class mIoU and 88.27% cat. mIoU. We evaluate the trade-offs between mIoU, and number of operations measured by multiply-add (MAdd), as well as the number of parameters.

pytorch-mobilenet - PyTorch MobileNet Implementation of "MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications"

  •    Python

PyTorch MobileNet Implementation of "MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications"


mace-models - Mobile AI Compute Engine Model Zoo

  •    

This project hosts Mobile AI Compute Engine (MACE) models. Each yml deployment script describes a case of deployments, which will generate one or one group (in case more than one ABIs specified) of static libraries and headers. To learn how to add new models, please refer to MACE documents.

ios-short-core-ml - iOS image classification app using Core ML and MobileNet

  •    Jupyter

Resources for Udacity's Core ML mini-course. This repository contains the iOS image classification app (SmartGroceryList) in various formats including its integration with and without Vision framework. A custom Core ML model is also included. If you don't have Docker installed, you can find instructions on installing here.

awesome-embedded-ai - Curated list of awesome AI resources about embedded and mobile devices

  •    

This awesome list will be continually updated. Besides, you can read new bi-weekly-reports: PerfXLab/embedded_ai. A curated list of awesome A.I. & Embedded/Mobile-devices resources, tools and more.

mk-tfjs - Play MK.js with TensorFlow.js

  •    Javascript

Source code for my article "Playing Mortal Kombat with TensorFlow.js. Transfer learning and data augmentation". You can find the post here and MK.js here.

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

  •    Python

This repo contains many object detection methods that aims at single shot and real time, so the speed is the only thing we talk about. Currently we have some base networks that support object detection task such as MobileNet V2, ResNet, VGG etc. And some SSD variants such as FSSD, RFBNet, Retina, and even Yolo are contained. If you have any faster object detection methods welcome to discuss with me to merge it into our master branches.

keras-mobile-colorizer - U-Net Model conditioned with MobileNet features for Grayscale -> Color mapping

  •    Python

Uses MobileNets for memory efficiency in comparison to Inception-ResNet-V2 so that training can be done on a single GPU (of 4 GB size minimum). Open the data_utils.py script and edit the TRAIN_IMAGE_PATH and VALIDATION_IMAGE_PATH to point to directories of images. There must be at least 1 folder pointed to by each of those paths.