Jacinto Ai DevkitTraining & Quantization of embedded friendly Deep Learning / Machine Learning / Computer Vision models
Stars: ✭ 49 (-30%)
Caffenet BenchmarkEvaluation of the CNN design choices performance on ImageNet-2012.
Stars: ✭ 700 (+900%)
Php Opencv ExamplesTutorial for computer vision and machine learning in PHP 7/8 by opencv (installation + examples + documentation)
Stars: ✭ 333 (+375.71%)
ImgclsmobSandbox for training deep learning networks
Stars: ✭ 2,405 (+3335.71%)
Pinto model zooA repository that shares tuning results of trained models generated by TensorFlow / Keras. Post-training quantization (Weight Quantization, Integer Quantization, Full Integer Quantization, Float16 Quantization), Quantization-aware training. TensorFlow Lite. OpenVINO. CoreML. TensorFlow.js. TF-TRT. MediaPipe. ONNX. [.tflite,.h5,.pb,saved_model,tfjs,tftrt,mlmodel,.xml/.bin, .onnx]
Stars: ✭ 634 (+805.71%)
Cnn ModelsImageNet pre-trained models with batch normalization for the Caffe framework
Stars: ✭ 355 (+407.14%)
Densenet CaffeDenseNet Caffe Models, converted from https://github.com/liuzhuang13/DenseNet
Stars: ✭ 350 (+400%)
Mobilenet CaffeCaffe Implementation of Google's MobileNets (v1 and v2)
Stars: ✭ 1,217 (+1638.57%)
ppqPPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.
Stars: ✭ 281 (+301.43%)
Caffe ModelCaffe models (including classification, detection and segmentation) and deploy files for famouse networks
Stars: ✭ 1,258 (+1697.14%)
Senet CaffeA Caffe Re-Implementation of SENet
Stars: ✭ 169 (+141.43%)
deepvacPyTorch Project Specification.
Stars: ✭ 507 (+624.29%)
colorchecker-detectionMultiple ColorChecker Detection. This code implements a multiple colorChecker detection method, as described in the paper Fast and Robust Multiple ColorChecker Detection.
Stars: ✭ 51 (-27.14%)
GuidedNetCaffe implementation for "Guided Optical Flow Learning"
Stars: ✭ 28 (-60%)
neural-compressorIntel® Neural Compressor (formerly known as Intel® Low Precision Optimization Tool), targeting to provide unified APIs for network compression technologies, such as low precision quantization, sparsity, pruning, knowledge distillation, across different deep learning frameworks to pursue optimal inference performance.
Stars: ✭ 666 (+851.43%)
VideoAudit📹 一个短视频APP视频内容安全审核的思路调研及实现汇总
Stars: ✭ 221 (+215.71%)
XNOR-NetXNOR-Net, CUDNN5 supported version of XNOR-Net-caffe: https://github.com/loswensiana/BWN-XNOR-caffe
Stars: ✭ 30 (-57.14%)
PSPNet-PytorchImplemetation of Pyramid Scene Parsing Network in Pytorch
Stars: ✭ 26 (-62.86%)
caffemodel2jsonA small tool to dump Caffe's *.caffemodel to JSON for inspection
Stars: ✭ 40 (-42.86%)
caffe srganA Caffe Implementation of SRGAN
Stars: ✭ 59 (-15.71%)
caffe-simnetsThe SimNets Architecture's Implementation in Caffe
Stars: ✭ 13 (-81.43%)
ImageModelsImageNet model implemented using the Keras Functional API
Stars: ✭ 63 (-10%)
onnx2caffepytorch to caffe by onnx
Stars: ✭ 341 (+387.14%)
DetectionMetricsTool to evaluate deep-learning detection and segmentation models, and to create datasets
Stars: ✭ 66 (-5.71%)
Skin Lesions Classification DCNNsTransfer Learning with DCNNs (DenseNet, Inception V3, Inception-ResNet V2, VGG16) for skin lesions classification
Stars: ✭ 47 (-32.86%)
SharpPeleeNetImageNet pre-trained SharpPeleeNet can be used in real-time Semantic Segmentation/Objects Detection
Stars: ✭ 13 (-81.43%)
MSG-NetDepth Map Super-Resolution by Deep Multi-Scale Guidance, ECCV 2016
Stars: ✭ 76 (+8.57%)
PyTorch-LMDBScripts to work with LMDB + PyTorch for Imagenet training
Stars: ✭ 49 (-30%)
local-search-quantizationState-of-the-art method for large-scale ANN search as of Oct 2016. Presented at ECCV 16.
Stars: ✭ 70 (+0%)
caffe-static在caffe应用到工程实现时,为了方便系统安装,需要尽可能减少软件的依赖库。 本项目以bash shell/PowerShell脚本实现将caffe依赖的所有第三方库与caffe静态编译一起,以满足全静态编译的要求。 通过本项目提供的脚本生成的caffe编译环境不需要在系统安装任何第三方库和软件,就可以自动完成caffe项目静态编译. 目前在centos6.5/ubuntu16/win7/win10上测试通过,windows上VS2013,VS2015,MinGW 5.2.0编译通过
Stars: ✭ 23 (-67.14%)
SAN[ECCV 2020] Scale Adaptive Network: Learning to Learn Parameterized Classification Networks for Scalable Input Images
Stars: ✭ 41 (-41.43%)
iAI🎯 保姆级深度学习从入门到放弃 🤪 🤪
Stars: ✭ 432 (+517.14%)
cisip-FIReFast Image Retrieval (FIRe) is an open source project to promote image retrieval research. It implements most of the major binary hashing methods to date, together with different popular backbone networks and public datasets.
Stars: ✭ 40 (-42.86%)
tripletRe-implementation of tripletloss function in FaceNet
Stars: ✭ 94 (+34.29%)
ghostnet.pytorch73.6% GhostNet 1.0x pre-trained model on ImageNet
Stars: ✭ 90 (+28.57%)
TokenLabelingPytorch implementation of "All Tokens Matter: Token Labeling for Training Better Vision Transformers"
Stars: ✭ 385 (+450%)
py-faster-rcnn-imagenetTrain faster rcnn on imagine dataset, related blog post: https://andrewliao11.github.io/object/detection/2016/07/23/detection/
Stars: ✭ 133 (+90%)
BAKESelf-distillation with Batch Knowledge Ensembling Improves ImageNet Classification
Stars: ✭ 79 (+12.86%)
Image2LMDBConvert image folder to lmdb, adapted from Efficient-PyTorch
Stars: ✭ 58 (-17.14%)
crowd density segmentationThe code for preparing the training data for crowd counting / segmentation algorithm.
Stars: ✭ 21 (-70%)
mmnMoore Machine Networks (MMN): Learning Finite-State Representations of Recurrent Policy Networks
Stars: ✭ 39 (-44.29%)
ck-crowd-scenariosPublic scenarios to crowdsource experiments (such as DNN crowd-benchmarking and crowd-tuning) using Collective Knowledge Framework across diverse mobile devices provided by volunteers. Results are continuously aggregated at the open repository of knowledge:
Stars: ✭ 22 (-68.57%)
score-zeroshotSemantically consistent regularizer for zero-shot learning
Stars: ✭ 65 (-7.14%)