jangjiun's starred repositories
pytorch-cifar100
Practice on cifar100(ResNet, DenseNet, VGG, GoogleNet, InceptionV3, InceptionV4, Inception-ResNetv2, Xception, Resnet In Resnet, ResNext,ShuffleNet, ShuffleNetv2, MobileNet, MobileNetv2, SqueezeNet, NasNet, Residual Attention Network, SENet, WideResNet)
resnet_cifar10_cifar100_imagenet
resnet_cifar10_cifar100_imagenet
resnet34-tensorflow
use cifar database to train , result better
cifar-10-cnn
Play deep learning with CIFAR datasets
CNNs_for_classifing_CIFAR10
An implement of LeNet, AlexNet, VGG16, GoogLeNet and ResNet with Tensorflow.
kaggle-cifar10
这是kaggle-cifar10的baseline
tensorflow-cifar100
High-acc(>0.7) model(ResNet, ResNeXt, DenseNet, SENet, SE-ResNeXt) on TensorFlow.
cifar10-tensorflow
cifar10数据集上进行图片分类，基于tensorflow框架，旨在探究不同的改进策略对分类准确率的影响，如何一步步得提高准确率
classification_models
Classification models trained on ImageNet. Keras.
ImageNet-Api
基于Keras+Tensorflow搭建，提供ResNet50神经网络的图片分类平台。
alexnetbenchmark
alexnet benchmark test on GPU
tensorflow_Resnet_train_test
Code for training different architectures( DenseNet, ResNet, AlexNet, GoogLeNet, VGG, NiN) on your own dataset + Multi-GPU support + batch and single image testing support
dl-4-regression
Deep learning for regression probelm
deep_gcns_torch
Pytorch Repo for DeepGCNs (ICCV'2019 Oral, TPAMI'2021), DeeperGCN (arXiv'2020) and GNN1000(ICML'2021): https://www.deepgcns.org
tensorflow_models_learning
tensorflow GoogleNet inception V1 V2 V3 V4
keras-squeezenet
SqueezeNet implementation with Keras Framework
SqueezeNet
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters
Ultra-Light-Fast-Generic-Face-Detector-1MB
💎1MB lightweight face detection model (1MB轻量级人脸检测模型)
deep_learning_object_detection
A paper list of object detection using deep learning.
py-faster-rcnn-cuda10
py-faster-rcnn which supports cuda 10.0
awesome-image-classification
A curated list of deep learning image classification papers and codes
DeepNetworkVisualization
This is a MATLAB project to extract the weights of a popular deep network architecture, AlexNet (pre-trained on ImageNet), and analyze the features produced by the first convolutional layer.