DeepLab v3+ model in PyTorch. Support different backbones.
翻译 - PyTorch中的DeepLab v3 +模型。支持不同的骨干网。
Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.
翻译 - pytorch的预训练ConvNet:NASNet,ResNeXt,ResNet,InceptionV4,InceptionResnetV2,Xception,DPN等。
TensorFlow implementation of the Xception Model by François Chollet
A PyTorch implementation of Xception: Deep Learning with Depthwise Separable Convolutions
Xception implemented with caffe
A cleaned version of XceptionNet in Keras.
Easy-to-use scripts for training and inferencing with Xception on your own dataset
#计算机科学#Practice on cifar100(ResNet, DenseNet, VGG, GoogleNet, InceptionV3, InceptionV4, Inception-ResNetv2, Xception, Resnet In Resnet, ResNext,ShuffleNet, ShuffleNetv2, MobileNet, MobileNetv2, SqueezeNet, N...
翻译 - 在cifar100上进行实践(ResNet,DenseNet,VGG,GoogleNet,InceptionV3,InceptionV4,Inception-ResNetv2,Xception,Resnet In Resnet,ResNext,ShuffleNet,ShuffleNetv2,MobileNet,MobileNetv2,SqueezeNet,NasNet,残留注意力网络,SENet)
使用Flask+Keras部署的基于Xception神经网络的细胞图像AI医疗辅助识别系统(含简单前端demo)
A MXNet implementation of Xception
Xception
A PyTorch implementation of Xception
IVA-Xception model which can achieve high performance in identifying multiple birds from overlapping bird sounds recordings based on IVA and Xception
Xception V1 model in Tensorflow with pretrained weights on ImageNet
위조 영상 식별을 위한 Xception 모델의 일반화 성능 분석
Pytorch implementation of "Real-time Convolutional Neural Networks for Emotion and Gender Classification" (mini-Xception)
Here is a pytorch implementation of deeplabv3+ supporting ResNet(79.155%) and Xception(79.945%). Multi-scale & flip test and COCO dataset interface has been finished.
StateFarm dataset used to predict the class of the distracted driver using VGG-16, RESNET50, XCEPTION and MOBILE NET models
基于keras集成多种图像分类模型: VGG16、VGG19、InceptionV3、Xception、MobileNet、AlexNet、LeNet、ZF_Net、ResNet18、ResNet34、ResNet50、ResNet_101、ResNet_152、DenseNet
遥感图像的语义分割,分别使用Deeplab V3+(Xception 和mobilenet V2 backbone)和unet模型,keras+python