How this analysis was created: This summary and feature list were written by an AI model that read the project's README and public documentation pages. Each feature links to the documentation it came from; stars, license and language come straight from the GitHub API. The model does not read the source code, and the analysis is refreshed when the project is re-analysed. Learn more on our About page.
MeshCNN is a general-purpose deep neural network for 3D triangular meshes, which can be used for tasks such as 3D shape classification or segmentation. This framework includes convolution, pooling and unpooling layers which are applied directly on the mesh edges.
The main features of ranahanocka/meshcnn are: 3D Object Classification, 3D Shape Analysis, Convolutional Neural Networks (CNNs).
Open-source alternatives to ranahanocka/meshcnn include: itailang/samplenet — Created by Itai Lang, Asaf Manor, and Shai Avidan from Tel Aviv University. aaron-xichen/pytorch-playground — Base pretrained models and datasets in pytorch (MNIST, SVHN, CIFAR10, CIFAR100, STL10, AlexNet, VGG16, VGG19, ResNet,… ajbrock/generative-and-discriminative-voxel-modeling — Voxel-Based Variational Autoencoders, VAE GUI, and Convnets for Classification. amir32002/feedback-networks — Paper: Feedback Networks, CVPR 2017. automan000/convolution_lstm_pytorch. a2zadeh/variational-autodecoder.
Created by Itai Lang, Asaf Manor, and Shai Avidan from Tel Aviv University.
Base pretrained models and datasets in pytorch (MNIST, SVHN, CIFAR10, CIFAR100, STL10, AlexNet, VGG16, VGG19, ResNet, Inception, SqueezeNet)
Voxel-Based Variational Autoencoders, VAE GUI, and Convnets for Classification