Draw.io Neural Network Model Library

A collection of 37 ready-to-use neural network architecture templates for draw.io, designed for academic papers, technical reports, and presentations. All diagrams follow IEEE Transactions color conventions with a consistent, professional style.

Open nn_model_library.xml in draw.io (File > Open Library) to load all 37 templates into the scratchpad. Drag any template onto your canvas and customize as needed.

Alternatively, individual .drawio files are available in exports/drawio/ for standalone use.

LeNet-5	ResNet Block	MobileNet Block	Inception Module

Vision Transformer (ViT)	Transformer Encoder	Swin Transformer Block

Seq2Seq + Attention	BERT Block	GPT Block

U-Net	Faster R-CNN

CNNs: LeNet-5, AlexNet, VGG Block, ResNet Block, ResNet Bottleneck, DenseNet Block, MobileNet Block, EfficientNet MBConv, Inception Module

Transformers: Transformer Encoder, Transformer Decoder, Full Transformer, ViT, Swin Transformer Block, Multi-Head Attention Detail, MLP-Mixer

NLP Models: BERT Block, GPT Block, Seq2Seq, Seq2Seq + Attention

RNNs: Stacked LSTM, Stacked GRU, Bi-LSTM

Detection & Segmentation: Faster R-CNN, FPN, YOLO Head, U-Net, FCN Decoder, ASPP Module

Generative Models: GAN, DCGAN Generator, DCGAN Discriminator, Conditional GAN, VAE, Autoencoder

Other: GAT Layer, Siamese Network

All templates use a standardized IEEE Transactions academic color palette.

This library is provided under the MIT License. Feel free to use these templates in your papers, presentations, and projects.