A PyTorch implementation of "MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer"
-
Updated
Jan 16, 2022 - Python
#
mobilevit
Here are 26 public repositories matching this topic...
Language: All
Filter by language
Sort: Most stars
Sort options
Advanced Android photo editor powered by on-device AI models (LaMa, EdgeSAM, MobileViT) with GPU-accelerated adjustments, voice commands, generative fill, and professional editing tools. Built with Jetpack Compose and ONNX Runtime for fast, offline-first image processing.
android kotlin photo-editing mvvm-architecture jetpack-compose vosk mobilevit edgesam minicpm lama-inpainting
-
Updated
Dec 28, 2025 - Kotlin
Collection and Implementation of Mobile-based Vision Transformer in Pytorch
-
Updated
Jul 19, 2023 - Python
Edge Impulse FOMO Implementation from scratch
-
Updated
Feb 27, 2026 - Python
Porting vision models to Keras 3 for easily accessibility. Contains MobileViT v1, MobileViT v2, fastvit
computer-vision deep-learning tensorflow keras transformers cnn pytorch self-attention jax mobilevit mobilevitv1 mobilevitv2 fastvit keras3
-
Updated
Apr 20, 2025 - Jupyter Notebook
Transformers goes brrr... Attention and Transformers from scratch in TensorFlow. Currently contains Vision transformers, MobileViT-v1, MobileViT-v2, MobileViT-v3
mobile tensorflow transformer attention-mechanism tensorflow2 vision-transformer mobilevit mobilevitv1 mobilevitv2 mobilevitv3
-
Updated
Apr 2, 2025 - Python
A PyTorch implementation of MobileViT.
-
Updated
Oct 2, 2022 - Jupyter Notebook
Earthquake building damage detection using UAV-based image datasets.
image-processing image-classification deeplearning attention-mechanism uavs turkey-earthquake imagedetection vision-transformers mobilevit buidling-damage-estimation efficient-channel-attantion-blok
-
Updated
Jul 21, 2025 - Python
MobileViT Implementation from scratch in TensorFlow and PyTorch
-
Updated
Nov 13, 2022 - Python
in this project we used image processing Technique to classify 9 class malwares our final goal is to reach an appropriate model with high accuracy and small size and computational cost
distributed-systems machine-learning cloud deep-learning pipeline malware image-processing ml embedded-systems transformer cloud-computing resnet dl smote malware-detection mobilenetv2 squeeznet malware-classification mobilevit cloudhierarchicaldnn
-
Updated
Dec 3, 2024 - Jupyter Notebook
vit初步,CIFAR10
-
Updated
Sep 3, 2022 - Python
Implements MobileViT and ViT from scratch, compatible with graph execution mode in tensorflow. Compares multiple cnn and transformer-based models including VGG, ResNet, ViT and MobileViT on a small cultrual relic data set.
-
Updated
Nov 27, 2024 - Python
This project is developed under the Computer Security and Privacy Lab of University of Goettingen. Images inside the public and private folders in assets will be classified as either Sensitive(Private) or Non-sensitive(Public) with the help of mobilevit model deployed in an Android application
-
Updated
Mar 27, 2023 - Jupyter Notebook
Unofficial reimplementation and improvements to arXiv:2304.09715 — camera-LiDAR extrinsic calibration via MobileViT early fusion, 6-D continuous rotation, and differentiable spatial loss.
-
Updated
Jul 12, 2026 - Python
End-to-end AI workflow for cervical cytology using MobileViT and Cellpose. Features automated cell segmentation, classification on SIPaKMeD, and PDF clinical reporting via FastAPI.
bioinformatics deep-learning pytorch medical-imaging image-classification cell-segmentation digital-pathology cytology fastapi medical-ai cervical-screening cervical-cancer mobilevit sipakmed health-it-ai-research
-
Updated
Apr 10, 2026 - Python
2D facial landmarks detection with neural networks
neural-networks resnet-18 mobilenetv2 mobilenetv3 efficientnet augmentations facial-landmarks-detection mobilevit lapa wing-loss
-
Updated
Jun 8, 2023 - Jupyter Notebook
A mobile-friendly solution for COVID-19 diagnosis from CT images using Mobile ViT transformers
-
Updated
Aug 16, 2026 - Python
From-scratch PyTorch implementation of "MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer" (ICLR 2022) with FP16, INT8, and INT4 post-training quantization
pytorch quantization cifar10 model-compression post-training-quantization vision-transformer mobilevit
-
Updated
Feb 19, 2026 - Python
Lightweight Vision Transformer models for multiclass skin-lesion classification using imbalance-aware learning, Grad-CAM visualization, and efficiency analysis.
computer-vision deep-learning pytorch medical-imaging class-imbalance gradcam skin-lesion-classification ham10000 vision-transformer mobilevit tinyvit
-
Updated
Aug 5, 2026 - Jupyter Notebook
Add this topic to your repo
To associate your repository with the mobilevit topic, visit your repo's landing page and select "manage topics."