dan246 / VisionFlow
VisionFlow is a backend application for image recognition and notification systems, built with Flask, PostgreSQL, Redis, and Docker. It supports multi-camera setups, real-time image processing, and provides APIs for user authentication, camera management, and notifications via LINE and email.
☆70Updated this week
Related projects ⓘ
Alternatives and complementary repositories for VisionFlow
- [ICML 2024] JSQ: Compressing Large Language Models by Joint Sparsification and Quantization☆148Updated 3 weeks ago
- [ECCV 2022] Patch Similarity Aware Data-Free Quantization for Vision Transformers☆120Updated last year
- [ICCV 2023] RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers☆113Updated 10 months ago
- [ICCV 2023] I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference☆156Updated 2 months ago
- Deep learning framework realized by Numpy purely, supports for both Dynamic Graph and Static Graph with GPU acceleration☆261Updated 3 years ago
- Filter Grafting for Deep Neural Networks(CVPR 2020)☆140Updated 2 years ago
- mm-retrieval-evaluation☆10Updated 2 years ago
- Source code for MMEvalPro, a more trustworthy and efficient benchmark for evaluating LMMs☆22Updated last month
- QAT(quantize aware training) for classification with MQBench☆35Updated 3 years ago
- ☆37Updated last month
- PyTorch code for Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers☆34Updated 2 months ago
- ☆12Updated 2 years ago
- Simple but Useful Layers based on Tensorflow☆14Updated 4 years ago
- An Tensorflow.keras implementation of Same, Same But Different - Recovering Neural Network Quantization Error Through Weight Factorizatio…