ZhihuaGao/TinyLLaVA_Factory
A Framework of Small-scale Large Multimodal Models
Repositories
ZhihuaGao/MiniLLaVA
A minimal vision-language model prototype that aligns image and text embeddings via a projection layer (inspired by LLaVA)
ZhihuaGao/Vim-python
ZhihuaGao/R-MTCNN
ZhihuaGao/images
link
ZhihuaGao/detectron2
Detectron2 is FAIR's next-generation platform for object detection and segmentation.
ZhihuaGao/mobilenets-caffe-prototxt
Google's MobileNets definition with Alpha = 0.25, 0.5, 0.75, 1.0, in Caffe prototxt.
ZhihuaGao/antialiased-cnns
Antialiasing cnns to improve stability and accuracy. In ICML 2019.
ZhihuaGao/mmdetection
Open MMLab Detection Toolbox and Benchmark
ZhihuaGao/cnn-models
ImageNet pre-trained models with batch normalization for the Caffe framework
ZhihuaGao/PaperNote
some notes for reading papers