Jim Bohnslav's repositories
opencv_transforms
OpenCV implementation of Torchvision's image augmentations
pose_annotator
Free, open-source GUI for annotating keypoints for pose estimation
Acquisition2P_class
For managing 2P imaging datasets from preprocessing to activity trace extraction
B-SOID
Behavioral segmentation of open field in DeepLabCut, or B-SOID ("B-side"), is a pipeline that pairs unsupervised pattern recognition with supervised classification to achieve fast predictions of behaviors that are not predefined by users.
BigGAN-PyTorch
The author's officially unofficial PyTorch BigGAN implementation.
cortexModel
Recurrent cortical circuit model based on adaptive-exponential integrate and fire neurons. Includes 3 interneuron subtypes (PV, SOM, and VIP). Implemented in MATLAB (2016b)
DeepLabCut
Markerless pose estimation of user-defined features with deep learning for all animals including humans
DeepLabCut-core
Headless DeepLabCut (no GUI support)
kornia
Open Source Differentiable Computer Vision Library for PyTorch
lightning
Build and train PyTorch models and connect them to the ML lifecycle using Lightning App templates, without handling DIY infrastructure, cost management, scaling, and other headaches.
neural_networks_intro
Harvard PiN Nerd Club's introduction to neural networks.
neural_renderer
A PyTorch port of the Neural 3D Mesh Renderer
pytorch-image-models
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more
pytorch-ssim
pytorch structural similarity (SSIM) loss
tinyimagenet_benchmarking
Timing script for one epoch of TinyImageNet. Can be used to evaluate performance of deep learning workstations or cloud machines.
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs