ivanpanshin

opti_models

PyTorch optimizations and benchmarking

flask_gunicorn_nginx_docker

Template for deploying ML models using Flask + Gunicorn + Nginx inside Docker

hist_cancer

Histopathologic Cancer Detection model based on Kaggle Challenge https://www.kaggle.com/c/histopathologic-cancer-detection (top 1%)

malawi_1st_place

segment-vasculature-5th-place

3D segmentation of blood vessels based on Hierarchical Phase-Contrast Tomography (HiP-CT)

SupCon-Framework

Implementation of Supervised Contrastive Learning with AMP, EMA, SWA, and many other tricks

VinBigData_MMDetection

Part of the final solution for 2nd place in kaggle.com/c/vinbigdata-chest-xray-abnormalities-detection

2nd-place-solution-for-VinBigData-Chest-X-ray-Abnormalities-Detection

Localization of thoracic abnormalities model based on VinBigData (top 1%)

ivanpanshin/SupCon-Framework

Implementation of Supervised Contrastive Learning with AMP, EMA, SWA, and many other tricks

ivanpanshin/flask_gunicorn_nginx_docker

Template for deploying ML models using Flask + Gunicorn + Nginx inside Docker

ivanpanshin/hist_cancer

Histopathologic Cancer Detection model based on Kaggle Challenge https://www.kaggle.com/c/histopathologic-cancer-detection (top 1%)

ivanpanshin/segment-vasculature-5th-place

3D segmentation of blood vessels based on Hierarchical Phase-Contrast Tomography (HiP-CT)

ivanpanshin/VinBigData_MMDetection

Part of the final solution for 2nd place in kaggle.com/c/vinbigdata-chest-xray-abnormalities-detection

ivanpanshin/malawi_1st_place

ivanpanshin/dvc_registry

ivanpanshin/field_area_segmentation

ivanpanshin/mmsegmentation

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

ivanpanshin/opti_models

PyTorch optimizations and benchmarking

ivanpanshin/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

ivanpanshin/retinanet-examples

Fast and accurate object detection with end-to-end GPU optimization