Image classification: efficientnet/resnest/seresnext/.....
-
Updated
Jan 29, 2024 - Python
Image classification: efficientnet/resnest/seresnext/.....
Fully supervised binary classification of skin lesions from dermatoscopic images using an ensemble of diverse CNN architectures (EfficientNet-B6, Inception-V3, SEResNeXt-101, SENet-154, DenseNet-169) with multi-scale input.
Models supported: ResNet, ResNetV2, SE-ResNet, ResNeXt, SE-ResNeXt [layers: 18, 34, 50, 101, 152] (1D and 2D versions with DEMO for Classification and Regression).
Pytorch implementation of vision models.
Top 10% (bronze) Kaggle pipeline for cassava leaf disease classification: SE-ResNeXt50 with a binary head and bi-tempered logistic loss, mixed precision, FMix/CutMix, 5-fold CV.
Detecting Melanoma (skin cancer) using CNNs
BirdCLEF 2025 soundscape classification project using deep learning (SeresNeXt26t) with PyTorch, pseudo-labeling, and audio preprocessing for bird species identification.
To associate your repository with the seresnext topic, visit your repo's landing page and select "manage topics."