{"data":{"full_name":"hoanglechau/channelwise-attention-residual-networks-dl","name":"channelwise-attention-residual-networks-dl","description":"This project implements a Squeeze-and-Excitation Residual Network (SE-ResNet) to solve a fine-grained classification problem on  32 × 32  images. It addresses signal-to-noise challenges in low-resolution data.","stars":0.0,"forks":0.0,"language":"Jupyter Notebook","license":null,"archived":0.0,"subcategory":"cifar-10-image-classification","last_pushed_at":"2026-01-28T09:13:21+00:00","pypi_package":null,"npm_package":null,"downloads_monthly":0.0,"dependency_count":0.0,"commits_30d":null,"reverse_dep_count":0.0,"maintenance_score":10.0,"adoption_score":0.0,"maturity_score":1.0,"community_score":0.0,"quality_score":11.0,"quality_tier":"experimental","risk_flags":"['no_license', 'no_package', 'no_dependents']"},"meta":{"timestamp":"2026-04-05T19:35:49.103101+00:00"}}