Parallel reporter assays provide rich data to decipher gene regulatory regions with deep learning. Here we introduce LegNet, a convolutional network architecture that secured the first place for ourautosome.orgteam in the DREAM 2022 challenge of predicting gene expression from gigantic parallel reporter assays. To construct LegNet, we drew inspiration from EfficientNetV2 and reformulated the sequence-to-expression regression problem as a soft-classification task. Here, with published data, we demonstrate that LegNet outperforms existing models and accurately predicts gene expressionper seas well as the effects of sequence alterations, such as single-nucleotide variants.