Model card for dm nfnet f0.dm in1k A NFNet (Normalization Free Network) image classification model. Trained on ImageNet 1k by paper authors. Normalization Free Networks are (pre activation) ResNet like models without any normalization layers. Instead of Batch Normalization or alternatives, they use Scaled Weight Standardization and specifically placed scalar gains in residual path and at non linearities based on signal propagation analysis. Model Details Model Type: Image classification / feature backbone Model Stats: Params (M): 71.5 GMACs: 7.2 Activations (M): 10.2 Image size: train = 192 x 192, test = 256 x 256 Papers: High Performance Large Scale Image Recognition Without Normalization: https://arxiv.org/abs/2102.06171 Characterizing signal propagation to close the performance gap in unnormalized ResNets: https://arxiv.org/abs/2101.08692 Original: https://github.com/deepmind/deepmind research/tree/master/nfnets Dataset: ImageNet 1k Model Usage Image Classification Feature Map Extraction Image Embeddings Model Comparison Explore the dataset and runtime metrics of this model in timm model results. Citation
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy