Model card for mobilenetv4 hybrid medium.e200 r256 in12k A MobileNet V4 image classification model. Trained on ImageNet 12k by Ross Wightman. Model Details Model Type: Image classification / feature backbone Model Stats: Params (M): 24.9 GMACs: 1.3 Activations (M): 9.0 Image size: train = 256 x 256, test = 320 x 320 Dataset: ImageNet 12k Papers: MobileNetV4 Universal Models for the Mobile Ecosystem: https://arxiv.org/abs/2404.10518 PyTorch Image Models: https://github.com/huggingface/pytorch image models Model Usage Image Classification Feature Map Extraction Image Embeddings Model Comparison By Top 1 model top1 top5 param count img size mobilenetv4 conv aa large.e230 r448 in12k ft in1k 84.99 97.294 32.59 544 mobilenetv4 conv aa large.e230 r384 in12k ft in1k 84.772 97.344 32.59 480 mobilenetv4 conv aa large.e230 r448 in12k ft in1k 84.64 97.114 32.59 448 mobilenetv4 hybrid large.ix e600 r384 in1k 84.356 96.892 37.76 448 mobilenetv4 conv aa large.e230 r384 in12k ft in1k 84.314 97.102 32.59 384 mobilenetv4 hybrid large.e600 r384 in1k 84.266 96.936 37.76 448 mobilenetv4 hybrid large.ix e600 r384 in1k 83.990 96.702 37.76 384 mobilenetv4 conv aa large.e600 r384 in1k 83.824 96.734 32.59 4…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy