Model card for mobilenetv4 conv small 050.e3000 r224 in1k A MobileNet V4 image classification model. Trained on ImageNet 1k by Ross Wightman. Trained with timm scripts using hyper parameters inspired by the MobileNet V4 paper with timm enhancements. NOTE: So far, these are the only known MNV4 weights. Official weights for Tensorflow models are unreleased. Model Details Model Type: Image classification / feature backbone Model Stats: Params (M): 2.2 GMACs: 0.1 Activations (M): 1.2 Image size: train = 224 x 224, test = 256 x 256 Dataset: ImageNet 1k Original: https://github.com/tensorflow/models/tree/master/official/vision 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…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy