Model card for eva large patch14 196.in22k ft in22k in1k An EVA image classification model. Pretrained on ImageNet 22k with masked image modeling (using EVA CLIP as a MIM teacher) and fine tuned on ImageNet 22k then on ImageNet 1k by paper authors. NOTE: timm checkpoints are float32 for consistency with other models. Original checkpoints are float16 or bfloat16 in some cases, see originals if that's preferred. Model Details Model Type: Image classification / feature backbone Model Stats: Params (M): 304.1 GMACs: 61.6 Activations (M): 63.5 Image size: 196 x 196 Papers: EVA: Exploring the Limits of Masked Visual Representation Learning at Scale: https://arxiv.org/abs/2211.07636 Pretrain Dataset: ImageNet 22k ImageNet 22k Dataset: ImageNet 1k Original: https://github.com/baaivision/EVA https://huggingface.co/BAAI/EVA Model Usage Image Classification Image Embeddings Model Comparison Explore the dataset and runtime metrics of this model in timm model results. model top1 top5 param count img size eva02 large patch14 448.mim m38m ft in22k in1k 90.054 99.042 305.08 448 eva02 large patch14 448.mim in22k ft in22k in1k 89.946 99.01 305.08 448 eva giant patch14 560.m30m ft in22k in1k 89.792 9…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy