Model card for convnextv2 femto.fcmae ft in1k A ConvNeXt V2 image classification model. Pretrained with a fully convolutional masked autoencoder framework (FCMAE) and fine tuned on ImageNet 1k. Model Details Model Type: Image classification / feature backbone Model Stats: Params (M): 5.2 GMACs: 0.8 Activations (M): 4.6 Image size: train = 224 x 224, test = 288 x 288 Papers: ConvNeXt V2: Co designing and Scaling ConvNets with Masked Autoencoders: https://arxiv.org/abs/2301.00808 Original: https://github.com/facebookresearch/ConvNeXt V2 Dataset: ImageNet 1k Pretrain 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. All timing numbers from eager model PyTorch 1.13 on RTX 3090 w/ AMP. model top1 top5 img size param count gmacs macts samples per sec batch size convnextv2 huge.fcmae ft in22k in1k 512 88.848 98.742 512 660.29 600.81 413.07 28.58 48 convnextv2 huge.fcmae ft in22k in1k 384 88.668 98.738 384 660.29 337.96 232.35 50.56 64 convnext xxlarge.clip laion2b soup ft in1k 88.612 98.704 256 846.47 198.09 124.45 122.45 256 convnext large mlp.clip lai…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy