Model card for convnextv2 base.fcmae A ConvNeXt V2 self supervised feature representation model. Pretrained with a fully convolutional masked autoencoder framework (FCMAE). This model has no pretrained head and is only useful for fine tune or feature extraction. Model Details Model Type: Image classification / feature backbone Model Stats: Params (M): 87.7 GMACs: 15.4 Activations (M): 28.8 Image size: 224 x 224 Papers: ConvNeXt V2: Co designing and Scaling ConvNets with Masked Autoencoders: https://arxiv.org/abs/2301.00808 Original: https://github.com/facebookresearch/ConvNeXt V2 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 co…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy