{ "architecture": "convnextv2_tiny", "num_classes": 1000, "num_features": 768, "pretrained_cfg": { "tag": "fcmae_ft_in22k_in1k", "custom_load": false, "input_size": [ 3, 224, 224 ], "test_input_size": [ 3, 288, 288 ], "fixed_input_size": false, "interpolation": "bicubic", "crop_pct": 0.875, "test_crop_pct": 1.0, "crop_mode": "center", "mean": [ 0.485, 0.456, 0.406 ], "std": [ 0.229, 0.224, 0.225 ], "num_classes": 1000, "pool_size": [ 7, 7 ], "first_conv": "stem.0", "classifier": "head.fc", "license": "cc-by-nc-4.0", "origin_url": "https://github.com/facebookresearch/ConvNeXt-V2", "paper_name": "ConvNeXt-V2: Co-designing and Scaling ConvNets with Masked Autoencoders", "paper_ids": "arXiv:2301.00808" } }