ConvNeXt V2

• Original code: https://github.com/huggingface/pytorch-image-models at 0df212b369a5
• Code licence: Apache-2.0 (permissive); files:
• Weights licence: CC-BY-NC-4.0
• Licence evidence: https://huggingface.co/timm/convnextv2_base.fcmae_ft_in22k_in1k/blob/9e250ed8f88b436472d2b24af26f82a8aa8c719d/README.md
• Training data: ImageNet-21k / ImageNet-22k (full ImageNet, fall 2011 release), ImageNet-1k (ILSVRC 2012 classification)
• Kernel libraries: cudnn_hacc, fvm_conv, fvm_extra, fvm_mb, fvm_r3
• Variants: convnextv2_base.fcmae_ft_in22k_in1k (default of convnextv2_base)
• Outputs: logits; label_set: imagenet-1k
• Input size: fixed 224x224: the input is resized (short side 256) and centre-cropped to it
• Tested up to (portable, fp16, RTX 5060 Ti 16 GB): convnextv2_base.fcmae_ft_in22k_in1k 224x224 (0.3 GiB peak allocated, 0.4 reserved)
• convnextv2_base.fcmae_ft_in22k_in1k 224x224, first call: portable + torch.compile 14 s (cold Inductor cache), TensorRT fp16 35 s (ONNX + engine).
• convnextv2_base.fcmae_ft_in22k_in1k original 224x224: torch.autocast(fp16) around the forward
• convnextv2_base.fcmae_ft_in22k_in1k load / first call: original 2.7 s / 0.631 s, portable 1.23 s / 0.029 s, kernels 2.12 s / 0.158 s
• Protocol, median of 5 after 3 warm-up, uint8 CUDA input (synthetic for bench_inputs sizes), card defaults; gc before each load; peak = max over the first call and the timed calls

Measured

fastforks: the model's own resize / crop on the GPU; original: the library's pretrained loader and its PIL eval transform. Original = the original code named under Details, same checkpoint and protocol.

Measured on NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks 939adfe8, 2026-11-06.

Parity

CPU, float32: max |diff| <= 0.002 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.02 and p99 <= 0.08 (absolute error of the output logits).