RT-DETRv2 (ResNet-vd, S / M / M* / L / X)

• Original code: https://github.com/lyuwenyu/RT-DETR at df2a96c8c3a0
• Code licence: Apache-2.0 (permissive); files: LICENSE
• Weights licence: Apache-2.0 (assumed from code)
• Licence evidence: https://github.com/lyuwenyu/RT-DETR/blob/df2a96c8c3a098567a1149bf0248da6efe6d495d/LICENSE
• Training data: COCO 2017 (train, instance annotations), ImageNet-1k (ILSVRC 2012 classification) (COCO 2017 train (72 to 84 epochs); the ResNet-vd backbones start from ImageNet-1k (PaddleClas) pretraining)
• Options: score_threshold = 0.05 (0.0 to 1.0), max_detections = 100 (>= 1), cuda_graphs = True (speed only)
• Kernel libraries: cudnn_hacc
• Variants: rtdetrv2-s-coco, rtdetrv2-m-coco, rtdetrv2-ms-coco, rtdetrv2-l-coco, rtdetrv2-x-coco
• Outputs: boxes, scores, labels; label_set: coco-80
• Input size: any H x W >= 32, padded to a multiple of 32
• Tested up to (portable, fp16, RTX 5060 Ti 16 GB): rtdetrv2-s-coco 3000x4000 (0.5 GiB peak allocated, 0.6 reserved); rtdetrv2-m-coco 3000x4000 (0.5 GiB peak allocated, 0.7 reserved); rtdetrv2-ms-coco 3000x4000 (0.5 GiB peak allocated, 0.7 reserved); rtdetrv2-l-coco 3000x4000 (0.6 GiB peak allocated, 0.7 reserved); rtdetrv2-x-coco 3000x4000 (0.6 GiB peak allocated, 0.8 reserved)
• rtdetrv2-s-coco 800x1344, first call: portable + torch.compile 37 s (cold Inductor cache), TensorRT fp16 42 s (ONNX + engine).
• rtdetrv2-s-coco original (fp32) 800x1344: incl. CPU resize + host copy (official pipeline)
• rtdetrv2-s-coco original 800x1344: torch.autocast(fp16) around the forward; incl. CPU resize + host copy (official pipeline)
• rtdetrv2-m-coco original (fp32) 800x1344: incl. CPU resize + host copy (official pipeline)
• rtdetrv2-m-coco original 800x1344: torch.autocast(fp16) around the forward; incl. CPU resize + host copy (official pipeline)
• rtdetrv2-ms-coco original (fp32) 800x1344: incl. CPU resize + host copy (official pipeline)
• rtdetrv2-ms-coco original 800x1344: torch.autocast(fp16) around the forward; incl. CPU resize + host copy (official pipeline)
• rtdetrv2-l-coco original (fp32) 800x1344: incl. CPU resize + host copy (official pipeline)
• rtdetrv2-l-coco original 800x1344: torch.autocast(fp16) around the forward; incl. CPU resize + host copy (official pipeline)
• rtdetrv2-x-coco original (fp32) 800x1344: incl. CPU resize + host copy (official pipeline)
• rtdetrv2-x-coco original 800x1344: torch.autocast(fp16) around the forward; incl. CPU resize + host copy (official pipeline)
• rtdetrv2-s-coco load / first call: original 1.32 s / 0.417 s, portable 0.31 s / 0.097 s, kernels 0.46† s / 0.534 s
• rtdetrv2-m-coco load / first call: original 0.45 s / 0.023 s, portable 0.33 s / 0.011 s, kernels 0.16† s / 0.012 s
• rtdetrv2-ms-coco load / first call: original 0.52 s / 0.057 s, portable 0.45 s / 0.03 s, kernels 0.17† s / 0.092 s
• rtdetrv2-l-coco load / first call: original 0.66 s / 0.043 s, portable 0.5 s / 0.015 s, kernels 0.25† s / 0.016 s
• rtdetrv2-x-coco load / first call: original 1.13 s / 0.076 s, portable 1.09 s / 0.048 s, kernels 0.29† s / 0.021 s
• † measured in the speed sweep after the portable load (or an earlier size) in the same process: file cache and kernels are warm, so the time is lower than a fresh start.
• 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

pycocotools COCOeval of the top 100 detections per image. 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| <= 0.2 and p99 <= 1.0 (absolute error of the output boxes).