Models

Retrieval models

2 retrieval models. Each section says what the model is, whether it may be used commercially and how fast it is; licences and checks are under Details.

Input: one RGB image. Output: a global descriptor [D] (unit L2 norm) for image retrieval / visual place recognition; fastforks.retrieval.top_k and pairs find the nearest images (cosine similarity) on the GPU.

Measured on RTX 5060 Ti, torch 2.14.1+cu130; fastforks bench MODEL --size HxW measures yours. The summary uses one input, 480x640: kernels time with its speed-up over the faster original run, and kernels peak reserved memory with its ratio to the smaller original one. Where measured (one variant per family), a variant's table also lists portable under torch.compile and the fp16 TensorRT engine of portable (export; memory: the engine's device memory + torch's peak). – = not measured; no kernels = the family has no kernels backend (reason under its table). Reserved memory is the allocator's cache: kernels (CUDA graphs, cuDNN workspaces) can reserve a few percent to some tens of percent more than portable at the same allocated peak.

Other devices: Apple M1 Pro 16 GB, NVIDIA L4, NVIDIA L40S, NVIDIA A10, NVIDIA A100-SXM4-40GB, NVIDIA RTX PRO 6000; across devices.

modelcommercialkernels time (ms),
speed-up vs original
kernels peak memory (MiB, reserved),
ratio to original
boq-dinov2yes2.84, 2.6x256, 1.0x
megalocyes4.26, 2.3x508, 0.37x

All models

Modes, licences, training data and outputs per model

Commercial status per variant: yes if the code and the weights licence both allow commercial use (the training data is listed but does not change it; weights without a licence of their own are assumed to carry the code licence); no if either forbids it; unclear for custom licence terms (treat as no).

modelmodescode licenceweights licencetraining datacommercialoutputs
boq-dinov2portable, kernelsMITMITlvd-142m, gsv-citiesyesdescriptor
megalocportable, kernelsMITMITlvd-142m, gsv-cities, msls, megascenes, scannet, sf-xlyesdescriptor

Training datasets