Download README.md from fastforks/flowformer: direct link, hf CLI and curl.
- Browser
- Download file 8.35 kB
-
https://huggingface.co/fastforks/flowformer/resolve/main/README.md
- Command line
-
hf download hf://fastforks/flowformer/README.md
-
curl -L -o README.md https://huggingface.co/fastforks/flowformer/resolve/main/README.md
library_name: fastforks
pipeline_tag: image-to-image
license: other
license_name: see-model-card
license_link: >-
https://github.com/drinkingcoder/FlowFormer-Official/blob/6ba7ea82b45394d3a7a25808399695427c9febd8/README.md#license
tags:
- flow
- optical-flow
- motion-estimation
- cuda
- pytorch
- fastforks
- fastforks-card
FlowFormer Small (fastforks)
FlowFormer Small (ECCV 2022): convolutional features, a latent cost-memory transformer and recurrent flow decoding. The authors' Small checkpoints, with plain float32 inference.
This repo is the model card only: it holds no weights. fastforks downloads the authors' weights from the links below and checks them against the SHA-256 in the model card. Code: https://github.com/kleinicke/fastforks. Kernels for the kernels backend: https://huggingface.co/fastforks/kernels. Original code: https://github.com/drinkingcoder/FlowFormer-Official at 6ba7ea82b453.
Task: flow. Tier: experimental. Outputs: flow. Backends: portable.
Input: two RGB images (consecutive frames). Output: per-pixel motion from the first to the second (dx, dy in pixels).
Variants
Weights are the authors' files (not hosted here). SHA-256 shortened to 12 hex digits; the full hashes are in card.toml.
| variant | weights (author link) | SHA-256 | weights licence | commercial use |
|---|---|---|---|---|
flowformer-small-chairs@1 |
flowformer-small-chairs.pth | 353914dcbf90 |
Apache-2.0 AND BSD-3-Clause AND WTFPL (assumed from code) | yes |
flowformer-small-sintel@1 |
flowformer-small-sintel.pth | 0ed780e00504 |
Apache-2.0 AND BSD-3-Clause AND WTFPL (assumed from code) | yes |
flowformer-small-things@1 |
flowformer-small-things.pth | 6bd2b44f3170 |
Apache-2.0 AND BSD-3-Clause AND WTFPL (assumed from code) | yes |
Licence
Original-code strings, recorded as they are (research-use package; check them before any other use). Code: Apache-2.0 AND BSD-3-Clause AND WTFPL. Licence files: LICENSE, LICENSE-RAFT, LICENSE-GMA.
Code licence: Apache-2.0 AND BSD-3-Clause AND WTFPL; the authors do not state a separate weights licence.
Training data: FlyingChairs (Freiburg), Freiburg SceneFlow (FlyingThings3D, Driving, Monkaa) (The authors' Small checkpoints follow the chairs, things and sintel training stages; per-variant training data follows configs/small_*.py.).
Licence evidence: https://github.com/drinkingcoder/FlowFormer-Official/blob/6ba7ea82b45394d3a7a25808399695427c9febd8/README.md#license
Input size
any H x W >= 64, padded to a multiple of 8
Tested up to (portable, fp16, RTX 5060 Ti 16 GB): flowformer-small-chairs 1024x1024 (11.2 GiB peak allocated, 12.3 reserved); flowformer-small-sintel 1024x1024 (11.2 GiB peak allocated, 12.3 reserved); flowformer-small-things 1024x1024 (11.2 GiB peak allocated, 12.3 reserved)
Speed and memory
Flow, synthetic
| model | input | time (ms): original fp32 | original | portable | kernels | kernels speed-up: vs original | vs portable | peak memory (MiB, allocated / reserved): original | portable | kernels |
|---|---|---|---|---|---|---|---|---|---|---|
flowformer-small-chairs |
375x1242 | 352 | 303 | 351 | β | β | β | 2382 / 2970 | 3165 / 3638 | β |
flowformer-small-sintel |
375x1242 | 352 | 303 | 351 | β | β | β | 2382 / 2990 | 3165 / 3638 | β |
flowformer-small-things |
375x1242 | 352 | 303 | 351 | β | β | β | 2382 / 3010 | 3165 / 3638 | β |
Startup and first call
| model | load (s): original | portable | kernels | first call (s): original | portable | kernels |
|---|---|---|---|---|---|---|
flowformer-small-chairs |
0.16 (375x1242) | 1.31 (375x1242) | β | 0.37 (375x1242) | 0.57 (375x1242) | β |
flowformer-small-sintel |
0.15 (375x1242) | 1.30 (375x1242) | β | 0.30 (375x1242) | 0.57 (375x1242) | β |
flowformer-small-things |
0.15 (375x1242) | 1.31 (375x1242) | β | 0.30 (375x1242) | 0.57 (375x1242) | β |
torch.compile and TensorRT
| model | input | time: portable | compile | TensorRT fp16 | kernels | preparation: compile (cold first call) | ONNX + engine build | peak MiB (alloc / reserved): portable | compile | kernels | TensorRT (engine + torch) |
|---|---|---|---|---|---|---|---|---|---|---|---|
flowformer-small-chairs |
375x1242 | 351 ms | 250 ms | 202 ms | β | 98.7 s | 118 s | 3165 / 3638 | 2438 / 3196 | β | 2087 / 2138 |
flowformer-small-sintel |
375x1242 | 351 ms | 250 ms | 202 ms | β | 98.9 s | 117 s | 3165 / 3638 | 2438 / 3196 | β | 2087 / 2138 |
flowformer-small-things |
375x1242 | 351 ms | 250 ms | 202 ms | β | 99.3 s | 118 s | 3165 / 3638 | 2438 / 3196 | β | 2087 / 2138 |
Fixed-size cells: time (ms) / peak allocated / peak reserved memory (MiB).
Hardware, protocol and caveats: benchmarks (RTX 5060 Ti 16 GB, sm_120). Original = the original code named above at the precision of portable (fp16, or (fp32) where fp16 is unsupported or not finite); original fp32 = its default fp32 run. Peak memory is the torch allocator's.
Accuracy
On public datasets
Frames _10 -> _11 at full size against the flow_occ ground truth; EPE = mean of the per-pair mean end-point error, Fl-all = share of all valid pixels with an error > 3 px and > 5 % of the GT magnitude. Original = the original code named under Details, same checkpoint and protocol.
| variant | dataset | original fp32 | original fp16 | portable | note |
|---|---|---|---|---|---|
flowformer-small-chairs |
KITTI 2015 train, EPE / Fl-all % | 10.952 / 36.72 | 11.102 / 36.80 | 10.952 / 36.72 | |
flowformer-small-things |
KITTI 2015 train, EPE / Fl-all % | 6.884 / 17.92 | 7.034 / 17.91 | 6.884 / 17.92 | |
flowformer-small-sintel |
KITTI 2015 train, EPE / Fl-all % | 4.657 / 6.35 | 4.206 / 6.30 | 4.657 / 6.35 | trained on this dataset's public images; not a zero-shot result |
Measured on NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks a6ea0725+dirty, 2026-11-11.
Parity with the original code
Every variant is checked against reference outputs of the original code at its pinned commit. CPU, float32: max |diff| <= 0.0001 vs the original. GPU, portable float32 and kernels float16 (the defaults): mean |diff| <= 0.0021 and p99 <= 0.013 (absolute error of the output flow).
Limitations
- Only the Small architecture is included.
- No custom kernels backend: the time is in cuDNN TF32 convolutions and the float32 aggregation matmul, and lowering precision changes EPE.
- Portable runs float32 (the validated dtype): 338 ms and 1410 MB at 375x1242 against 303 ms and 2382 MB for the fp16-autocast original (EPE identical to the float32 original); switching the default to fp16 needs a full accuracy re-validation.
- Full-frame cost memory grows quadratically with input area; upstream tiled evaluation is not included. Full-frame 1080p exceeded the RTX 5060 Ti 16GB memory in portable and original fp32/fp16 runs.
Usage
from fastforks import flow
model = flow.load("flowformer-small-chairs") # mode="auto": the preferred backend from recorded measurements
result = model("frame1.png", "frame2.png")
result.flow # [2, H, W] float32 tensor: dx, dy in input pixels
result.backend # what ran, e.g. Backend(mode='portable', device='cuda:0', dtype='float16')
Install with pip install fastforks (see https://github.com/kleinicke/fastforks). Other variants: flowformer-small-chairs, flowformer-small-sintel, flowformer-small-things.
Kernels backend
No kernels backend: Measured 2026-11-15: time is cuDNN TF32 convolutions plus the float32 aggregation matmul; fp16 aggregation (NaN at scale 1024, worse EPE) and SDPA (slower, EPE changed) were tried and dropped..