Views
No views yet
| Property | Value |
|---|---|
| Architecture | Spotiflow (U-Net backbone + stereographic flow head) |
| Input | float32 [B, 1, H, W] — single-channel grayscale image |
| Output 0 | float32 [B, 1, H, W] — heatmap (pre-sigmoid logits) |
| Output 1 | float32 [B, 3, H, W] — stereographic flow (z, y, x) |
| ONNX opset | 16 |
| Pretrained variant | general |
1import onnxruntime as ort
2import numpy as np
3
4session = ort.InferenceSession("model.onnx")
5image = np.random.rand(1, 1, 512, 512).astype(np.float32)
6outputs = session.run(None, {"input": image})
7heatmaps, flow = outputs[0], outputs[-1] # flow has shape [B, 3, H, W]1use spotiflow_rs::{SpotiflowSession, PredictParams};
2
3let mut session = SpotiflowSession::new("model.onnx")?;
4let (spots, heatmaps, flows) = session.predict(&image_f32, h, w, PredictParams::default())?;(heatmaps, flow) tuple for correct ONNX tracing:python scripts/export_onnx.py --model general --output model.onnx1@article{dominguez2024spotiflow,
2 title={Spotiflow: accurate and efficient spot detection for fluorescence microscopy with deep stereographic flow regression},
3 author={Dominguez Mantes, Albert and Herrera, Antonio and Khven, Irina and Schlaeppi, Anjalie and Aho, Eftychia and Erskine, Amber and Laubscher, Eleonora and Hendriks, Gert-Jan and Thiran, Jean-Philippe and Bhatt, Deepak K and Wegner, Joerg D and Weigert, Martin},
4 journal={bioRxiv},
5 year={2024},
6 publisher={Cold Spring Harbor Laboratory}
7}