Views
No views yet
FastSAM-s.pt, assets release v8.4.0.ultralytics 8.4.107, imgsz=1024, opset=17, simplified with onnxslim.images: [1, 3, 1024, 1024] float32, values 0..1, letterboxed
top-left with pad value 114/255.[1, 37, 21504] — per anchor: 4 box (xywh, in 1024-space) + 1
class score (sigmoid already applied; FastSAM is class-agnostic) + 32 mask
coefficients.[1, 32, 256, 256] — 32 mask prototypes at a quarter of input
resolution. An instance mask is sigmoid(sum(coeff_i * proto_i)), cropped to
its own box.