Downloads · 30 days
0
latolukasz/sam2.1-hq-hiera-large-onnx
sam2.1-hq-hiera-large-onnx is a machine learning model from latolukasz. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Server-side export of SysCV's HQ-SAM 2 (sam2.1hqhieralarge checkpoint, 224.7M params): SAM 2.1 Hiera Large with an extra learnable high-quality output token and global-local feature fusion, trained on HQSeg-44K for fi…
Downloads · 30 days
0
Access
Public
Updated Aug 14, 2026
Repo size
17.2 MB
Likes
0
Public
Click a slice to open those files.
.onnx17.2 MB · 100%
From the Hugging Face model README
Server-side export of SysCV's HQ-SAM 2 (sam2.1_hq_hiera_large checkpoint, 224.7M params): SAM 2.1 Hiera Large with an extra learnable high-quality output token and global-local feature fusion, trained on HQSeg-44K for fine structures (thin edges, insect legs/wings).
| File | Size | Notes |
|---|---|---|
decoder_hq.onnx | 17 MB | HQ prompt decoder (points/box → masks). Output masks are the three SAM multimask candidates with the HQ residual mask added (masks_hq + masks_sam, MaskDecoderHQ.forward multimask path). |
No encoder here on purpose: HQ-SAM 2's image encoder is the frozen SAM 2.1 Hiera Large encoder — its ONNX outputs are bit-identical (verified max abs diff 0.0) to latolukasz/sam2.1-hiera-large-onnx encoder.onnx. Use that encoder with this decoder.
sam2.1_hq_hiera_large.pt (SysCV, 2024-11-17, Apache 2.0)sam-hq2, config sam2.1_hq_hiera_l.yamlexport_sam2.py decoder wrapper, replicating MaskDecoderHQ.forward's multimask path (5 candidate masks [single, m1, m2, m3, hq]; output = masks[4:5] + masks[1:4], iou = iou_pred[1:]). torch 2.13, opset 18.Decoder: image_embed [1,256,64,64], high_res_feats_0 [1,32,256,256], high_res_feats_1 [1,64,128,128], point_coords [n,p,2], point_labels [n,p] float32, mask_input [n,1,256,256], has_mask_input [n] → masks [n,3,256,256] logits (clamped ±32), iou_predictions [n,3].
Same interface as the base-plus and large decoders — drop-in swap.