SAM3 — ONNX FP16 models
Meta SAM 3 (Segment Anything Model 3), exported to ONNX (FP16) for a C++ ONNX Runtime pipeline: a vision encoder, a text encoder and a decoder with a dynamic prompt-count batch (a single file accepts any number of text prompts at runtime, no re-export needed).
Files
| File | Description |
|---|---|
fp16/vision-encoder.onnx |
Image encoder, input [1,3,644,644] FP16 |
fp16/text-encoder.onnx |
Text encoder, input [nc,32] int64 (dynamic batch) |
fp16/decoder.onnx |
Prompt decoder with a dynamic prompt-count batch: inputs text_features [32,nc,256], text_mask [nc,32], text_ids [nc]; outputs pred_boxes [nc,200,4], pred_logits [nc,200,1], pred_masks [nc,200,184,184], presence_logits [nc,1] |
fp16/bpe_simple_vocab_16e6.txt, fp16/clip_vocab.json |
CLIP BPE tokenizer vocabulary |
License
The model is derived from Meta's SAM 3 and is provided under the SAM License
(see LICENSE in this repository). Use, reproduction and redistribution are
subject to that agreement; the license text must be kept with any redistribution.