Skip to content

docs: update docs and benchmarks for FastSAM model #1151

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
msluszniak merged 2 commits into from
May 18, 2026
+13 −3
Merged

docs: update docs and benchmarks for FastSAM model #1151

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
68529ff
docs: add API references for selectByPoint, selectByBox, and selectBy…
barhanc May 14, 2026
59f0f29
docs: update inference time and memory usage for FastSAM models
barhanc May 18, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions docs/docs/02-benchmarks/inference-time.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -243,8 +243,8 @@ Nano Seg uses a fixed resolution of 312×312.
| YOLO26L_SEG (XNNPACK) | 680 | 608 | 582 |
| YOLO26X_SEG (XNNPACK) | 1410 | 1338 | 1191 |
| RF_DETR_NANO_SEG (XNNPACK) | 549 | 330 | 428 |
| FASTSAM_S (XNNPACK) | - | 30 | 286 |
| FASTSAM_X (XNNPACK) | - | 2520 | 1993 |
Comment thread
msluszniak marked this conversation as resolved.
| FASTSAM_S (XNNPACK) | 184 | 30 | 286 |
| FASTSAM_X (XNNPACK) | 1886 | 2520 | 1993 |
| FASTSAM_S (Core ML) | - | 51 | - |
| FASTSAM_X (Core ML) | - | 72 | - |

Expand Down
6 changes: 5 additions & 1 deletion docs/docs/02-benchmarks/memory-usage.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -130,7 +130,7 @@ with higher resolutions.
## Instance Segmentation

:::note
Data presented in the following sections is based on inference with forward_640 method.
Data presented in the following sections is based on inference with 640x640 input.
:::

| Model / Device | iPhone 17 Pro [MB] | OnePlus 12 [MB] |
Expand All @@ -141,6 +141,10 @@ Data presented in the following sections is based on inference with forward_640
| YOLO26L_SEG (XNNPACK) | 1024 | 680 |
| YOLO26X_SEG (XNNPACK) | 1450 | 1410 |
| RF_DETR_NANO_SEG (XNNPACK) | 603 | 620 |
| FASTSAM_S (XNNPACK FP32) | 535 | 567 |
| FASTSAM_X (XNNPACK FP32) | 760 | 792 |
| FASTSAM_S (Core ML FP16) | 523 | - |
| FASTSAM_X (Core ML FP16) | 684 | - |

## Text to Image

Expand Down
6 changes: 6 additions & 0 deletions docs/docs/03-hooks/02-computer-vision/useInstanceSegmentation.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -179,6 +179,12 @@ try {
}
```

For detailed API Reference for `selectByPoint`, `selectByBox`, and `selectByText` see their respective documentation pages:

- [`selectByPoint` API Reference](../../06-api-reference/functions/selectByPoint.md)
- [`selectByBox` API Reference](../../06-api-reference/functions/selectByBox.md)
- [`selectByText` API Reference](../../06-api-reference/functions/selectByText.md)

:::tip
Use FastSAM-S for faster performance on simple images with non-overlapping
instances and FastSAM-X for better accuracy on complex scenes with many
Expand Down