pankaj-kaushik commited on
Commit
47e724b
·
verified ·
1 Parent(s): fbe6d9c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -0
README.md CHANGED
@@ -9,15 +9,22 @@ tags:
9
  - fastsam
10
  pipeline_tag: image-segmentation
11
  ---
 
12
  # FastSAM ONNX Weights
 
13
  This repository contains ONNX-optimized weights for **FastSAM (Fast Segment Anything Model)**, a real-time CNN-based instance segmentation model built upon the YOLOv8-Seg architecture.
14
  By converting the PyTorch weights to standard ONNX format, these models enable real-time object proposal generation and mask decoding on both CPU and GPU edge devices without requiring the PyTorch runtime.
 
15
  ## Available Files
 
16
  * **`FastSAM-s.onnx`**: Small YOLOv8-Seg backbone variant (`"s"`), optimized for high frame rate and edge deployment.
17
  * **`FastSAM-x.onnx`**: Extra-large YOLOv8-Seg backbone variant (`"x"`), higher capacity proposal generation model.
 
18
  ---
19
  ## How to Use
 
20
  The easiest way to load and run these models is through the **[spatialhub](https://github.com/spatialhub-ai/spatialhub)** Python library:
 
21
  ```python
22
  from spatialhub import FastSAM
23
  # Initialize FastSAM segmentor
@@ -29,7 +36,9 @@ result.visualize_mask("fastsam_output.png")
29
  ```
30
 
31
  ## Original Citation
 
32
  If you use these models in academic work, please cite the original authors:
 
33
  ```bibtex
34
  @article{zhao2023fast,
35
  title={Fast Segment Anything},
 
9
  - fastsam
10
  pipeline_tag: image-segmentation
11
  ---
12
+
13
  # FastSAM ONNX Weights
14
+
15
  This repository contains ONNX-optimized weights for **FastSAM (Fast Segment Anything Model)**, a real-time CNN-based instance segmentation model built upon the YOLOv8-Seg architecture.
16
  By converting the PyTorch weights to standard ONNX format, these models enable real-time object proposal generation and mask decoding on both CPU and GPU edge devices without requiring the PyTorch runtime.
17
+
18
  ## Available Files
19
+
20
  * **`FastSAM-s.onnx`**: Small YOLOv8-Seg backbone variant (`"s"`), optimized for high frame rate and edge deployment.
21
  * **`FastSAM-x.onnx`**: Extra-large YOLOv8-Seg backbone variant (`"x"`), higher capacity proposal generation model.
22
+
23
  ---
24
  ## How to Use
25
+
26
  The easiest way to load and run these models is through the **[spatialhub](https://github.com/spatialhub-ai/spatialhub)** Python library:
27
+
28
  ```python
29
  from spatialhub import FastSAM
30
  # Initialize FastSAM segmentor
 
36
  ```
37
 
38
  ## Original Citation
39
+
40
  If you use these models in academic work, please cite the original authors:
41
+
42
  ```bibtex
43
  @article{zhao2023fast,
44
  title={Fast Segment Anything},