Hugging Face's logo

AXERA-TECH
/
EdgeTAM

Image Segmentation
ONNX
ONNX
Model card Files
xet
Community
wli1995 commited on
Commit
3838620
·
verified ·
1 Parent(s): 4336ed2

Delete EdgeTAM

Browse files
Files changed (2) hide show
  1. EdgeTAM/.gitattributes +0 -35
  2. EdgeTAM/README.md +0 -102
EdgeTAM/.gitattributes DELETED
@@ -1,35 +0,0 @@
1
- *.7z filter=lfs diff=lfs merge=lfs -text
2
- *.arrow filter=lfs diff=lfs merge=lfs -text
3
- *.bin filter=lfs diff=lfs merge=lfs -text
4
- *.bz2 filter=lfs diff=lfs merge=lfs -text
5
- *.ckpt filter=lfs diff=lfs merge=lfs -text
6
- *.ftz filter=lfs diff=lfs merge=lfs -text
7
- *.gz filter=lfs diff=lfs merge=lfs -text
8
- *.h5 filter=lfs diff=lfs merge=lfs -text
9
- *.joblib filter=lfs diff=lfs merge=lfs -text
10
- *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
- *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
- *.model filter=lfs diff=lfs merge=lfs -text
13
- *.msgpack filter=lfs diff=lfs merge=lfs -text
14
- *.npy filter=lfs diff=lfs merge=lfs -text
15
- *.npz filter=lfs diff=lfs merge=lfs -text
16
- *.onnx filter=lfs diff=lfs merge=lfs -text
17
- *.ot filter=lfs diff=lfs merge=lfs -text
18
- *.parquet filter=lfs diff=lfs merge=lfs -text
19
- *.pb filter=lfs diff=lfs merge=lfs -text
20
- *.pickle filter=lfs diff=lfs merge=lfs -text
21
- *.pkl filter=lfs diff=lfs merge=lfs -text
22
- *.pt filter=lfs diff=lfs merge=lfs -text
23
- *.pth filter=lfs diff=lfs merge=lfs -text
24
- *.rar filter=lfs diff=lfs merge=lfs -text
25
- *.safetensors filter=lfs diff=lfs merge=lfs -text
26
- saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
- *.tar.* filter=lfs diff=lfs merge=lfs -text
28
- *.tar filter=lfs diff=lfs merge=lfs -text
29
- *.tflite filter=lfs diff=lfs merge=lfs -text
30
- *.tgz filter=lfs diff=lfs merge=lfs -text
31
- *.wasm filter=lfs diff=lfs merge=lfs -text
32
- *.xz filter=lfs diff=lfs merge=lfs -text
33
- *.zip filter=lfs diff=lfs merge=lfs -text
34
- *.zst filter=lfs diff=lfs merge=lfs -text
35
- *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
EdgeTAM/README.md DELETED
@@ -1,102 +0,0 @@
1
- # EdgeTAM
2
- 基于EdgeSAM的图像分割Pipeline，支持多种输入提示（框、点、掩码），支持650N系列平台的模型推理。
3
-
4
- 支持芯片:
5
- - AX650N
6
-
7
-
8
- 支持硬件
9
-
10
- - [M4N-Dock(爱芯派Pro)](https://wiki.sipeed.com/hardware/zh/maixIV/m4ndock/m4ndock.html)
11
- - [M.2 Accelerator card](https://axcl-docs.readthedocs.io/zh-cn/latest/doc_guide_hardware.html)
12
-
13
- 原始模型请参考
14
- - [EdgeTAM Github](https://github.com/facebookresearch/EdgeTAM)
15
- - [EdgeTAM Huggingface](https://huggingface.co/facebook/EdgeTAM)
16
-
17
- ## 性能对比
18
-
19
- - 输入图片大小 512x512
20
-
21
- | Models | Latency (ms) | CMM Usage (MB) |
22
- | --------------------- | ---------------------- | -------------- |
23
- | edgetam_image_encoder | 22.348 | 29.124 |
24
- | edgetam_prompt_encoder | 0.055 | 0.023 |
25
- | edgetam_prompt_mask_encoder | 0.457 | 0.037 |
26
- | edgetam_mask_decoder | 4.729 | 16.730 |
27
-
28
- ## 模型转换
29
- - 模型转换工具链[Pulsar2](https://huggingface.co/AXERA-TECH/Pulsar2)
30
- - 转换文档[TODO]
31
-
32
- ## 环境准备
33
- - NPU Python API: [pyaxengine](https://github.com/AXERA-TECH/pyaxengine)
34
-
35
- 安装需要的python库
36
- ```pip install -r requirements.txt```
37
-
38
- ## 运行
39
-
40
- ```bash
41
- (myenv) root@ax650:~/EdgeTAM# python3 image_prediction_ax.py --input_box 75,275,1725,850
42
- [INFO] Available providers: ['AxEngineExecutionProvider']
43
- Loading EdgeTAM Onnx models...
44
- [INFO] Using provider: AxEngineExecutionProvider
45
- [INFO] Chip type: ChipType.MC50
46
- [INFO] VNPU type: VNPUType.DISABLED
47
- [INFO] Engine version: 2.12.0s
48
- [INFO] Model type: 2 (triple core)
49
- [INFO] Compiler version: 5.0-patch1-dirty a512c95e-dirty
50
- [INFO] Using provider: AxEngineExecutionProvider
51
- [INFO] Model type: 2 (triple core)
52
- [INFO] Compiler version: 5.0-patch1-dirty a512c95e-dirty
53
- [INFO] Using provider: AxEngineExecutionProvider
54
- [INFO] Model type: 2 (triple core)
55
- [INFO] Compiler version: 5.0-patch1-dirty a512c95e-dirty
56
- [INFO] Using provider: AxEngineExecutionProvider
57
- [INFO] Model type: 2 (triple core)
58
- [INFO] Compiler version: 5.0-patch1-dirty a512c95e-dirty
59
- Get prompts:
60
- input_box: [ 75 275 1725 850]
61
- input_point_coords: None
62
- input_point_labels: None
63
- Only box input provided
64
- Get dense_embeddings_no_mask
65
- [0.9777304]
66
- ✅ Saved: ./results/mask_1.png
67
- ```
68
-
69
- 保存结果在 `./results` 目录下：
70
- ![image](./results/mask_1.png)
71
-
72
- ```
73
- (myenv) root@ax650:~/EdgeTAM# python3 image_prediction_ax.py --image_path ./examples/images/truck.jpg --input_box 425,600,700,875 --input_point_coords 575,750 --input_point_labels 0
74
- [INFO] Available providers: ['AxEngineExecutionProvider']
75
- Loading EdgeTAM Onnx models...
76
- [INFO] Using provider: AxEngineExecutionProvider
77
- [INFO] Chip type: ChipType.MC50
78
- [INFO] VNPU type: VNPUType.DISABLED
79
- [INFO] Engine version: 2.12.0s
80
- [INFO] Model type: 2 (triple core)
81
- [INFO] Compiler version: 5.0-patch1-dirty a512c95e-dirty
82
- [INFO] Using provider: AxEngineExecutionProvider
83
- [INFO] Model type: 2 (triple core)
84
- [INFO] Compiler version: 5.0-patch1-dirty a512c95e-dirty
85
- [INFO] Using provider: AxEngineExecutionProvider
86
- [INFO] Model type: 2 (triple core)
87
- [INFO] Compiler version: 5.0-patch1-dirty a512c95e-dirty
88
- [INFO] Using provider: AxEngineExecutionProvider
89
- [INFO] Model type: 2 (triple core)
90
- [INFO] Compiler version: 5.0-patch1-dirty a512c95e-dirty
91
- ['575,750']
92
- 575,750
93
- Get prompts:
94
- input_box: [425 600 700 875]
95
- input_point_coords: [[575 750]]
96
- input_point_labels: [0]
97
- Get dense_embeddings_no_mask
98
- [0.90291053]
99
- ✅ Saved: ./results/mask_1.png
100
-
101
- ```
102
- ![image](./results/mask_5.png)