Hugging Face's logo

qualcomm
/
Sequencer2D

Image Classification
PyTorch
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
7876202
·
verified ·
1 Parent(s): 7abe8ab

v0.42.0

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.42.0 for changelog.

Files changed (5) hide show
  1. README.md +16 -36
  2. Sequencer2D_float.dlc +0 -3
  3. Sequencer2D_float.onnx.zip +2 -2
  4. Sequencer2D_w8a8.onnx.zip +0 -3
  5. Sequencer2D_w8a8.tflite +0 -3
README.md CHANGED
@@ -36,38 +36,18 @@ More details on model performance across various devices, can be found
36
 
37
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
- | Sequencer2D | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 41.259 ms | 0 - 425 MB | NPU | [Sequencer2D.tflite](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D.tflite) |
40
- | Sequencer2D | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 52.131 ms | 1 - 636 MB | NPU | [Sequencer2D.dlc](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D.dlc) |
41
- | Sequencer2D | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 21.942 ms | 0 - 312 MB | NPU | [Sequencer2D.tflite](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D.tflite) |
42
- | Sequencer2D | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 27.213 ms | 0 - 494 MB | NPU | [Sequencer2D.dlc](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D.dlc) |
43
- | Sequencer2D | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 19.243 ms | 0 - 55 MB | NPU | [Sequencer2D.tflite](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D.tflite) |
44
- | Sequencer2D | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 20.871 ms | 0 - 112 MB | NPU | [Sequencer2D.dlc](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D.dlc) |
45
- | Sequencer2D | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 46.765 ms | 0 - 162 MB | NPU | [Sequencer2D.onnx.zip](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D.onnx.zip) |
46
- | Sequencer2D | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 21.197 ms | 0 - 421 MB | NPU | [Sequencer2D.tflite](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D.tflite) |
47
- | Sequencer2D | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 24.902 ms | 1 - 599 MB | NPU | [Sequencer2D.dlc](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D.dlc) |
48
- | Sequencer2D | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 13.278 ms | 0 - 422 MB | NPU | [Sequencer2D.tflite](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D.tflite) |
49
- | Sequencer2D | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 14.504 ms | 1 - 1765 MB | NPU | [Sequencer2D.dlc](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D.dlc) |
50
- | Sequencer2D | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 33.664 ms | 0 - 873 MB | NPU | [Sequencer2D.onnx.zip](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D.onnx.zip) |
51
- | Sequencer2D | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 11.468 ms | 0 - 418 MB | NPU | [Sequencer2D.tflite](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D.tflite) |
52
- | Sequencer2D | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 12.322 ms | 1 - 670 MB | NPU | [Sequencer2D.dlc](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D.dlc) |
53
- | Sequencer2D | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 23.544 ms | 1 - 507 MB | NPU | [Sequencer2D.onnx.zip](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D.onnx.zip) |
54
- | Sequencer2D | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 10.897 ms | 0 - 433 MB | NPU | [Sequencer2D.tflite](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D.tflite) |
55
- | Sequencer2D | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 9.407 ms | 1 - 865 MB | NPU | [Sequencer2D.dlc](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D.dlc) |
56
- | Sequencer2D | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 18.151 ms | 1 - 935 MB | NPU | [Sequencer2D.onnx.zip](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D.onnx.zip) |
57
- | Sequencer2D | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 21.388 ms | 444 - 444 MB | NPU | [Sequencer2D.dlc](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D.dlc) |
58
- | Sequencer2D | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 48.318 ms | 65 - 65 MB | NPU | [Sequencer2D.onnx.zip](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D.onnx.zip) |
59
- | Sequencer2D | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 38.929 ms | 0 - 403 MB | NPU | [Sequencer2D.tflite](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D_w8a8.tflite) |
60
- | Sequencer2D | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 20.3 ms | 0 - 304 MB | NPU | [Sequencer2D.tflite](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D_w8a8.tflite) |
61
- | Sequencer2D | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 20.078 ms | 0 - 58 MB | NPU | [Sequencer2D.tflite](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D_w8a8.tflite) |
62
- | Sequencer2D | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 22.249 ms | 0 - 397 MB | NPU | [Sequencer2D.tflite](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D_w8a8.tflite) |
63
- | Sequencer2D | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | ONNX | 262.075 ms | 30 - 52 MB | CPU | [Sequencer2D.onnx.zip](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D_w8a8.onnx.zip) |
64
- | Sequencer2D | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | ONNX | 271.373 ms | 27 - 37 MB | CPU | [Sequencer2D.onnx.zip](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D_w8a8.onnx.zip) |
65
- | Sequencer2D | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 14.566 ms | 0 - 408 MB | NPU | [Sequencer2D.tflite](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D_w8a8.tflite) |
66
- | Sequencer2D | w8a8 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 12.907 ms | 0 - 393 MB | NPU | [Sequencer2D.tflite](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D_w8a8.tflite) |
67
- | Sequencer2D | w8a8 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 104.365 ms | 104 - 200 MB | NPU | [Sequencer2D.onnx.zip](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D_w8a8.onnx.zip) |
68
- | Sequencer2D | w8a8 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 13.349 ms | 0 - 393 MB | NPU | [Sequencer2D.tflite](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D_w8a8.tflite) |
69
- | Sequencer2D | w8a8 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 101.588 ms | 103 - 197 MB | NPU | [Sequencer2D.onnx.zip](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D_w8a8.onnx.zip) |
70
- | Sequencer2D | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 123.908 ms | 132 - 132 MB | NPU | [Sequencer2D.onnx.zip](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D_w8a8.onnx.zip) |
71
 
72
 
73
 
@@ -82,9 +62,9 @@ pip install "qai-hub-models[sequencer2d]"
82
  ```
83
 
84
 
85
- ## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
86
 
87
- Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
88
  Qualcomm® ID. Once signed in navigate to `Account -> Settings -> API Token`.
89
 
90
  With this API token, you can configure your client to run models on the cloud
@@ -92,7 +72,7 @@ hosted devices.
92
  ```bash
93
  qai-hub configure --api_token API_TOKEN
94
  ```
95
- Navigate to [docs](https://app.aihub.qualcomm.com/docs/) for more information.
96
 
97
 
98
 
@@ -203,7 +183,7 @@ With the output of the model, you can compute like PSNR, relative errors or
203
  spot check the output with expected output.
204
 
205
  **Note**: This on-device profiling and inference requires access to Qualcomm®
206
- AI Hub. [Sign up for access](https://myaccount.qualcomm.com/signup).
207
 
208
 
209
 
 
36
 
37
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
+ | Sequencer2D | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 41.295 ms | 0 - 443 MB | NPU | [Sequencer2D.tflite](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D.tflite) |
40
+ | Sequencer2D | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 21.757 ms | 0 - 323 MB | NPU | [Sequencer2D.tflite](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D.tflite) |
41
+ | Sequencer2D | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 18.539 ms | 0 - 53 MB | NPU | [Sequencer2D.tflite](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D.tflite) |
42
+ | Sequencer2D | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 46.724 ms | 0 - 218 MB | NPU | [Sequencer2D.onnx.zip](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D.onnx.zip) |
43
+ | Sequencer2D | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 90.428 ms | 0 - 445 MB | NPU | [Sequencer2D.tflite](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D.tflite) |
44
+ | Sequencer2D | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 13.475 ms | 0 - 481 MB | NPU | [Sequencer2D.tflite](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D.tflite) |
45
+ | Sequencer2D | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 33.67 ms | 0 - 880 MB | NPU | [Sequencer2D.onnx.zip](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D.onnx.zip) |
46
+ | Sequencer2D | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 11.475 ms | 0 - 417 MB | NPU | [Sequencer2D.tflite](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D.tflite) |
47
+ | Sequencer2D | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 23.341 ms | 1 - 506 MB | NPU | [Sequencer2D.onnx.zip](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D.onnx.zip) |
48
+ | Sequencer2D | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 10.654 ms | 0 - 414 MB | NPU | [Sequencer2D.tflite](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D.tflite) |
49
+ | Sequencer2D | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 18.51 ms | 1 - 547 MB | NPU | [Sequencer2D.onnx.zip](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D.onnx.zip) |
50
+ | Sequencer2D | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 48.737 ms | 65 - 65 MB | NPU | [Sequencer2D.onnx.zip](https://huggingface.co/qualcomm/Sequencer2D/blob/main/Sequencer2D.onnx.zip) |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51
 
52
 
53
 
 
62
  ```
63
 
64
 
65
+ ## Configure Qualcomm® AI Hub Workbench to run this model on a cloud-hosted device
66
 
67
+ Sign-in to [Qualcomm® AI Hub Workbench](https://workbench.aihub.qualcomm.com/) with your
68
  Qualcomm® ID. Once signed in navigate to `Account -> Settings -> API Token`.
69
 
70
  With this API token, you can configure your client to run models on the cloud
 
72
  ```bash
73
  qai-hub configure --api_token API_TOKEN
74
  ```
75
+ Navigate to [docs](https://workbench.aihub.qualcomm.com/docs/) for more information.
76
 
77
 
78
 
 
183
  spot check the output with expected output.
184
 
185
  **Note**: This on-device profiling and inference requires access to Qualcomm®
186
+ AI Hub Workbench. [Sign up for access](https://myaccount.qualcomm.com/signup).
187
 
188
 
189
 
Sequencer2D_float.dlc DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f139c846ca5c27c560248a02d506b7b8d9039a6a264b618a8dc00f12ab99c1c
3
- size 123434660
 
 
 
 
Sequencer2D_float.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce97d794de4ba0343a8dfefa90377f81050ce9c2aa88e7d8aa6f7ab6f2e6bb40
3
- size 102956358
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea346154cc450fcd48aa52ac53313ffd8890d927826ce94a6e6cb01e41e51e08
3
+ size 102959846
Sequencer2D_w8a8.onnx.zip DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:54ef803c3173a10cee61407693209be9c211617b9199289d35b93d3a240f5096
3
- size 72142568
 
 
 
 
Sequencer2D_w8a8.tflite DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:65ff70fcad5e84ba901d99de7e9800bdfb211049907836e23ce15258136517dd
3
- size 65551016