Hugging Face's logo

qualcomm
/
Beit

Image Classification
PyTorch
backbone
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
1c898b6
·
verified ·
1 Parent(s): c2ef554

v0.30.5

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.30.5 for changelog.

Files changed (1) hide show
  1. README.md +33 -29
README.md CHANGED
@@ -35,31 +35,35 @@ More details on model performance across various devices, can be found
35
 
36
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
- | Beit | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 56.293 ms | 0 - 284 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
39
- | Beit | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 52.919 ms | 0 - 9 MB | NPU | Use Export Script |
40
- | Beit | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 19.607 ms | 0 - 297 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
41
- | Beit | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 28.195 ms | 1 - 300 MB | NPU | Use Export Script |
42
- | Beit | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 19.202 ms | 0 - 18 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
43
- | Beit | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 17.84 ms | 1 - 3 MB | NPU | Use Export Script |
44
- | Beit | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 56.293 ms | 0 - 284 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
45
- | Beit | float | SA7255P ADP | Qualcomm® SA7255P | QNN | 52.919 ms | 0 - 9 MB | NPU | Use Export Script |
46
- | Beit | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 19.204 ms | 0 - 26 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
47
- | Beit | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 18.235 ms | 2 - 4 MB | NPU | Use Export Script |
48
- | Beit | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 22.02 ms | 0 - 284 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
49
- | Beit | float | SA8295P ADP | Qualcomm® SA8295P | QNN | 24.239 ms | 1 - 18 MB | NPU | Use Export Script |
50
- | Beit | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 19.485 ms | 0 - 19 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
51
- | Beit | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 18.508 ms | 1 - 2 MB | NPU | Use Export Script |
52
- | Beit | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 19.267 ms | 0 - 20 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
53
- | Beit | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 18.321 ms | 0 - 35 MB | NPU | Use Export Script |
54
- | Beit | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 17.517 ms | 0 - 396 MB | NPU | [Beit.onnx](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx) |
55
- | Beit | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 13.696 ms | 0 - 300 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
56
- | Beit | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 13.245 ms | 1 - 324 MB | NPU | Use Export Script |
57
- | Beit | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 12.004 ms | 1 - 335 MB | NPU | [Beit.onnx](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx) |
58
- | Beit | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 13.494 ms | 0 - 286 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
59
- | Beit | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 14.735 ms | 1 - 298 MB | NPU | Use Export Script |
60
- | Beit | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 14.909 ms | 1 - 302 MB | NPU | [Beit.onnx](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx) |
61
- | Beit | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 18.292 ms | 1 - 1 MB | NPU | Use Export Script |
62
- | Beit | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 20.051 ms | 186 - 186 MB | NPU | [Beit.onnx](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx) |
 
 
 
 
63
 
64
 
65
 
@@ -123,8 +127,8 @@ Profiling Results
123
  Beit
124
  Device : cs_8275 (ANDROID 14)
125
  Runtime : TFLITE
126
- Estimated inference time (ms) : 56.3
127
- Estimated peak memory usage (MB): [0, 284]
128
  Total # Ops : 569
129
  Compute Unit(s) : npu (569 ops) gpu (0 ops) cpu (0 ops)
130
  ```
@@ -213,13 +217,13 @@ AI Hub. [Sign up for access](https://myaccount.qualcomm.com/signup).
213
  You can also run the demo on-device.
214
 
215
  ```bash
216
- python -m qai_hub_models.models.beit.demo --on-device
217
  ```
218
 
219
  **NOTE**: If you want running in a Jupyter Notebook or Google Colab like
220
  environment, please add the following to your cell (instead of the above).
221
  ```
222
- %run -m qai_hub_models.models.beit.demo -- --on-device
223
  ```
224
 
225
 
 
35
 
36
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
+ | Beit | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 43.941 ms | 0 - 315 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
39
+ | Beit | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 261.829 ms | 1 - 10 MB | NPU | Use Export Script |
40
+ | Beit | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 18.2 ms | 0 - 324 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
41
+ | Beit | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 26.7 ms | 1 - 309 MB | NPU | Use Export Script |
42
+ | Beit | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 12.548 ms | 0 - 15 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
43
+ | Beit | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 14.335 ms | 1 - 3 MB | NPU | Use Export Script |
44
+ | Beit | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 15.588 ms | 0 - 315 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
45
+ | Beit | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 17.043 ms | 1 - 10 MB | NPU | Use Export Script |
46
+ | Beit | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 43.941 ms | 0 - 315 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
47
+ | Beit | float | SA7255P ADP | Qualcomm® SA7255P | QNN | 261.829 ms | 1 - 10 MB | NPU | Use Export Script |
48
+ | Beit | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 12.597 ms | 0 - 14 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
49
+ | Beit | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 14.518 ms | 1 - 3 MB | NPU | Use Export Script |
50
+ | Beit | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 20.447 ms | 0 - 307 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
51
+ | Beit | float | SA8295P ADP | Qualcomm® SA8295P | QNN | 21.809 ms | 1 - 18 MB | NPU | Use Export Script |
52
+ | Beit | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 12.188 ms | 0 - 18 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
53
+ | Beit | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 14.352 ms | 1 - 3 MB | NPU | Use Export Script |
54
+ | Beit | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 15.588 ms | 0 - 315 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
55
+ | Beit | float | SA8775P ADP | Qualcomm® SA8775P | QNN | 17.043 ms | 1 - 10 MB | NPU | Use Export Script |
56
+ | Beit | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 12.56 ms | 3 - 17 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
57
+ | Beit | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 14.467 ms | 0 - 38 MB | NPU | Use Export Script |
58
+ | Beit | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 14.91 ms | 0 - 429 MB | NPU | [Beit.onnx](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx) |
59
+ | Beit | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 8.581 ms | 0 - 339 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
60
+ | Beit | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 9.855 ms | 1 - 342 MB | NPU | Use Export Script |
61
+ | Beit | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 10.223 ms | 1 - 356 MB | NPU | [Beit.onnx](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx) |
62
+ | Beit | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 8.009 ms | 0 - 322 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
63
+ | Beit | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 8.323 ms | 1 - 321 MB | NPU | Use Export Script |
64
+ | Beit | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 8.308 ms | 1 - 326 MB | NPU | [Beit.onnx](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx) |
65
+ | Beit | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 14.895 ms | 1 - 1 MB | NPU | Use Export Script |
66
+ | Beit | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 17.826 ms | 186 - 186 MB | NPU | [Beit.onnx](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx) |
67
 
68
 
69
 
 
127
  Beit
128
  Device : cs_8275 (ANDROID 14)
129
  Runtime : TFLITE
130
+ Estimated inference time (ms) : 43.9
131
+ Estimated peak memory usage (MB): [0, 315]
132
  Total # Ops : 569
133
  Compute Unit(s) : npu (569 ops) gpu (0 ops) cpu (0 ops)
134
  ```
 
217
  You can also run the demo on-device.
218
 
219
  ```bash
220
+ python -m qai_hub_models.models.beit.demo --eval-mode on-device
221
  ```
222
 
223
  **NOTE**: If you want running in a Jupyter Notebook or Google Colab like
224
  environment, please add the following to your cell (instead of the above).
225
  ```
226
+ %run -m qai_hub_models.models.beit.demo -- --eval-mode on-device
227
  ```
228
 
229