Hugging Face's logo

qualcomm
/
Beit

Image Classification
PyTorch
backbone
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
3568dd9
·
verified ·
1 Parent(s): 6a66956

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +30 -30
README.md CHANGED
@@ -35,45 +35,44 @@ More details on model performance across various devices, can be found
35
 
36
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
- | Beit | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 16.934 ms | 0 - 50 MB | FP16 | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
39
- | Beit | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 25.244 ms | 0 - 48 MB | FP16 | NPU | [Beit.so](https://huggingface.co/qualcomm/Beit/blob/main/Beit.so) |
40
- | Beit | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 18.093 ms | 0 - 383 MB | FP16 | NPU | [Beit.onnx](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx) |
41
- | Beit | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 11.698 ms | 0 - 59 MB | FP16 | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
42
- | Beit | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 17.516 ms | 1 - 61 MB | FP16 | NPU | [Beit.so](https://huggingface.co/qualcomm/Beit/blob/main/Beit.so) |
43
- | Beit | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 13.918 ms | 1 - 59 MB | FP16 | NPU | [Beit.onnx](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx) |
44
- | Beit | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 9.485 ms | 0 - 65 MB | FP16 | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
45
- | Beit | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 17.858 ms | 1 - 65 MB | FP16 | NPU | Use Export Script |
46
- | Beit | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 13.313 ms | 0 - 52 MB | FP16 | NPU | [Beit.onnx](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx) |
47
- | Beit | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 16.921 ms | 0 - 46 MB | FP16 | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
48
- | Beit | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 17.447 ms | 1 - 4 MB | FP16 | NPU | Use Export Script |
49
- | Beit | SA7255P ADP | SA7255P | TFLITE | 260.85 ms | 0 - 61 MB | FP16 | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
50
- | Beit | SA7255P ADP | SA7255P | QNN | 268.701 ms | 1 - 10 MB | FP16 | NPU | Use Export Script |
51
- | Beit | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 16.974 ms | 0 - 48 MB | FP16 | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
52
- | Beit | SA8255 (Proxy) | SA8255P Proxy | QNN | 17.494 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
53
- | Beit | SA8295P ADP | SA8295P | TFLITE | 24.519 ms | 0 - 58 MB | FP16 | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
54
- | Beit | SA8295P ADP | SA8295P | QNN | 30.245 ms | 1 - 15 MB | FP16 | NPU | Use Export Script |
55
- | Beit | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 16.688 ms | 0 - 45 MB | FP16 | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
56
- | Beit | SA8650 (Proxy) | SA8650P Proxy | QNN | 17.472 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
57
- | Beit | SA8775P ADP | SA8775P | TFLITE | 24.491 ms | 0 - 60 MB | FP16 | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
58
- | Beit | SA8775P ADP | SA8775P | QNN | 25.456 ms | 1 - 10 MB | FP16 | NPU | Use Export Script |
59
- | Beit | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 21.814 ms | 0 - 58 MB | FP16 | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
60
- | Beit | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 31.586 ms | 1 - 57 MB | FP16 | NPU | Use Export Script |
61
  | Beit | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 18.5 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
62
- | Beit | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 21.661 ms | 187 - 187 MB | FP16 | NPU | [Beit.onnx](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx) |
63
 
64
 
65
 
66
 
67
  ## Installation
68
 
69
- This model can be installed as a Python package via pip.
70
 
 
71
  ```bash
72
  pip install "qai-hub-models[beit]"
73
  ```
74
 
75
 
76
-
77
  ## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
78
 
79
  Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
@@ -124,8 +123,8 @@ Profiling Results
124
  Beit
125
  Device : Samsung Galaxy S23 (13)
126
  Runtime : TFLITE
127
- Estimated inference time (ms) : 16.9
128
- Estimated peak memory usage (MB): [0, 50]
129
  Total # Ops : 557
130
  Compute Unit(s) : NPU (557 ops)
131
  ```
@@ -152,7 +151,7 @@ from qai_hub_models.models.beit import Model
152
  torch_model = Model.from_pretrained()
153
 
154
  # Device
155
- device = hub.Device("Samsung Galaxy S23")
156
 
157
  # Trace model
158
  input_shape = torch_model.get_input_spec()
@@ -244,7 +243,8 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
244
 
245
 
246
  ## License
247
- * The license for the original implementation of Beit can be found [here](https://github.com/pytorch/vision/blob/main/LICENSE).
 
248
  * The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)
249
 
250
 
 
35
 
36
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
+ | Beit | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 16.993 ms | 0 - 47 MB | FP16 | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
39
+ | Beit | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 25.154 ms | 0 - 47 MB | FP16 | NPU | [Beit.so](https://huggingface.co/qualcomm/Beit/blob/main/Beit.so) |
40
+ | Beit | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 18.065 ms | 0 - 383 MB | FP16 | NPU | [Beit.onnx](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx) |
41
+ | Beit | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 11.704 ms | 0 - 56 MB | FP16 | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
42
+ | Beit | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 17.476 ms | 1 - 60 MB | FP16 | NPU | [Beit.so](https://huggingface.co/qualcomm/Beit/blob/main/Beit.so) |
43
+ | Beit | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 13.822 ms | 1 - 60 MB | FP16 | NPU | [Beit.onnx](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx) |
44
+ | Beit | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 11.494 ms | 0 - 64 MB | FP16 | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
45
+ | Beit | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 17.732 ms | 1 - 66 MB | FP16 | NPU | Use Export Script |
46
+ | Beit | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 13.325 ms | 1 - 54 MB | FP16 | NPU | [Beit.onnx](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx) |
47
+ | Beit | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 16.951 ms | 0 - 46 MB | FP16 | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
48
+ | Beit | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 17.474 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
49
+ | Beit | SA7255P ADP | SA7255P | TFLITE | 260.795 ms | 0 - 61 MB | FP16 | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
50
+ | Beit | SA7255P ADP | SA7255P | QNN | 268.685 ms | 1 - 10 MB | FP16 | NPU | Use Export Script |
51
+ | Beit | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 16.615 ms | 0 - 43 MB | FP16 | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
52
+ | Beit | SA8255 (Proxy) | SA8255P Proxy | QNN | 17.502 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
53
+ | Beit | SA8295P ADP | SA8295P | TFLITE | 24.573 ms | 0 - 57 MB | FP16 | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
54
+ | Beit | SA8295P ADP | SA8295P | QNN | 30.18 ms | 1 - 14 MB | FP16 | NPU | Use Export Script |
55
+ | Beit | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 16.956 ms | 0 - 50 MB | FP16 | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
56
+ | Beit | SA8650 (Proxy) | SA8650P Proxy | QNN | 17.478 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
57
+ | Beit | SA8775P ADP | SA8775P | TFLITE | 24.481 ms | 0 - 60 MB | FP16 | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
58
+ | Beit | SA8775P ADP | SA8775P | QNN | 25.454 ms | 1 - 10 MB | FP16 | NPU | Use Export Script |
59
+ | Beit | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 21.853 ms | 0 - 57 MB | FP16 | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
60
+ | Beit | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 31.888 ms | 1 - 56 MB | FP16 | NPU | Use Export Script |
61
  | Beit | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 18.5 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
62
+ | Beit | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 21.681 ms | 187 - 187 MB | FP16 | NPU | [Beit.onnx](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx) |
63
 
64
 
65
 
66
 
67
  ## Installation
68
 
 
69
 
70
+ Install the package via pip:
71
  ```bash
72
  pip install "qai-hub-models[beit]"
73
  ```
74
 
75
 
 
76
  ## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
77
 
78
  Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
 
123
  Beit
124
  Device : Samsung Galaxy S23 (13)
125
  Runtime : TFLITE
126
+ Estimated inference time (ms) : 17.0
127
+ Estimated peak memory usage (MB): [0, 47]
128
  Total # Ops : 557
129
  Compute Unit(s) : NPU (557 ops)
130
  ```
 
151
  torch_model = Model.from_pretrained()
152
 
153
  # Device
154
+ device = hub.Device("Samsung Galaxy S24")
155
 
156
  # Trace model
157
  input_shape = torch_model.get_input_spec()
 
243
 
244
 
245
  ## License
246
+ * The license for the original implementation of Beit can be found
247
+ [here](https://github.com/pytorch/vision/blob/main/LICENSE).
248
  * The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)
249
 
250