qaihm-bot commited on
Commit
a1f0f61
·
verified ·
1 Parent(s): ee7d2fa

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +34 -48
README.md CHANGED
@@ -36,38 +36,38 @@ More details on model performance across various devices, can be found
36
 
37
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
- | Inception-v3-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.658 ms | 0 - 111 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
40
- | Inception-v3-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 0.603 ms | 0 - 3 MB | INT8 | NPU | [Inception-v3-Quantized.so](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.so) |
41
- | Inception-v3-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 26.558 ms | 5 - 129 MB | INT8 | NPU | [Inception-v3-Quantized.onnx](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.onnx) |
42
- | Inception-v3-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.492 ms | 0 - 55 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
43
- | Inception-v3-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.46 ms | 0 - 19 MB | INT8 | NPU | [Inception-v3-Quantized.so](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.so) |
44
- | Inception-v3-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 19.871 ms | 2 - 680 MB | INT8 | NPU | [Inception-v3-Quantized.onnx](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.onnx) |
45
- | Inception-v3-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.491 ms | 0 - 38 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
46
- | Inception-v3-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.436 ms | 0 - 40 MB | INT8 | NPU | Use Export Script |
47
- | Inception-v3-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 23.303 ms | 0 - 655 MB | INT8 | NPU | [Inception-v3-Quantized.onnx](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.onnx) |
48
- | Inception-v3-Quantized | SA7255P ADP | SA7255P | TFLITE | 8.488 ms | 0 - 34 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
49
- | Inception-v3-Quantized | SA7255P ADP | SA7255P | QNN | 8.464 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
50
- | Inception-v3-Quantized | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.656 ms | 0 - 7 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
51
- | Inception-v3-Quantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.598 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
52
- | Inception-v3-Quantized | SA8295P ADP | SA8295P | TFLITE | 1.123 ms | 0 - 36 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
53
- | Inception-v3-Quantized | SA8295P ADP | SA8295P | QNN | 1.147 ms | 0 - 18 MB | INT8 | NPU | Use Export Script |
54
- | Inception-v3-Quantized | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.661 ms | 0 - 111 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
55
- | Inception-v3-Quantized | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.608 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
56
- | Inception-v3-Quantized | SA8775P ADP | SA8775P | TFLITE | 0.933 ms | 0 - 35 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
57
- | Inception-v3-Quantized | SA8775P ADP | SA8775P | QNN | 0.868 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
58
- | Inception-v3-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 2.439 ms | 0 - 53 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
59
- | Inception-v3-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 2.915 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
60
- | Inception-v3-Quantized | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 8.069 ms | 0 - 2 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
61
- | Inception-v3-Quantized | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 8.488 ms | 0 - 34 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
62
- | Inception-v3-Quantized | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 8.464 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
63
- | Inception-v3-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.651 ms | 0 - 112 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
64
- | Inception-v3-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.602 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
65
- | Inception-v3-Quantized | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 0.933 ms | 0 - 35 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
66
- | Inception-v3-Quantized | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 0.868 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
67
- | Inception-v3-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 0.876 ms | 0 - 55 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
68
- | Inception-v3-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 0.798 ms | 0 - 49 MB | INT8 | NPU | Use Export Script |
69
- | Inception-v3-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 0.643 ms | 0 - 0 MB | INT8 | NPU | Use Export Script |
70
- | Inception-v3-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 26.602 ms | 41 - 41 MB | INT8 | NPU | [Inception-v3-Quantized.onnx](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.onnx) |
71
 
72
 
73
 
@@ -128,11 +128,11 @@ python -m qai_hub_models.models.inception_v3_quantized.export
128
  ```
129
  Profiling Results
130
  ------------------------------------------------------------
131
- Inception-v3-Quantized
132
  Device : Samsung Galaxy S23 (13)
133
  Runtime : TFLITE
134
  Estimated inference time (ms) : 0.7
135
- Estimated peak memory usage (MB): [0, 111]
136
  Total # Ops : 142
137
  Compute Unit(s) : NPU (142 ops)
138
  ```
@@ -216,20 +216,6 @@ AI Hub. [Sign up for access](https://myaccount.qualcomm.com/signup).
216
 
217
 
218
 
219
- ## Run demo on a cloud-hosted device
220
-
221
- You can also run the demo on-device.
222
-
223
- ```bash
224
- python -m qai_hub_models.models.inception_v3_quantized.demo --on-device
225
- ```
226
-
227
- **NOTE**: If you want running in a Jupyter Notebook or Google Colab like
228
- environment, please add the following to your cell (instead of the above).
229
- ```
230
- %run -m qai_hub_models.models.inception_v3_quantized.demo -- --on-device
231
- ```
232
-
233
 
234
  ## Deploying compiled model to Android
235
 
 
36
 
37
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
+ | Inception-v3 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.656 ms | 0 - 109 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3.tflite) |
40
+ | Inception-v3 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 0.608 ms | 0 - 2 MB | INT8 | NPU | [Inception-v3-Quantized.so](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3.so) |
41
+ | Inception-v3 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 25.602 ms | 0 - 197 MB | INT8 | NPU | [Inception-v3-Quantized.onnx](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3.onnx) |
42
+ | Inception-v3 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.49 ms | 0 - 51 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3.tflite) |
43
+ | Inception-v3 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.456 ms | 0 - 21 MB | INT8 | NPU | [Inception-v3-Quantized.so](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3.so) |
44
+ | Inception-v3 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 20.213 ms | 0 - 743 MB | INT8 | NPU | [Inception-v3-Quantized.onnx](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3.onnx) |
45
+ | Inception-v3 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.503 ms | 0 - 38 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3.tflite) |
46
+ | Inception-v3 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.441 ms | 0 - 37 MB | INT8 | NPU | Use Export Script |
47
+ | Inception-v3 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 22.823 ms | 0 - 704 MB | INT8 | NPU | [Inception-v3-Quantized.onnx](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3.onnx) |
48
+ | Inception-v3 | SA7255P ADP | SA7255P | TFLITE | 8.562 ms | 0 - 34 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3.tflite) |
49
+ | Inception-v3 | SA7255P ADP | SA7255P | QNN | 8.46 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
50
+ | Inception-v3 | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.661 ms | 0 - 111 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3.tflite) |
51
+ | Inception-v3 | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.611 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
52
+ | Inception-v3 | SA8295P ADP | SA8295P | TFLITE | 1.132 ms | 0 - 36 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3.tflite) |
53
+ | Inception-v3 | SA8295P ADP | SA8295P | QNN | 1.137 ms | 0 - 18 MB | INT8 | NPU | Use Export Script |
54
+ | Inception-v3 | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.658 ms | 0 - 111 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3.tflite) |
55
+ | Inception-v3 | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.611 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
56
+ | Inception-v3 | SA8775P ADP | SA8775P | TFLITE | 0.948 ms | 0 - 34 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3.tflite) |
57
+ | Inception-v3 | SA8775P ADP | SA8775P | QNN | 0.852 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
58
+ | Inception-v3 | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 2.451 ms | 0 - 52 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3.tflite) |
59
+ | Inception-v3 | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 2.805 ms | 0 - 15 MB | INT8 | NPU | Use Export Script |
60
+ | Inception-v3 | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 7.786 ms | 0 - 3 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3.tflite) |
61
+ | Inception-v3 | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 8.562 ms | 0 - 34 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3.tflite) |
62
+ | Inception-v3 | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 8.46 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
63
+ | Inception-v3 | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.657 ms | 0 - 110 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3.tflite) |
64
+ | Inception-v3 | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.614 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
65
+ | Inception-v3 | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 0.948 ms | 0 - 34 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3.tflite) |
66
+ | Inception-v3 | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 0.852 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
67
+ | Inception-v3 | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 0.866 ms | 0 - 57 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3.tflite) |
68
+ | Inception-v3 | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 0.799 ms | 0 - 52 MB | INT8 | NPU | Use Export Script |
69
+ | Inception-v3 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 0.634 ms | 0 - 0 MB | INT8 | NPU | Use Export Script |
70
+ | Inception-v3 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 26.74 ms | 42 - 42 MB | INT8 | NPU | [Inception-v3-Quantized.onnx](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3.onnx) |
71
 
72
 
73
 
 
128
  ```
129
  Profiling Results
130
  ------------------------------------------------------------
131
+ Inception-v3
132
  Device : Samsung Galaxy S23 (13)
133
  Runtime : TFLITE
134
  Estimated inference time (ms) : 0.7
135
+ Estimated peak memory usage (MB): [0, 109]
136
  Total # Ops : 142
137
  Compute Unit(s) : NPU (142 ops)
138
  ```
 
216
 
217
 
218
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
219
 
220
  ## Deploying compiled model to Android
221