qaihm-bot commited on
Commit
1c63a3f
·
verified ·
1 Parent(s): 0b2a556

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +29 -29
README.md CHANGED
@@ -36,34 +36,34 @@ 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
- | SqueezeNet-1_1Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.203 ms | 0 - 27 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.tflite](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.tflite) |
40
- | SqueezeNet-1_1Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 0.46 ms | 0 - 10 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.so](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.so) |
41
- | SqueezeNet-1_1Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 36.264 ms | 10 - 13 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.onnx](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.onnx) |
42
- | SqueezeNet-1_1Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.156 ms | 0 - 10 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.tflite](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.tflite) |
43
- | SqueezeNet-1_1Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.342 ms | 0 - 12 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.so](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.so) |
44
- | SqueezeNet-1_1Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 28.6 ms | 10 - 995 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.onnx](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.onnx) |
45
- | SqueezeNet-1_1Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.154 ms | 0 - 9 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.tflite](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.tflite) |
46
- | SqueezeNet-1_1Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.363 ms | 0 - 9 MB | INT8 | NPU | Use Export Script |
47
- | SqueezeNet-1_1Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 33.391 ms | 12 - 936 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.onnx](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.onnx) |
48
- | SqueezeNet-1_1Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 0.5 ms | 0 - 16 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.tflite](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.tflite) |
49
- | SqueezeNet-1_1Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 0.998 ms | 0 - 7 MB | INT8 | NPU | Use Export Script |
50
- | SqueezeNet-1_1Quantized | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 4.064 ms | 0 - 4 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.tflite](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.tflite) |
51
- | SqueezeNet-1_1Quantized | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.198 ms | 0 - 68 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.tflite](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.tflite) |
52
- | SqueezeNet-1_1Quantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.432 ms | 0 - 1 MB | INT8 | NPU | Use Export Script |
53
- | SqueezeNet-1_1Quantized | SA7255P ADP | SA7255P | TFLITE | 1.376 ms | 0 - 12 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.tflite](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.tflite) |
54
- | SqueezeNet-1_1Quantized | SA7255P ADP | SA7255P | QNN | 2.073 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
55
- | SqueezeNet-1_1Quantized | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.208 ms | 0 - 4 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.tflite](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.tflite) |
56
- | SqueezeNet-1_1Quantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.429 ms | 0 - 1 MB | INT8 | NPU | Use Export Script |
57
- | SqueezeNet-1_1Quantized | SA8295P ADP | SA8295P | TFLITE | 0.505 ms | 0 - 8 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.tflite](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.tflite) |
58
- | SqueezeNet-1_1Quantized | SA8295P ADP | SA8295P | QNN | 1.017 ms | 0 - 6 MB | INT8 | NPU | Use Export Script |
59
- | SqueezeNet-1_1Quantized | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.2 ms | 0 - 9 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.tflite](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.tflite) |
60
- | SqueezeNet-1_1Quantized | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.429 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
61
- | SqueezeNet-1_1Quantized | SA8775P ADP | SA8775P | TFLITE | 0.469 ms | 0 - 8 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.tflite](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.tflite) |
62
- | SqueezeNet-1_1Quantized | SA8775P ADP | SA8775P | QNN | 0.937 ms | 0 - 6 MB | INT8 | NPU | Use Export Script |
63
- | SqueezeNet-1_1Quantized | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 0.239 ms | 0 - 13 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.tflite](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.tflite) |
64
- | SqueezeNet-1_1Quantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 0.513 ms | 0 - 15 MB | INT8 | NPU | Use Export Script |
65
- | SqueezeNet-1_1Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 0.546 ms | 0 - 0 MB | INT8 | NPU | Use Export Script |
66
- | SqueezeNet-1_1Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 44.174 ms | 19 - 19 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.onnx](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.onnx) |
67
 
68
 
69
 
@@ -128,7 +128,7 @@ SqueezeNet-1_1Quantized
128
  Device : Samsung Galaxy S23 (13)
129
  Runtime : TFLITE
130
  Estimated inference time (ms) : 0.2
131
- Estimated peak memory usage (MB): [0, 27]
132
  Total # Ops : 43
133
  Compute Unit(s) : NPU (43 ops)
134
  ```
 
36
 
37
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
+ | SqueezeNet-1_1Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.205 ms | 0 - 10 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.tflite](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.tflite) |
40
+ | SqueezeNet-1_1Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 0.471 ms | 0 - 10 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.so](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.so) |
41
+ | SqueezeNet-1_1Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 0.522 ms | 0 - 8 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.onnx](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.onnx) |
42
+ | SqueezeNet-1_1Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.153 ms | 0 - 23 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.tflite](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.tflite) |
43
+ | SqueezeNet-1_1Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.345 ms | 0 - 25 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.so](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.so) |
44
+ | SqueezeNet-1_1Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.342 ms | 0 - 24 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.onnx](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.onnx) |
45
+ | SqueezeNet-1_1Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.126 ms | 0 - 17 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.tflite](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.tflite) |
46
+ | SqueezeNet-1_1Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.348 ms | 0 - 16 MB | INT8 | NPU | Use Export Script |
47
+ | SqueezeNet-1_1Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.402 ms | 0 - 18 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.onnx](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.onnx) |
48
+ | SqueezeNet-1_1Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 0.508 ms | 0 - 15 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.tflite](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.tflite) |
49
+ | SqueezeNet-1_1Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 0.993 ms | 0 - 12 MB | INT8 | NPU | Use Export Script |
50
+ | SqueezeNet-1_1Quantized | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 4.423 ms | 0 - 3 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.tflite](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.tflite) |
51
+ | SqueezeNet-1_1Quantized | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.207 ms | 0 - 10 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.tflite](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.tflite) |
52
+ | SqueezeNet-1_1Quantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.433 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
53
+ | SqueezeNet-1_1Quantized | SA7255P ADP | SA7255P | TFLITE | 1.377 ms | 0 - 9 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.tflite](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.tflite) |
54
+ | SqueezeNet-1_1Quantized | SA7255P ADP | SA7255P | QNN | 2.139 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
55
+ | SqueezeNet-1_1Quantized | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.202 ms | 0 - 11 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.tflite](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.tflite) |
56
+ | SqueezeNet-1_1Quantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.43 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
57
+ | SqueezeNet-1_1Quantized | SA8295P ADP | SA8295P | TFLITE | 0.508 ms | 0 - 16 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.tflite](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.tflite) |
58
+ | SqueezeNet-1_1Quantized | SA8295P ADP | SA8295P | QNN | 1.427 ms | 0 - 14 MB | INT8 | NPU | Use Export Script |
59
+ | SqueezeNet-1_1Quantized | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.206 ms | 0 - 10 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.tflite](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.tflite) |
60
+ | SqueezeNet-1_1Quantized | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.432 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
61
+ | SqueezeNet-1_1Quantized | SA8775P ADP | SA8775P | TFLITE | 0.47 ms | 0 - 10 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.tflite](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.tflite) |
62
+ | SqueezeNet-1_1Quantized | SA8775P ADP | SA8775P | QNN | 0.949 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
63
+ | SqueezeNet-1_1Quantized | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 0.26 ms | 0 - 17 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.tflite](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.tflite) |
64
+ | SqueezeNet-1_1Quantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 0.518 ms | 0 - 22 MB | INT8 | NPU | Use Export Script |
65
+ | SqueezeNet-1_1Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 0.553 ms | 1 - 1 MB | INT8 | NPU | Use Export Script |
66
+ | SqueezeNet-1_1Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.516 ms | 3 - 3 MB | INT8 | NPU | [SqueezeNet-1_1Quantized.onnx](https://huggingface.co/qualcomm/SqueezeNet-1_1Quantized/blob/main/SqueezeNet-1_1Quantized.onnx) |
67
 
68
 
69
 
 
128
  Device : Samsung Galaxy S23 (13)
129
  Runtime : TFLITE
130
  Estimated inference time (ms) : 0.2
131
+ Estimated peak memory usage (MB): [0, 10]
132
  Total # Ops : 43
133
  Compute Unit(s) : NPU (43 ops)
134
  ```