qaihm-bot commited on
Commit
24ad40a
·
verified ·
1 Parent(s): 66b2cd3

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +20 -20
README.md CHANGED
@@ -35,25 +35,25 @@ 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
- | EfficientNet-V2-s | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 2.685 ms | 0 - 325 MB | FP16 | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
39
- | EfficientNet-V2-s | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 2.528 ms | 1 - 4 MB | FP16 | NPU | [EfficientNet-V2-s.so](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.so) |
40
- | EfficientNet-V2-s | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 2.685 ms | 0 - 154 MB | FP16 | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx) |
41
- | EfficientNet-V2-s | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 2.012 ms | 0 - 101 MB | FP16 | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
42
- | EfficientNet-V2-s | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 1.87 ms | 1 - 19 MB | FP16 | NPU | [EfficientNet-V2-s.so](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.so) |
43
- | EfficientNet-V2-s | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 1.993 ms | 0 - 73 MB | FP16 | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx) |
44
- | EfficientNet-V2-s | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 1.858 ms | 0 - 75 MB | FP16 | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
45
- | EfficientNet-V2-s | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 1.86 ms | 1 - 31 MB | FP16 | NPU | Use Export Script |
46
- | EfficientNet-V2-s | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 1.944 ms | 0 - 36 MB | FP16 | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx) |
47
- | EfficientNet-V2-s | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 60.026 ms | 0 - 71 MB | FP16 | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
48
- | EfficientNet-V2-s | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 60.016 ms | 1 - 10 MB | FP16 | NPU | Use Export Script |
49
- | EfficientNet-V2-s | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 2.673 ms | 0 - 327 MB | FP16 | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
50
- | EfficientNet-V2-s | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 2.528 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
51
- | EfficientNet-V2-s | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 4.615 ms | 0 - 71 MB | FP16 | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
52
- | EfficientNet-V2-s | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 4.318 ms | 1 - 10 MB | FP16 | NPU | Use Export Script |
53
- | EfficientNet-V2-s | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 5.179 ms | 0 - 88 MB | FP16 | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
54
- | EfficientNet-V2-s | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 5.103 ms | 0 - 42 MB | FP16 | NPU | Use Export Script |
55
- | EfficientNet-V2-s | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 2.786 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
56
- | EfficientNet-V2-s | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2.771 ms | 47 - 47 MB | FP16 | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx) |
57
 
58
 
59
 
@@ -118,7 +118,7 @@ EfficientNet-V2-s
118
  Device : Samsung Galaxy S23 (13)
119
  Runtime : TFLITE
120
  Estimated inference time (ms) : 2.7
121
- Estimated peak memory usage (MB): [0, 325]
122
  Total # Ops : 508
123
  Compute Unit(s) : NPU (508 ops)
124
  ```
 
35
 
36
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
+ | EfficientNet-V2-s | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 2.662 ms | 0 - 326 MB | FP16 | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
39
+ | EfficientNet-V2-s | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 2.524 ms | 1 - 3 MB | FP16 | NPU | [EfficientNet-V2-s.so](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.so) |
40
+ | EfficientNet-V2-s | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 2.587 ms | 0 - 99 MB | FP16 | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx) |
41
+ | EfficientNet-V2-s | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 2.0 ms | 0 - 102 MB | FP16 | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
42
+ | EfficientNet-V2-s | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 1.852 ms | 1 - 19 MB | FP16 | NPU | [EfficientNet-V2-s.so](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.so) |
43
+ | EfficientNet-V2-s | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 1.933 ms | 0 - 72 MB | FP16 | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx) |
44
+ | EfficientNet-V2-s | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 1.851 ms | 0 - 75 MB | FP16 | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
45
+ | EfficientNet-V2-s | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 1.583 ms | 1 - 30 MB | FP16 | NPU | Use Export Script |
46
+ | EfficientNet-V2-s | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 1.834 ms | 0 - 35 MB | FP16 | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx) |
47
+ | EfficientNet-V2-s | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 60.013 ms | 0 - 71 MB | FP16 | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
48
+ | EfficientNet-V2-s | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 60.021 ms | 1 - 10 MB | FP16 | NPU | Use Export Script |
49
+ | EfficientNet-V2-s | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 2.676 ms | 0 - 324 MB | FP16 | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
50
+ | EfficientNet-V2-s | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 2.538 ms | 1 - 4 MB | FP16 | NPU | Use Export Script |
51
+ | EfficientNet-V2-s | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 4.597 ms | 0 - 71 MB | FP16 | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
52
+ | EfficientNet-V2-s | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 4.307 ms | 1 - 10 MB | FP16 | NPU | Use Export Script |
53
+ | EfficientNet-V2-s | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 5.147 ms | 0 - 86 MB | FP16 | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
54
+ | EfficientNet-V2-s | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 5.23 ms | 1 - 40 MB | FP16 | NPU | Use Export Script |
55
+ | EfficientNet-V2-s | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 2.797 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
56
+ | EfficientNet-V2-s | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2.73 ms | 46 - 46 MB | FP16 | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx) |
57
 
58
 
59
 
 
118
  Device : Samsung Galaxy S23 (13)
119
  Runtime : TFLITE
120
  Estimated inference time (ms) : 2.7
121
+ Estimated peak memory usage (MB): [0, 326]
122
  Total # Ops : 508
123
  Compute Unit(s) : NPU (508 ops)
124
  ```