Hugging Face's logo

qualcomm
/
ConvNext-Base

Image Classification
PyTorch
LiteRT
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
10434ef
·
verified ·
1 Parent(s): 9352aed

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +17 -21
README.md CHANGED
@@ -34,25 +34,21 @@ More details on model performance across various devices, can be found
34
 
35
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
36
  |---|---|---|---|---|---|---|---|---|
37
- | ConvNext-Base | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 7.701 ms | 0 - 27 MB | FP16 | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
38
- | ConvNext-Base | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 8.217 ms | 1 - 3 MB | FP16 | NPU | [ConvNext-Base.so](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.so) |
39
- | ConvNext-Base | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 37.963 ms | 0 - 273 MB | FP16 | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx) |
40
- | ConvNext-Base | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 5.779 ms | 183 - 245 MB | FP16 | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
41
- | ConvNext-Base | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 5.918 ms | 1 - 16 MB | FP16 | NPU | [ConvNext-Base.so](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.so) |
42
- | ConvNext-Base | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 26.43 ms | 1 - 141 MB | FP16 | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx) |
43
- | ConvNext-Base | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 4.38 ms | 0 - 73 MB | FP16 | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
44
- | ConvNext-Base | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 5.466 ms | 1 - 75 MB | FP16 | NPU | Use Export Script |
45
- | ConvNext-Base | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 23.215 ms | 1 - 154 MB | FP16 | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx) |
46
- | ConvNext-Base | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 303.064 ms | 0 - 70 MB | FP16 | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
47
- | ConvNext-Base | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 303.545 ms | 1 - 8 MB | FP16 | NPU | Use Export Script |
48
- | ConvNext-Base | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 7.782 ms | 0 - 23 MB | FP16 | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
49
- | ConvNext-Base | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 8.151 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
50
- | ConvNext-Base | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 14.256 ms | 0 - 70 MB | FP16 | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
51
- | ConvNext-Base | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 14.796 ms | 1 - 8 MB | FP16 | NPU | Use Export Script |
52
- | ConvNext-Base | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 20.119 ms | 0 - 52 MB | FP16 | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
53
- | ConvNext-Base | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 21.055 ms | 0 - 55 MB | FP16 | NPU | Use Export Script |
54
- | ConvNext-Base | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 8.542 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
55
- | ConvNext-Base | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 41.0 ms | 176 - 176 MB | FP16 | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx) |
56
 
57
 
58
 
@@ -116,8 +112,8 @@ Profiling Results
116
  ConvNext-Base
117
  Device : Samsung Galaxy S23 (13)
118
  Runtime : TFLITE
119
- Estimated inference time (ms) : 7.7
120
- Estimated peak memory usage (MB): [0, 27]
121
  Total # Ops : 598
122
  Compute Unit(s) : NPU (598 ops)
123
  ```
 
34
 
35
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
36
  |---|---|---|---|---|---|---|---|---|
37
+ | ConvNext-Base | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 7.478 ms | 0 - 24 MB | FP16 | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
38
+ | ConvNext-Base | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 7.811 ms | 1 - 2 MB | FP16 | NPU | [ConvNext-Base.so](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.so) |
39
+ | ConvNext-Base | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 5.636 ms | 0 - 272 MB | FP16 | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
40
+ | ConvNext-Base | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 5.911 ms | 1 - 21 MB | FP16 | NPU | [ConvNext-Base.so](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.so) |
41
+ | ConvNext-Base | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 5.063 ms | 0 - 261 MB | FP16 | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
42
+ | ConvNext-Base | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 5.347 ms | 1 - 266 MB | FP16 | NPU | Use Export Script |
43
+ | ConvNext-Base | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 303.066 ms | 0 - 258 MB | FP16 | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
44
+ | ConvNext-Base | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 302.923 ms | 1 - 8 MB | FP16 | NPU | Use Export Script |
45
+ | ConvNext-Base | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 7.589 ms | 0 - 12 MB | FP16 | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
46
+ | ConvNext-Base | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 7.617 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
47
+ | ConvNext-Base | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 13.93 ms | 0 - 257 MB | FP16 | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
48
+ | ConvNext-Base | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 14.086 ms | 1 - 10 MB | FP16 | NPU | Use Export Script |
49
+ | ConvNext-Base | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 19.194 ms | 0 - 276 MB | FP16 | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
50
+ | ConvNext-Base | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 19.424 ms | 1 - 270 MB | FP16 | NPU | Use Export Script |
51
+ | ConvNext-Base | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 8.175 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
 
 
 
 
52
 
53
 
54
 
 
112
  ConvNext-Base
113
  Device : Samsung Galaxy S23 (13)
114
  Runtime : TFLITE
115
+ Estimated inference time (ms) : 7.5
116
+ Estimated peak memory usage (MB): [0, 24]
117
  Total # Ops : 598
118
  Compute Unit(s) : NPU (598 ops)
119
  ```