Hugging Face's logo

qualcomm
/
EfficientNet-B4

Image Classification
PyTorch
LiteRT
ONNX
backbone
android
Model card Files Community
qaihm-bot commited on
Commit
39caab8
·
verified ·
1 Parent(s): fb338a4

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +21 -21
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-B4 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 3.608 ms | 0 - 280 MB | FP16 | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
39
- | EfficientNet-B4 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 3.341 ms | 1 - 3 MB | FP16 | NPU | [EfficientNet-B4.so](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.so) |
40
- | EfficientNet-B4 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 3.549 ms | 0 - 212 MB | FP16 | NPU | [EfficientNet-B4.onnx](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx) |
41
- | EfficientNet-B4 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 2.63 ms | 0 - 30 MB | FP16 | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
42
- | EfficientNet-B4 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 2.448 ms | 0 - 16 MB | FP16 | NPU | [EfficientNet-B4.so](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.so) |
43
- | EfficientNet-B4 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 2.614 ms | 0 - 39 MB | FP16 | NPU | [EfficientNet-B4.onnx](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx) |
44
- | EfficientNet-B4 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 2.484 ms | 0 - 30 MB | FP16 | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
45
- | EfficientNet-B4 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 2.554 ms | 1 - 29 MB | FP16 | NPU | Use Export Script |
46
- | EfficientNet-B4 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 2.471 ms | 1 - 33 MB | FP16 | NPU | [EfficientNet-B4.onnx](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx) |
47
- | EfficientNet-B4 | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 65.207 ms | 0 - 24 MB | FP16 | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
48
- | EfficientNet-B4 | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 64.967 ms | 1 - 8 MB | FP16 | NPU | Use Export Script |
49
- | EfficientNet-B4 | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 3.614 ms | 0 - 281 MB | FP16 | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
50
- | EfficientNet-B4 | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 3.347 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
51
- | EfficientNet-B4 | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 5.632 ms | 0 - 25 MB | FP16 | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
52
- | EfficientNet-B4 | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 5.568 ms | 1 - 7 MB | FP16 | NPU | Use Export Script |
53
- | EfficientNet-B4 | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 7.179 ms | 0 - 35 MB | FP16 | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
54
- | EfficientNet-B4 | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 7.359 ms | 1 - 36 MB | FP16 | NPU | Use Export Script |
55
- | EfficientNet-B4 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 3.65 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
56
- | EfficientNet-B4 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 3.71 ms | 47 - 47 MB | FP16 | NPU | [EfficientNet-B4.onnx](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx) |
57
 
58
 
59
 
@@ -117,8 +117,8 @@ Profiling Results
117
  EfficientNet-B4
118
  Device : Samsung Galaxy S23 (13)
119
  Runtime : TFLITE
120
- Estimated inference time (ms) : 3.6
121
- Estimated peak memory usage (MB): [0, 280]
122
  Total # Ops : 482
123
  Compute Unit(s) : NPU (482 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-B4 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 3.341 ms | 0 - 386 MB | FP16 | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
39
+ | EfficientNet-B4 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 3.201 ms | 1 - 3 MB | FP16 | NPU | [EfficientNet-B4.so](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.so) |
40
+ | EfficientNet-B4 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 3.449 ms | 0 - 264 MB | FP16 | NPU | [EfficientNet-B4.onnx](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx) |
41
+ | EfficientNet-B4 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 2.44 ms | 0 - 78 MB | FP16 | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
42
+ | EfficientNet-B4 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 2.376 ms | 1 - 19 MB | FP16 | NPU | [EfficientNet-B4.so](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.so) |
43
+ | EfficientNet-B4 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 2.485 ms | 0 - 55 MB | FP16 | NPU | [EfficientNet-B4.onnx](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx) |
44
+ | EfficientNet-B4 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 2.315 ms | 0 - 65 MB | FP16 | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
45
+ | EfficientNet-B4 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 1.952 ms | 1 - 33 MB | FP16 | NPU | Use Export Script |
46
+ | EfficientNet-B4 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 2.45 ms | 0 - 36 MB | FP16 | NPU | [EfficientNet-B4.onnx](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx) |
47
+ | EfficientNet-B4 | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 64.838 ms | 0 - 61 MB | FP16 | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
48
+ | EfficientNet-B4 | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 64.616 ms | 1 - 8 MB | FP16 | NPU | Use Export Script |
49
+ | EfficientNet-B4 | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 3.338 ms | 0 - 385 MB | FP16 | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
50
+ | EfficientNet-B4 | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 3.183 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
51
+ | EfficientNet-B4 | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 5.266 ms | 0 - 61 MB | FP16 | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
52
+ | EfficientNet-B4 | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 5.029 ms | 1 - 10 MB | FP16 | NPU | Use Export Script |
53
+ | EfficientNet-B4 | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 6.977 ms | 0 - 82 MB | FP16 | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
54
+ | EfficientNet-B4 | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 6.983 ms | 1 - 46 MB | FP16 | NPU | Use Export Script |
55
+ | EfficientNet-B4 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 3.478 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
56
+ | EfficientNet-B4 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 3.421 ms | 46 - 46 MB | FP16 | NPU | [EfficientNet-B4.onnx](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx) |
57
 
58
 
59
 
 
117
  EfficientNet-B4
118
  Device : Samsung Galaxy S23 (13)
119
  Runtime : TFLITE
120
+ Estimated inference time (ms) : 3.3
121
+ Estimated peak memory usage (MB): [0, 386]
122
  Total # Ops : 482
123
  Compute Unit(s) : NPU (482 ops)
124
  ```