Hugging Face's logo

qualcomm
/
EfficientNet-V2-s

Image Classification
PyTorch
LiteRT
backbone
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
880f202
·
verified ·
1 Parent(s): bf82642

v0.31.0

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.31.0 for changelog.

Files changed (4) hide show
  1. .gitattributes +2 -0
  2. EfficientNet-V2-s.dlc +3 -0
  3. EfficientNet-V2-s_w8a16.dlc +3 -0
  4. README.md +33 -33
.gitattributes CHANGED
@@ -35,3 +35,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  EfficientNet-V2-s.so filter=lfs diff=lfs merge=lfs -text
37
  EfficientNet-V2-s_w8a16.so filter=lfs diff=lfs merge=lfs -text
 
 
 
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  EfficientNet-V2-s.so filter=lfs diff=lfs merge=lfs -text
37
  EfficientNet-V2-s_w8a16.so filter=lfs diff=lfs merge=lfs -text
38
+ EfficientNet-V2-s.dlc filter=lfs diff=lfs merge=lfs -text
39
+ EfficientNet-V2-s_w8a16.dlc filter=lfs diff=lfs merge=lfs -text
EfficientNet-V2-s.dlc ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:528c495414443fa6e5f12852e5a82d3b9c7600dc07d023cd36a110d080029f47
3
+ size 86047099
EfficientNet-V2-s_w8a16.dlc ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6c4427cfe04663d8207bf738a88c03133bbe9aeeb082eceb71b36e433fbd6db
3
+ size 28541928
README.md CHANGED
@@ -35,38 +35,38 @@ More details on model performance across various devices, can be found
35
 
36
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
- | EfficientNet-V2-s | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 60.038 ms | 0 - 78 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
39
- | EfficientNet-V2-s | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 10.778 ms | 0 - 9 MB | NPU | Use Export Script |
40
- | EfficientNet-V2-s | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 4.968 ms | 0 - 89 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
41
- | EfficientNet-V2-s | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 5.554 ms | 1 - 44 MB | NPU | Use Export Script |
42
- | EfficientNet-V2-s | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 2.69 ms | 0 - 375 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
43
- | EfficientNet-V2-s | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 2.545 ms | 0 - 7 MB | NPU | Use Export Script |
44
- | EfficientNet-V2-s | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 3.934 ms | 0 - 78 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
45
- | EfficientNet-V2-s | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 3.625 ms | 1 - 11 MB | NPU | Use Export Script |
46
- | EfficientNet-V2-s | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 2.718 ms | 0 - 375 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
47
- | EfficientNet-V2-s | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 2.583 ms | 0 - 43 MB | NPU | Use Export Script |
48
- | EfficientNet-V2-s | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 2.618 ms | 0 - 116 MB | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx) |
49
- | EfficientNet-V2-s | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 2.003 ms | 0 - 105 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
50
- | EfficientNet-V2-s | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 1.887 ms | 0 - 54 MB | NPU | Use Export Script |
51
- | EfficientNet-V2-s | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 1.944 ms | 0 - 67 MB | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx) |
52
- | EfficientNet-V2-s | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 1.611 ms | 0 - 80 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
53
- | EfficientNet-V2-s | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 1.503 ms | 1 - 36 MB | NPU | Use Export Script |
54
- | EfficientNet-V2-s | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 1.885 ms | 0 - 42 MB | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx) |
55
- | EfficientNet-V2-s | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 2.858 ms | 1 - 1 MB | NPU | Use Export Script |
56
- | EfficientNet-V2-s | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2.782 ms | 47 - 47 MB | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx) |
57
- | EfficientNet-V2-s | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 17.233 ms | 0 - 10 MB | NPU | Use Export Script |
58
- | EfficientNet-V2-s | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 3.254 ms | 0 - 67 MB | NPU | Use Export Script |
59
- | EfficientNet-V2-s | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 2.616 ms | 0 - 3 MB | NPU | Use Export Script |
60
- | EfficientNet-V2-s | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 2.993 ms | 0 - 11 MB | NPU | Use Export Script |
61
- | EfficientNet-V2-s | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN | 8.962 ms | 0 - 12 MB | NPU | Use Export Script |
62
- | EfficientNet-V2-s | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 2.628 ms | 0 - 18 MB | NPU | Use Export Script |
63
- | EfficientNet-V2-s | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 2.688 ms | 0 - 46 MB | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.onnx) |
64
- | EfficientNet-V2-s | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 1.773 ms | 0 - 68 MB | NPU | Use Export Script |
65
- | EfficientNet-V2-s | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 1.766 ms | 0 - 91 MB | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.onnx) |
66
- | EfficientNet-V2-s | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 1.526 ms | 0 - 62 MB | NPU | Use Export Script |
67
- | EfficientNet-V2-s | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 1.668 ms | 0 - 75 MB | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.onnx) |
68
- | EfficientNet-V2-s | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 2.916 ms | 0 - 0 MB | NPU | Use Export Script |
69
- | EfficientNet-V2-s | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2.849 ms | 26 - 26 MB | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.onnx) |
70
 
71
 
72
 
@@ -130,7 +130,7 @@ Profiling Results
130
  EfficientNet-V2-s
131
  Device : cs_8275 (ANDROID 14)
132
  Runtime : TFLITE
133
- Estimated inference time (ms) : 60.0
134
  Estimated peak memory usage (MB): [0, 78]
135
  Total # Ops : 508
136
  Compute Unit(s) : npu (508 ops) gpu (0 ops) cpu (0 ops)
 
35
 
36
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
+ | EfficientNet-V2-s | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 10.946 ms | 0 - 78 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
39
+ | EfficientNet-V2-s | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 10.8 ms | 1 - 32 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.dlc) |
40
+ | EfficientNet-V2-s | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 4.992 ms | 0 - 94 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
41
+ | EfficientNet-V2-s | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 5.534 ms | 1 - 45 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.dlc) |
42
+ | EfficientNet-V2-s | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 2.719 ms | 0 - 378 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
43
+ | EfficientNet-V2-s | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 2.597 ms | 1 - 12 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.dlc) |
44
+ | EfficientNet-V2-s | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 3.882 ms | 0 - 77 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
45
+ | EfficientNet-V2-s | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 3.663 ms | 1 - 32 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.dlc) |
46
+ | EfficientNet-V2-s | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 2.711 ms | 0 - 374 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
47
+ | EfficientNet-V2-s | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 2.599 ms | 0 - 53 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.dlc) |
48
+ | EfficientNet-V2-s | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 2.619 ms | 0 - 99 MB | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx) |
49
+ | EfficientNet-V2-s | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 1.997 ms | 0 - 106 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
50
+ | EfficientNet-V2-s | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 1.888 ms | 1 - 62 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.dlc) |
51
+ | EfficientNet-V2-s | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 1.907 ms | 0 - 68 MB | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx) |
52
+ | EfficientNet-V2-s | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 1.889 ms | 0 - 81 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
53
+ | EfficientNet-V2-s | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 1.778 ms | 1 - 38 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.dlc) |
54
+ | EfficientNet-V2-s | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 1.875 ms | 0 - 41 MB | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx) |
55
+ | EfficientNet-V2-s | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 3.334 ms | 232 - 232 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.dlc) |
56
+ | EfficientNet-V2-s | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2.812 ms | 47 - 47 MB | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx) |
57
+ | EfficientNet-V2-s | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 17.251 ms | 0 - 63 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
58
+ | EfficientNet-V2-s | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 3.251 ms | 0 - 77 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
59
+ | EfficientNet-V2-s | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 2.614 ms | 0 - 17 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
60
+ | EfficientNet-V2-s | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 3.017 ms | 0 - 64 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
61
+ | EfficientNet-V2-s | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 9.068 ms | 0 - 77 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
62
+ | EfficientNet-V2-s | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 2.637 ms | 0 - 16 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
63
+ | EfficientNet-V2-s | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 2.699 ms | 0 - 60 MB | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.onnx) |
64
+ | EfficientNet-V2-s | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 1.763 ms | 0 - 76 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
65
+ | EfficientNet-V2-s | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 1.84 ms | 0 - 92 MB | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.onnx) |
66
+ | EfficientNet-V2-s | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 1.496 ms | 0 - 69 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
67
+ | EfficientNet-V2-s | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 1.65 ms | 0 - 77 MB | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.onnx) |
68
+ | EfficientNet-V2-s | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 3.102 ms | 89 - 89 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
69
+ | EfficientNet-V2-s | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2.824 ms | 26 - 26 MB | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.onnx) |
70
 
71
 
72
 
 
130
  EfficientNet-V2-s
131
  Device : cs_8275 (ANDROID 14)
132
  Runtime : TFLITE
133
+ Estimated inference time (ms) : 10.9
134
  Estimated peak memory usage (MB): [0, 78]
135
  Total # Ops : 508
136
  Compute Unit(s) : npu (508 ops) gpu (0 ops) cpu (0 ops)