Hugging Face's logo

qualcomm
/
EfficientNet-V2-s

Image Classification
PyTorch
backbone
bu_auto
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
b41cdba
·
verified ·
1 Parent(s): 936e0a9

v0.34.0

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.34.0 for changelog.

Files changed (6) hide show
  1. EfficientNet-V2-s_w8a16.dlc +1 -1
  2. README.md +18 -27
  3. precompiled/qualcomm-qcs6490-proxy/sdk_versions.yml +3 -0
  4. precompiled/qualcomm-snapdragon-x-elite/EfficientNet-V2-s.onnx.zip +2 -2
  5. precompiled/qualcomm-snapdragon-x-elite/EfficientNet-V2-s_w8a16.onnx.zip +2 -2
  6. precompiled/qualcomm-snapdragon-x-elite/sdk_versions.yml +5 -0
EfficientNet-V2-s_w8a16.dlc CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5fc472f3bccdf4757d78f97f37b555595ec136bfa9e674fc7e297bbc659b77ba
3
  size 28550407
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cc5a617ef9953fe564a6e448511c4035235670c02e1f6863092175143c5f322
3
  size 28550407
README.md CHANGED
@@ -24,6 +24,7 @@ More details on model performance across various devices, can be found
24
  [here](https://aihub.qualcomm.com/models/efficientnet_v2_s).
25
 
26
 
 
27
  ### Model Details
28
 
29
  - **Model Type:** Model_use_case.image_classification
@@ -36,37 +37,37 @@ More details on model performance across various devices, can be found
36
 
37
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
- | 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) |
40
  | 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) |
41
- | 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) |
42
  | 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) |
43
- | 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) |
44
  | 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) |
45
- | 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) |
46
  | 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) |
47
- | 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) |
48
  | 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) |
49
  | EfficientNet-V2-s | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 2.667 ms | 0 - 107 MB | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx) |
50
- | 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) |
51
  | 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) |
52
  | EfficientNet-V2-s | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 1.969 ms | 0 - 68 MB | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx) |
53
- | 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) |
54
  | 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) |
55
  | EfficientNet-V2-s | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 1.898 ms | 1 - 40 MB | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx) |
56
  | 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) |
57
  | EfficientNet-V2-s | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2.798 ms | 47 - 47 MB | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx) |
58
- | EfficientNet-V2-s | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 5.266 ms | 0 - 63 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 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 3.314 ms | 0 - 74 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 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 2.579 ms | 0 - 23 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 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 2.998 ms | 0 - 64 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 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 8.933 ms | 0 - 76 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 | QNN_DLC | 2.651 ms | 0 - 17 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
64
  | EfficientNet-V2-s | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 2.725 ms | 0 - 51 MB | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.onnx) |
65
- | EfficientNet-V2-s | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 1.758 ms | 0 - 73 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
66
  | EfficientNet-V2-s | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 1.815 ms | 0 - 78 MB | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.onnx) |
67
- | EfficientNet-V2-s | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 1.246 ms | 0 - 68 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
68
  | EfficientNet-V2-s | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 1.659 ms | 0 - 74 MB | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.onnx) |
69
- | EfficientNet-V2-s | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 3.085 ms | 88 - 88 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
70
  | EfficientNet-V2-s | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2.881 ms | 25 - 25 MB | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.onnx) |
71
 
72
 
@@ -125,17 +126,7 @@ device. This script does the following:
125
  ```bash
126
  python -m qai_hub_models.models.efficientnet_v2_s.export
127
  ```
128
- ```
129
- Profiling Results
130
- ------------------------------------------------------------
131
- EfficientNet-V2-s
132
- Device : cs_8275 (ANDROID 14)
133
- Runtime : TFLITE
134
- Estimated inference time (ms) : 10.9
135
- Estimated peak memory usage (MB): [0, 78]
136
- Total # Ops : 508
137
- Compute Unit(s) : npu (508 ops) gpu (0 ops) cpu (0 ops)
138
- ```
139
 
140
 
141
  ## How does this work?
 
24
  [here](https://aihub.qualcomm.com/models/efficientnet_v2_s).
25
 
26
 
27
+
28
  ### Model Details
29
 
30
  - **Model Type:** Model_use_case.image_classification
 
37
 
38
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
39
  |---|---|---|---|---|---|---|---|---|
40
+ | EfficientNet-V2-s | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 10.959 ms | 0 - 78 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
41
  | 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) |
42
+ | EfficientNet-V2-s | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 5.019 ms | 0 - 90 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
43
  | 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) |
44
+ | EfficientNet-V2-s | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 2.716 ms | 0 - 374 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
45
  | 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) |
46
+ | EfficientNet-V2-s | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 3.917 ms | 0 - 78 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
47
  | 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) |
48
+ | EfficientNet-V2-s | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 2.724 ms | 0 - 375 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
49
  | 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) |
50
  | EfficientNet-V2-s | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 2.667 ms | 0 - 107 MB | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx) |
51
+ | EfficientNet-V2-s | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 2.008 ms | 0 - 105 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
52
  | 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) |
53
  | EfficientNet-V2-s | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 1.969 ms | 0 - 68 MB | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx) |
54
+ | EfficientNet-V2-s | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 1.89 ms | 0 - 81 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
55
  | 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) |
56
  | EfficientNet-V2-s | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 1.898 ms | 1 - 40 MB | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx) |
57
  | 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) |
58
  | EfficientNet-V2-s | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2.798 ms | 47 - 47 MB | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx) |
59
+ | EfficientNet-V2-s | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 5.314 ms | 0 - 63 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 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 3.142 ms | 0 - 77 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 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 2.639 ms | 0 - 17 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 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 2.989 ms | 0 - 64 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 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 9.086 ms | 0 - 76 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
64
+ | EfficientNet-V2-s | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 2.612 ms | 0 - 17 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 S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 2.725 ms | 0 - 51 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 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 1.77 ms | 0 - 75 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 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 1.815 ms | 0 - 78 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 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 1.5 ms | 0 - 67 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 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 1.659 ms | 0 - 74 MB | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.onnx) |
70
+ | EfficientNet-V2-s | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 3.094 ms | 89 - 89 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
71
  | EfficientNet-V2-s | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2.881 ms | 25 - 25 MB | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.onnx) |
72
 
73
 
 
126
  ```bash
127
  python -m qai_hub_models.models.efficientnet_v2_s.export
128
  ```
129
+
 
 
 
 
 
 
 
 
 
 
130
 
131
 
132
  ## How does this work?
precompiled/qualcomm-qcs6490-proxy/sdk_versions.yml ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ sdk_versions:
2
+ qnn_context_binary:
3
+ qairt: 2.34.2.250528164111_119506
precompiled/qualcomm-snapdragon-x-elite/EfficientNet-V2-s.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b843964016e91624937363967b04804ff7f9034ffbf2f408d05e1f748bb35c61
3
- size 41331913
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27c797b7e35dcb032397d29fec1d2868e391c1d84b45b49373da40c05c24089f
3
+ size 41331934
precompiled/qualcomm-snapdragon-x-elite/EfficientNet-V2-s_w8a16.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:607169a9cce2cd0526bd4e7e77fce29aae7b761fda548fdce5ab9ef66d323d6a
3
- size 20061844
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26429750bd1fdb87d4092dba3ee4eaccca3300fb224f0e94612f60dfd26f3284
3
+ size 20061845
precompiled/qualcomm-snapdragon-x-elite/sdk_versions.yml ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ sdk_versions:
2
+ qnn_context_binary:
3
+ qairt: 2.34.2.250528164111_119506
4
+ precompiled_qnn_onnx:
5
+ qairt: 2.33.2.250410134701_117956