Hugging Face's logo

qualcomm
/
EfficientNet-V2-s

Image Classification
PyTorch
LiteRT
backbone
android
Model card Files Community
qaihm-bot commited on
Commit
e0c5997
·
verified ·
1 Parent(s): 880f202

v0.32.0

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.32.0 for changelog.

Files changed (7) hide show
  1. .gitattributes +1 -0
  2. DEPLOYMENT_MODEL_LICENSE.pdf +3 -0
  3. EfficientNet-V2-s.onnx +2 -2
  4. EfficientNet-V2-s_w8a16.dlc +2 -2
  5. EfficientNet-V2-s_w8a16.onnx +2 -2
  6. LICENSE +2 -0
  7. README.md +20 -19
.gitattributes CHANGED
@@ -37,3 +37,4 @@ 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
 
 
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
40
+ DEPLOYMENT_MODEL_LICENSE.pdf filter=lfs diff=lfs merge=lfs -text
DEPLOYMENT_MODEL_LICENSE.pdf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4409f93b0e82531303b3e10f52f1fdfb56467a25f05b7441c6bbd8bb8a64b42c
3
+ size 109629
EfficientNet-V2-s.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4864a97912dd26d4f4352db13dab7015916c4dc5cbaeea3616abced07bda77ba
3
- size 85677207
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eeb2f68b3da3b614c1a43839f8f2cef2513d281b7644eda3dc9227ec77eaecf1
3
+ size 85692617
EfficientNet-V2-s_w8a16.dlc CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6c4427cfe04663d8207bf738a88c03133bbe9aeeb082eceb71b36e433fbd6db
3
- size 28541928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1034cc57485386822176cff32bfdec64c9f4f77f38382d46c3f6593331b34a16
3
+ size 28541871
EfficientNet-V2-s_w8a16.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cdb52f08aea1b2a2e136a6feec47d30568e1659254548bd7dd34901951b6b918
3
- size 86610658
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:718fb04408baac19ff6c831e55e003224d6dfdd15416c38c3f359bbdca5272e2
3
+ size 86610690
LICENSE ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ The license of the original trained model can be found at https://github.com/pytorch/vision/blob/main/LICENSE.
2
+ The license for the deployable model files (.tflite, .onnx, .dlc, .bin, etc.) can be found in DEPLOYMENT_MODEL_LICENSE.pdf.
README.md CHANGED
@@ -30,8 +30,9 @@ More details on model performance across various devices, can be found
30
  - **Model Stats:**
31
  - Model checkpoint: Imagenet
32
  - Input resolution: 384x384
33
- - Number of parameters: 21.45M
34
- - Model size: 82.7 MB
 
35
 
36
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
@@ -45,28 +46,28 @@ More details on model performance across various devices, can be found
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
 
 
30
  - **Model Stats:**
31
  - Model checkpoint: Imagenet
32
  - Input resolution: 384x384
33
+ - Number of parameters: 21.4M
34
+ - Model size (float): 81.7 MB
35
+ - Model size (w8a16): 27.2 MB
36
 
37
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
 
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 | 2.647 ms | 0 - 118 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 | 1.975 ms | 0 - 70 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 | 1.879 ms | 0 - 42 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 | 2.826 ms | 46 - 46 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 | 5.316 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 | 3.169 ms | 0 - 73 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 | 2.618 ms | 0 - 18 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 | 2.997 ms | 0 - 63 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 - 75 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 | 2.634 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 | 2.756 ms | 0 - 55 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 | 1.766 ms | 0 - 75 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 | 1.851 ms | 0 - 93 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 | 1.503 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 | 1.677 ms | 0 - 77 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 | 3.073 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 | 2.923 ms | 26 - 26 MB | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.onnx) |
71
 
72
 
73