Hugging Face's logo

qualcomm
/
EfficientViT-l2-cls

Image Classification
PyTorch
backbone
bu_auto
real_time
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
76ebf43
·
verified ·
1 Parent(s): 4789523

v0.38.0

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.38.0 for changelog.

Files changed (7) hide show
  1. EfficientViT-l2-cls_float.dlc +2 -2
  2. EfficientViT-l2-cls_float.onnx.zip +2 -2
  3. README.md +18 -21
  4. precompiled/qualcomm-snapdragon-x-elite/EfficientViT-l2-cls_float.bin +0 -3
  5. precompiled/qualcomm-snapdragon-x-elite/EfficientViT-l2-cls_float.onnx.zip +0 -3
  6. precompiled/qualcomm-snapdragon-x-elite/tool-versions.yaml +0 -3
  7. tool-versions.yaml +2 -2
EfficientViT-l2-cls_float.dlc CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0da01719fe3f2d44bd71ca637a58fed4c42b0ab8b9df53573e81a4d209fc34f3
3
- size 255300204
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15b36e10ac0f95805f518748802157114745b00eb37839d59db3fc1774928c13
3
+ size 255300292
EfficientViT-l2-cls_float.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c0d94f8433cc4af7304e601f9fc79fd6e7e06773fee0493900090755c66b96d
3
- size 237936407
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9690a294bbaaf1dab0ef9d181fa74fe14b82c1bf22e109e243a31d7247f4f0e8
3
+ size 237936515
README.md CHANGED
@@ -37,26 +37,23 @@ More details on model performance across various devices, can be found
37
 
38
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
39
  |---|---|---|---|---|---|---|---|---|
40
- | EfficientViT-l2-cls | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 23.749 ms | 3 - 208 MB | NPU | [EfficientViT-l2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.tflite) |
41
- | EfficientViT-l2-cls | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 24.375 ms | 1 - 89 MB | NPU | [EfficientViT-l2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.dlc) |
42
- | EfficientViT-l2-cls | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 13.663 ms | 0 - 213 MB | NPU | [EfficientViT-l2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.tflite) |
43
- | EfficientViT-l2-cls | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 15.008 ms | 1 - 97 MB | NPU | [EfficientViT-l2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.dlc) |
44
- | EfficientViT-l2-cls | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 7.131 ms | 0 - 39 MB | NPU | [EfficientViT-l2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.tflite) |
45
- | EfficientViT-l2-cls | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 7.451 ms | 0 - 23 MB | NPU | [EfficientViT-l2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.dlc) |
46
- | EfficientViT-l2-cls | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 28.755 ms | 0 - 44 MB | NPU | [EfficientViT-l2-cls.onnx.zip](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.onnx.zip) |
47
- | EfficientViT-l2-cls | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 9.035 ms | 0 - 206 MB | NPU | [EfficientViT-l2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.tflite) |
48
- | EfficientViT-l2-cls | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 9.66 ms | 1 - 88 MB | NPU | [EfficientViT-l2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.dlc) |
49
- | EfficientViT-l2-cls | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 7.131 ms | 0 - 294 MB | NPU | [EfficientViT-l2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.tflite) |
50
- | EfficientViT-l2-cls | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 7.392 ms | 0 - 23 MB | NPU | [EfficientViT-l2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.dlc) |
51
- | EfficientViT-l2-cls | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 28.835 ms | 0 - 202 MB | NPU | [EfficientViT-l2-cls.onnx.zip](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.onnx.zip) |
52
- | EfficientViT-l2-cls | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 5.107 ms | 0 - 236 MB | NPU | [EfficientViT-l2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.tflite) |
53
- | EfficientViT-l2-cls | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 5.323 ms | 1 - 117 MB | NPU | [EfficientViT-l2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.dlc) |
54
- | EfficientViT-l2-cls | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 20.189 ms | 1 - 155 MB | NPU | [EfficientViT-l2-cls.onnx.zip](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.onnx.zip) |
55
- | EfficientViT-l2-cls | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 4.761 ms | 0 - 207 MB | NPU | [EfficientViT-l2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.tflite) |
56
- | EfficientViT-l2-cls | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 4.778 ms | 1 - 172 MB | NPU | [EfficientViT-l2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.dlc) |
57
- | EfficientViT-l2-cls | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 17.875 ms | 1 - 129 MB | NPU | [EfficientViT-l2-cls.onnx.zip](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.onnx.zip) |
58
- | EfficientViT-l2-cls | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 8.044 ms | 659 - 659 MB | NPU | [EfficientViT-l2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.dlc) |
59
- | EfficientViT-l2-cls | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 29.892 ms | 130 - 130 MB | NPU | [EfficientViT-l2-cls.onnx.zip](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.onnx.zip) |
60
 
61
 
62
 
@@ -138,7 +135,7 @@ from qai_hub_models.models.efficientvit_l2_cls import Model
138
  torch_model = Model.from_pretrained()
139
 
140
  # Device
141
- device = hub.Device("Samsung Galaxy S24")
142
 
143
  # Trace model
144
  input_shape = torch_model.get_input_spec()
 
37
 
38
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
39
  |---|---|---|---|---|---|---|---|---|
40
+ | EfficientViT-l2-cls | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 23.688 ms | 0 - 206 MB | NPU | [EfficientViT-l2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.tflite) |
41
+ | EfficientViT-l2-cls | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 24.349 ms | 1 - 89 MB | NPU | [EfficientViT-l2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.dlc) |
42
+ | EfficientViT-l2-cls | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 13.641 ms | 0 - 217 MB | NPU | [EfficientViT-l2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.tflite) |
43
+ | EfficientViT-l2-cls | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 14.875 ms | 0 - 96 MB | NPU | [EfficientViT-l2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.dlc) |
44
+ | EfficientViT-l2-cls | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 7.212 ms | 0 - 64 MB | NPU | [EfficientViT-l2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.tflite) |
45
+ | EfficientViT-l2-cls | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 7.424 ms | 0 - 25 MB | NPU | [EfficientViT-l2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.dlc) |
46
+ | EfficientViT-l2-cls | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 24.96 ms | 0 - 201 MB | NPU | [EfficientViT-l2-cls.onnx.zip](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.onnx.zip) |
47
+ | EfficientViT-l2-cls | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 9.117 ms | 0 - 207 MB | NPU | [EfficientViT-l2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.tflite) |
48
+ | EfficientViT-l2-cls | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 9.694 ms | 1 - 88 MB | NPU | [EfficientViT-l2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.dlc) |
49
+ | EfficientViT-l2-cls | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 5.147 ms | 0 - 230 MB | NPU | [EfficientViT-l2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.tflite) |
50
+ | EfficientViT-l2-cls | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 5.258 ms | 1 - 118 MB | NPU | [EfficientViT-l2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.dlc) |
51
+ | EfficientViT-l2-cls | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 17.78 ms | 1 - 161 MB | NPU | [EfficientViT-l2-cls.onnx.zip](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.onnx.zip) |
52
+ | EfficientViT-l2-cls | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 4.208 ms | 0 - 208 MB | NPU | [EfficientViT-l2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.tflite) |
53
+ | EfficientViT-l2-cls | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 4.197 ms | 1 - 176 MB | NPU | [EfficientViT-l2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.dlc) |
54
+ | EfficientViT-l2-cls | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 12.349 ms | 1 - 130 MB | NPU | [EfficientViT-l2-cls.onnx.zip](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.onnx.zip) |
55
+ | EfficientViT-l2-cls | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 8.075 ms | 660 - 660 MB | NPU | [EfficientViT-l2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.dlc) |
56
+ | EfficientViT-l2-cls | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 25.984 ms | 130 - 130 MB | NPU | [EfficientViT-l2-cls.onnx.zip](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.onnx.zip) |
 
 
 
57
 
58
 
59
 
 
135
  torch_model = Model.from_pretrained()
136
 
137
  # Device
138
+ device = hub.Device("Samsung Galaxy S25")
139
 
140
  # Trace model
141
  input_shape = torch_model.get_input_spec()
precompiled/qualcomm-snapdragon-x-elite/EfficientViT-l2-cls_float.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c42ffedcab429d17a58bfeb057154ec95644cba1fda1f33297f88f32e1495da
3
- size 137592832
 
 
 
 
precompiled/qualcomm-snapdragon-x-elite/EfficientViT-l2-cls_float.onnx.zip DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:85438dfc06b3137b37549b8cd17b542725e44d4daeb0a46bd34c34a19c98b883
3
- size 119964478
 
 
 
 
precompiled/qualcomm-snapdragon-x-elite/tool-versions.yaml DELETED
@@ -1,3 +0,0 @@
1
- tool_versions:
2
- precompiled_qnn_onnx:
3
- qairt: 2.36.4.250725200057_123280
 
 
 
 
tool-versions.yaml CHANGED
@@ -1,4 +1,4 @@
1
  tool_versions:
2
  onnx:
3
- qairt: 2.36.4.250725200057_123280
4
- onnx_runtime: 1.22.0
 
1
  tool_versions:
2
  onnx:
3
+ qairt: 2.37.1.250807093845_124904
4
+ onnx_runtime: 1.22.2