Hugging Face's logo

qualcomm
/
EfficientViT-b2-cls

Image Classification
PyTorch
LiteRT
backbone
bu_auto
real_time
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
fca1d71
·
verified ·
1 Parent(s): 44b2659

v0.44.0

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.44.0 for changelog.

Files changed (6) hide show
  1. DEPLOYMENT_MODEL_LICENSE.pdf +0 -3
  2. EfficientViT-b2-cls_float.dlc +1 -1
  3. EfficientViT-b2-cls_float.onnx.zip +2 -2
  4. EfficientViT-b2-cls_float.tflite +2 -2
  5. LICENSE +0 -1
  6. README.md +21 -21
DEPLOYMENT_MODEL_LICENSE.pdf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4409f93b0e82531303b3e10f52f1fdfb56467a25f05b7441c6bbd8bb8a64b42c
3
- size 109629
 
 
 
 
EfficientViT-b2-cls_float.dlc CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:598301c7ad18271bc8ada06f8ff732f8e74e223465256502c8f6b77a4cbf48bf
3
  size 97803788
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a698394fbec3c42bcb10dc1839765224f0031cca99e2ab31716a644bd7cc30b7
3
  size 97803788
EfficientViT-b2-cls_float.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72fe44612c7d1062473f91d96066eefa4e8aebc5ce4c841ef07c61c38adac6e9
3
- size 91249924
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94904106cb0d4c4ab926396e27154a2b5d95cc70b867232807216a829f826922
3
+ size 91249844
EfficientViT-b2-cls_float.tflite CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:274cbf5690e668f864e633bd739b2e882072a1ab325c466ca6a962bff798c5a8
3
- size 97360420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d34bdd57f7492c9203a9874092ee5b2684e9325d87da3d6ad7ee19de85490b32
3
+ size 97360440
LICENSE CHANGED
@@ -1,2 +1 @@
1
  The license of the original trained model can be found at https://github.com/CVHub520/efficientvit/blob/main/LICENSE.
2
- The license for the deployable model files (.tflite, .onnx, .dlc, .bin, etc.) can be found in DEPLOYMENT_MODEL_LICENSE.pdf.
 
1
  The license of the original trained model can be found at https://github.com/CVHub520/efficientvit/blob/main/LICENSE.
 
README.md CHANGED
@@ -3,6 +3,7 @@ library_name: pytorch
3
  license: other
4
  tags:
5
  - backbone
 
6
  - real_time
7
  - android
8
  pipeline_tag: image-classification
@@ -37,26 +38,26 @@ 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-b2-cls | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 12.333 ms | 0 - 105 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
41
- | EfficientViT-b2-cls | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 12.949 ms | 1 - 64 MB | NPU | [EfficientViT-b2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.dlc) |
42
- | EfficientViT-b2-cls | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 5.937 ms | 0 - 113 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
43
- | EfficientViT-b2-cls | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 7.077 ms | 1 - 71 MB | NPU | [EfficientViT-b2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.dlc) |
44
- | EfficientViT-b2-cls | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 5.021 ms | 0 - 329 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
45
- | EfficientViT-b2-cls | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 5.412 ms | 1 - 18 MB | NPU | [EfficientViT-b2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.dlc) |
46
- | EfficientViT-b2-cls | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 5.36 ms | 0 - 125 MB | NPU | [EfficientViT-b2-cls.onnx.zip](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.onnx.zip) |
47
- | EfficientViT-b2-cls | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 24.616 ms | 0 - 105 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
48
- | EfficientViT-b2-cls | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 6.645 ms | 1 - 63 MB | NPU | [EfficientViT-b2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.dlc) |
49
- | EfficientViT-b2-cls | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 3.464 ms | 0 - 120 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
50
- | EfficientViT-b2-cls | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 3.814 ms | 0 - 79 MB | NPU | [EfficientViT-b2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.dlc) |
51
- | EfficientViT-b2-cls | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 3.73 ms | 0 - 78 MB | NPU | [EfficientViT-b2-cls.onnx.zip](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.onnx.zip) |
52
- | EfficientViT-b2-cls | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 2.852 ms | 0 - 109 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
53
- | EfficientViT-b2-cls | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 2.814 ms | 1 - 69 MB | NPU | [EfficientViT-b2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.dlc) |
54
- | EfficientViT-b2-cls | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 2.865 ms | 0 - 64 MB | NPU | [EfficientViT-b2-cls.onnx.zip](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.onnx.zip) |
55
- | EfficientViT-b2-cls | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 2.404 ms | 0 - 107 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
56
- | EfficientViT-b2-cls | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 2.334 ms | 1 - 69 MB | NPU | [EfficientViT-b2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.dlc) |
57
- | EfficientViT-b2-cls | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 2.475 ms | 1 - 68 MB | NPU | [EfficientViT-b2-cls.onnx.zip](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.onnx.zip) |
58
- | EfficientViT-b2-cls | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 6.113 ms | 291 - 291 MB | NPU | [EfficientViT-b2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.dlc) |
59
- | EfficientViT-b2-cls | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 5.883 ms | 49 - 49 MB | NPU | [EfficientViT-b2-cls.onnx.zip](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.onnx.zip) |
60
 
61
 
62
 
@@ -233,7 +234,6 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
233
  ## License
234
  * The license for the original implementation of EfficientViT-b2-cls can be found
235
  [here](https://github.com/CVHub520/efficientvit/blob/main/LICENSE).
236
- * The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)
237
 
238
 
239
 
 
3
  license: other
4
  tags:
5
  - backbone
6
+ - bu_auto
7
  - real_time
8
  - android
9
  pipeline_tag: image-classification
 
38
 
39
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
40
  |---|---|---|---|---|---|---|---|---|
41
+ | EfficientViT-b2-cls | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 12.902 ms | 0 - 214 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
42
+ | EfficientViT-b2-cls | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 12.875 ms | 1 - 173 MB | NPU | [EfficientViT-b2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.dlc) |
43
+ | EfficientViT-b2-cls | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 6.963 ms | 0 - 291 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
44
+ | EfficientViT-b2-cls | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 7.108 ms | 1 - 251 MB | NPU | [EfficientViT-b2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.dlc) |
45
+ | EfficientViT-b2-cls | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 5.393 ms | 0 - 4 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
46
+ | EfficientViT-b2-cls | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 5.432 ms | 1 - 2 MB | NPU | [EfficientViT-b2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.dlc) |
47
+ | EfficientViT-b2-cls | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 5.375 ms | 0 - 58 MB | NPU | [EfficientViT-b2-cls.onnx.zip](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.onnx.zip) |
48
+ | EfficientViT-b2-cls | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 6.651 ms | 0 - 214 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
49
+ | EfficientViT-b2-cls | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 6.665 ms | 1 - 173 MB | NPU | [EfficientViT-b2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.dlc) |
50
+ | EfficientViT-b2-cls | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 3.791 ms | 0 - 289 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
51
+ | EfficientViT-b2-cls | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 3.771 ms | 1 - 252 MB | NPU | [EfficientViT-b2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.dlc) |
52
+ | EfficientViT-b2-cls | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 3.737 ms | 0 - 221 MB | NPU | [EfficientViT-b2-cls.onnx.zip](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.onnx.zip) |
53
+ | EfficientViT-b2-cls | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 2.801 ms | 0 - 211 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
54
+ | EfficientViT-b2-cls | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 2.794 ms | 0 - 174 MB | NPU | [EfficientViT-b2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.dlc) |
55
+ | EfficientViT-b2-cls | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 2.863 ms | 0 - 151 MB | NPU | [EfficientViT-b2-cls.onnx.zip](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.onnx.zip) |
56
+ | EfficientViT-b2-cls | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 2.342 ms | 0 - 215 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
57
+ | EfficientViT-b2-cls | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 2.343 ms | 1 - 179 MB | NPU | [EfficientViT-b2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.dlc) |
58
+ | EfficientViT-b2-cls | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 2.478 ms | 1 - 151 MB | NPU | [EfficientViT-b2-cls.onnx.zip](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.onnx.zip) |
59
+ | EfficientViT-b2-cls | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 6.131 ms | 1 - 1 MB | NPU | [EfficientViT-b2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.dlc) |
60
+ | EfficientViT-b2-cls | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 5.818 ms | 49 - 49 MB | NPU | [EfficientViT-b2-cls.onnx.zip](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.onnx.zip) |
61
 
62
 
63
 
 
234
  ## License
235
  * The license for the original implementation of EfficientViT-b2-cls can be found
236
  [here](https://github.com/CVHub520/efficientvit/blob/main/LICENSE).
 
237
 
238
 
239