Hugging Face's logo

qualcomm
/
EfficientViT-l2-cls

Image Classification
PyTorch
LiteRT
ONNX
backbone
real_time
android
Model card Files Community
qaihm-bot commited on
Commit
f723389
·
verified ·
1 Parent(s): 6bd187b

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +29 -29
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  library_name: pytorch
3
- license: bsd-3-clause
4
  tags:
5
  - backbone
6
  - real_time
@@ -27,34 +27,34 @@ More details on model performance across various devices, can be found
27
 
28
  ### Model Details
29
 
30
- - **Model Type:** Image classification
31
  - **Model Stats:**
32
  - Model checkpoint: Imagenet
33
  - Input resolution: 224x224
34
  - Number of parameters: 64M
35
- - Model size: 243 MB
36
 
37
- | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
- | EfficientViT-l2-cls | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 18.947 ms | 0 - 27 MB | FP16 | NPU | [EfficientViT-l2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.tflite) |
40
- | EfficientViT-l2-cls | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 18.956 ms | 0 - 29 MB | FP16 | NPU | [EfficientViT-l2-cls.so](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.so) |
41
- | EfficientViT-l2-cls | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 14.709 ms | 0 - 374 MB | FP16 | NPU | [EfficientViT-l2-cls.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.onnx) |
42
- | EfficientViT-l2-cls | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 13.702 ms | 0 - 274 MB | FP16 | NPU | [EfficientViT-l2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.tflite) |
43
- | EfficientViT-l2-cls | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 13.685 ms | 1 - 161 MB | FP16 | NPU | [EfficientViT-l2-cls.so](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.so) |
44
- | EfficientViT-l2-cls | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 10.337 ms | 1 - 185 MB | FP16 | NPU | [EfficientViT-l2-cls.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.onnx) |
45
- | EfficientViT-l2-cls | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 11.685 ms | 0 - 245 MB | FP16 | NPU | [EfficientViT-l2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.tflite) |
46
- | EfficientViT-l2-cls | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 11.859 ms | 0 - 135 MB | FP16 | NPU | Use Export Script |
47
- | EfficientViT-l2-cls | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 7.468 ms | 1 - 149 MB | FP16 | NPU | [EfficientViT-l2-cls.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.onnx) |
48
- | EfficientViT-l2-cls | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 149.519 ms | 0 - 243 MB | FP16 | NPU | [EfficientViT-l2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.tflite) |
49
- | EfficientViT-l2-cls | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 140.768 ms | 1 - 10 MB | FP16 | NPU | Use Export Script |
50
- | EfficientViT-l2-cls | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 18.81 ms | 0 - 29 MB | FP16 | NPU | [EfficientViT-l2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.tflite) |
51
- | EfficientViT-l2-cls | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 14.587 ms | 1 - 4 MB | FP16 | NPU | Use Export Script |
52
- | EfficientViT-l2-cls | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 24.972 ms | 0 - 243 MB | FP16 | NPU | [EfficientViT-l2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.tflite) |
53
- | EfficientViT-l2-cls | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 19.585 ms | 0 - 10 MB | FP16 | NPU | Use Export Script |
54
- | EfficientViT-l2-cls | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 17.284 ms | 0 - 213 MB | FP16 | NPU | [EfficientViT-l2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.tflite) |
55
- | EfficientViT-l2-cls | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 17.365 ms | 0 - 100 MB | FP16 | NPU | Use Export Script |
56
- | EfficientViT-l2-cls | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 15.545 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
57
- | EfficientViT-l2-cls | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 16.335 ms | 131 - 131 MB | FP16 | NPU | [EfficientViT-l2-cls.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.onnx) |
58
 
59
 
60
 
@@ -116,12 +116,12 @@ python -m qai_hub_models.models.efficientvit_l2_cls.export
116
  Profiling Results
117
  ------------------------------------------------------------
118
  EfficientViT-l2-cls
119
- Device : Samsung Galaxy S23 (13)
120
- Runtime : TFLITE
121
- Estimated inference time (ms) : 18.9
122
- Estimated peak memory usage (MB): [0, 27]
123
- Total # Ops : 675
124
- Compute Unit(s) : NPU (675 ops)
125
  ```
126
 
127
 
 
1
  ---
2
  library_name: pytorch
3
+ license: other
4
  tags:
5
  - backbone
6
  - real_time
 
27
 
28
  ### Model Details
29
 
30
+ - **Model Type:** Model_use_case.image_classification
31
  - **Model Stats:**
32
  - Model checkpoint: Imagenet
33
  - Input resolution: 224x224
34
  - Number of parameters: 64M
35
+ - Model size (float): 243 MB
36
 
37
+ | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
+ | EfficientViT-l2-cls | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 23.761 ms | 0 - 192 MB | NPU | [EfficientViT-l2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.tflite) |
40
+ | EfficientViT-l2-cls | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 23.921 ms | 0 - 10 MB | NPU | Use Export Script |
41
+ | EfficientViT-l2-cls | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 13.936 ms | 0 - 205 MB | NPU | [EfficientViT-l2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.tflite) |
42
+ | EfficientViT-l2-cls | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 14.834 ms | 0 - 88 MB | NPU | Use Export Script |
43
+ | EfficientViT-l2-cls | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 7.087 ms | 0 - 115 MB | NPU | [EfficientViT-l2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.tflite) |
44
+ | EfficientViT-l2-cls | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 7.258 ms | 1 - 2 MB | NPU | Use Export Script |
45
+ | EfficientViT-l2-cls | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 9.087 ms | 0 - 192 MB | NPU | [EfficientViT-l2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.tflite) |
46
+ | EfficientViT-l2-cls | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 9.203 ms | 1 - 10 MB | NPU | Use Export Script |
47
+ | EfficientViT-l2-cls | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 7.141 ms | 0 - 167 MB | NPU | [EfficientViT-l2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.tflite) |
48
+ | EfficientViT-l2-cls | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 7.293 ms | 0 - 22 MB | NPU | Use Export Script |
49
+ | EfficientViT-l2-cls | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 29.422 ms | 0 - 255 MB | NPU | [EfficientViT-l2-cls.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.onnx) |
50
+ | EfficientViT-l2-cls | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 5.11 ms | 0 - 219 MB | NPU | [EfficientViT-l2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.tflite) |
51
+ | EfficientViT-l2-cls | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 5.328 ms | 1 - 103 MB | NPU | Use Export Script |
52
+ | EfficientViT-l2-cls | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 20.345 ms | 1 - 156 MB | NPU | [EfficientViT-l2-cls.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.onnx) |
53
+ | EfficientViT-l2-cls | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 4.75 ms | 0 - 195 MB | NPU | [EfficientViT-l2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.tflite) |
54
+ | EfficientViT-l2-cls | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 4.023 ms | 1 - 83 MB | NPU | Use Export Script |
55
+ | EfficientViT-l2-cls | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 18.154 ms | 1 - 125 MB | NPU | [EfficientViT-l2-cls.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.onnx) |
56
+ | EfficientViT-l2-cls | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 7.749 ms | 1 - 1 MB | NPU | Use Export Script |
57
+ | EfficientViT-l2-cls | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 30.974 ms | 130 - 130 MB | NPU | [EfficientViT-l2-cls.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.onnx) |
58
 
59
 
60
 
 
116
  Profiling Results
117
  ------------------------------------------------------------
118
  EfficientViT-l2-cls
119
+ Device : cs_8275 (ANDROID 14)
120
+ Runtime : TFLITE
121
+ Estimated inference time (ms) : 23.8
122
+ Estimated peak memory usage (MB): [0, 192]
123
+ Total # Ops : 349
124
+ Compute Unit(s) : npu (349 ops) gpu (0 ops) cpu (0 ops)
125
  ```
126
 
127