Hugging Face's logo

qualcomm
/
EfficientViT-b2-cls

Image Classification
PyTorch
backbone
bu_auto
real_time
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
0dffa65
·
verified ·
1 Parent(s): 0425561

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: 24M
35
- - Model size: 200 MB
36
 
37
- | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
- | EfficientViT-b2-cls | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 5.053 ms | 0 - 249 MB | FP16 | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
40
- | EfficientViT-b2-cls | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 5.113 ms | 0 - 161 MB | FP16 | NPU | [EfficientViT-b2-cls.so](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.so) |
41
- | EfficientViT-b2-cls | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 5.172 ms | 0 - 143 MB | FP16 | NPU | [EfficientViT-b2-cls.onnx](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.onnx) |
42
- | EfficientViT-b2-cls | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 3.463 ms | 0 - 112 MB | FP16 | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
43
- | EfficientViT-b2-cls | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 3.486 ms | 1 - 72 MB | FP16 | NPU | [EfficientViT-b2-cls.so](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.so) |
44
- | EfficientViT-b2-cls | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 3.67 ms | 0 - 73 MB | FP16 | NPU | [EfficientViT-b2-cls.onnx](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.onnx) |
45
- | EfficientViT-b2-cls | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 3.32 ms | 0 - 97 MB | FP16 | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
46
- | EfficientViT-b2-cls | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 2.847 ms | 1 - 59 MB | FP16 | NPU | Use Export Script |
47
- | EfficientViT-b2-cls | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 2.86 ms | 1 - 60 MB | FP16 | NPU | [EfficientViT-b2-cls.onnx](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.onnx) |
48
- | EfficientViT-b2-cls | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 50.861 ms | 0 - 96 MB | FP16 | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
49
- | EfficientViT-b2-cls | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 51.6 ms | 1 - 10 MB | FP16 | NPU | Use Export Script |
50
- | EfficientViT-b2-cls | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 5.045 ms | 0 - 207 MB | FP16 | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
51
- | EfficientViT-b2-cls | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 5.25 ms | 1 - 4 MB | FP16 | NPU | Use Export Script |
52
- | EfficientViT-b2-cls | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 7.156 ms | 0 - 94 MB | FP16 | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
53
- | EfficientViT-b2-cls | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 7.718 ms | 1 - 10 MB | FP16 | NPU | Use Export Script |
54
- | EfficientViT-b2-cls | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 6.388 ms | 0 - 99 MB | FP16 | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
55
- | EfficientViT-b2-cls | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 6.287 ms | 1 - 63 MB | FP16 | NPU | Use Export Script |
56
- | EfficientViT-b2-cls | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 5.857 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
57
- | EfficientViT-b2-cls | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 6.152 ms | 50 - 50 MB | FP16 | NPU | [EfficientViT-b2-cls.onnx](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.onnx) |
58
 
59
 
60
 
@@ -116,12 +116,12 @@ python -m qai_hub_models.models.efficientvit_b2_cls.export
116
  Profiling Results
117
  ------------------------------------------------------------
118
  EfficientViT-b2-cls
119
- Device : Samsung Galaxy S23 (13)
120
- Runtime : TFLITE
121
- Estimated inference time (ms) : 5.1
122
- Estimated peak memory usage (MB): [0, 249]
123
- Total # Ops : 379
124
- Compute Unit(s) : NPU (379 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: 24M
35
+ - Model size (float): 200 MB
36
 
37
+ | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
+ | EfficientViT-b2-cls | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 12.101 ms | 0 - 95 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
40
+ | EfficientViT-b2-cls | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 12.643 ms | 1 - 10 MB | NPU | Use Export Script |
41
+ | EfficientViT-b2-cls | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 6.693 ms | 0 - 102 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
42
+ | EfficientViT-b2-cls | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 7.034 ms | 1 - 65 MB | NPU | Use Export Script |
43
+ | EfficientViT-b2-cls | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 5.024 ms | 3 - 251 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
44
+ | EfficientViT-b2-cls | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 5.233 ms | 1 - 4 MB | NPU | Use Export Script |
45
+ | EfficientViT-b2-cls | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 6.044 ms | 0 - 95 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
46
+ | EfficientViT-b2-cls | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 6.602 ms | 1 - 15 MB | NPU | Use Export Script |
47
+ | EfficientViT-b2-cls | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 5.067 ms | 0 - 249 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
48
+ | EfficientViT-b2-cls | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 5.194 ms | 1 - 17 MB | NPU | Use Export Script |
49
+ | EfficientViT-b2-cls | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 5.332 ms | 0 - 142 MB | NPU | [EfficientViT-b2-cls.onnx](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.onnx) |
50
+ | EfficientViT-b2-cls | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 3.46 ms | 0 - 110 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 | 3.689 ms | 1 - 73 MB | NPU | Use Export Script |
52
+ | EfficientViT-b2-cls | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 3.714 ms | 1 - 77 MB | NPU | [EfficientViT-b2-cls.onnx](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.onnx) |
53
+ | EfficientViT-b2-cls | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 3.342 ms | 0 - 97 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
54
+ | EfficientViT-b2-cls | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 2.685 ms | 1 - 60 MB | NPU | Use Export Script |
55
+ | EfficientViT-b2-cls | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 2.884 ms | 1 - 60 MB | NPU | [EfficientViT-b2-cls.onnx](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.onnx) |
56
+ | EfficientViT-b2-cls | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 5.882 ms | 1 - 1 MB | NPU | Use Export Script |
57
+ | EfficientViT-b2-cls | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 6.18 ms | 49 - 49 MB | NPU | [EfficientViT-b2-cls.onnx](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.onnx) |
58
 
59
 
60
 
 
116
  Profiling Results
117
  ------------------------------------------------------------
118
  EfficientViT-b2-cls
119
+ Device : cs_8275 (ANDROID 14)
120
+ Runtime : TFLITE
121
+ Estimated inference time (ms) : 12.1
122
+ Estimated peak memory usage (MB): [0, 95]
123
+ Total # Ops : 379
124
+ Compute Unit(s) : npu (379 ops) gpu (0 ops) cpu (0 ops)
125
  ```
126
 
127