Hugging Face's logo

qualcomm
/
LeViT

Image Classification
PyTorch
bu_auto
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
18a7a5b
·
verified ·
1 Parent(s): 52b96dd

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +24 -20
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  library_name: pytorch
3
- license: apache-2.0
4
  tags:
5
  - android
6
  pipeline_tag: image-classification
@@ -25,26 +25,30 @@ More details on model performance across various devices, can be found
25
 
26
  ### Model Details
27
 
28
- - **Model Type:** Image classification
29
  - **Model Stats:**
30
  - Model checkpoint: LeViT-128S
31
  - Input resolution: 224x224
32
  - Number of parameters: 7.82M
33
  - Model size: 29.9 MB
34
 
35
- | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
36
  |---|---|---|---|---|---|---|---|---|
37
- | LeViT | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 1.089 ms | 0 - 76 MB | FP16 | NPU | [LeViT.tflite](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.tflite) |
38
- | LeViT | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 1.648 ms | 0 - 50 MB | FP16 | NPU | [LeViT.onnx](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.onnx) |
39
- | LeViT | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.801 ms | 0 - 46 MB | FP16 | NPU | [LeViT.tflite](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.tflite) |
40
- | LeViT | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 1.128 ms | 0 - 49 MB | FP16 | NPU | [LeViT.onnx](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.onnx) |
41
- | LeViT | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.752 ms | 0 - 41 MB | FP16 | NPU | [LeViT.tflite](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.tflite) |
42
- | LeViT | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 1.2 ms | 1 - 44 MB | FP16 | NPU | [LeViT.onnx](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.onnx) |
43
- | LeViT | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 13.659 ms | 0 - 37 MB | FP16 | NPU | [LeViT.tflite](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.tflite) |
44
- | LeViT | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 1.098 ms | 0 - 73 MB | FP16 | NPU | [LeViT.tflite](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.tflite) |
45
- | LeViT | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 1.853 ms | 0 - 37 MB | FP16 | NPU | [LeViT.tflite](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.tflite) |
46
- | LeViT | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 1.459 ms | 0 - 47 MB | FP16 | NPU | [LeViT.tflite](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.tflite) |
47
- | LeViT | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 1.729 ms | 16 - 16 MB | FP16 | NPU | [LeViT.onnx](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.onnx) |
 
 
 
 
48
 
49
 
50
 
@@ -106,12 +110,12 @@ python -m qai_hub_models.models.levit.export
106
  Profiling Results
107
  ------------------------------------------------------------
108
  LeViT
109
- Device : Samsung Galaxy S23 (13)
110
- Runtime : TFLITE
111
- Estimated inference time (ms) : 1.1
112
- Estimated peak memory usage (MB): [0, 76]
113
- Total # Ops : 306
114
- Compute Unit(s) : NPU (306 ops)
115
  ```
116
 
117
 
 
1
  ---
2
  library_name: pytorch
3
+ license: other
4
  tags:
5
  - android
6
  pipeline_tag: image-classification
 
25
 
26
  ### Model Details
27
 
28
+ - **Model Type:** Model_use_case.image_classification
29
  - **Model Stats:**
30
  - Model checkpoint: LeViT-128S
31
  - Input resolution: 224x224
32
  - Number of parameters: 7.82M
33
  - Model size: 29.9 MB
34
 
35
+ | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
36
  |---|---|---|---|---|---|---|---|---|
37
+ | LeViT | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 3.301 ms | 0 - 36 MB | NPU | [LeViT.tflite](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.tflite) |
38
+ | LeViT | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 1.492 ms | 0 - 48 MB | NPU | [LeViT.tflite](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.tflite) |
39
+ | LeViT | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 1.091 ms | 0 - 71 MB | NPU | [LeViT.tflite](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.tflite) |
40
+ | LeViT | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 1.582 ms | 0 - 39 MB | NPU | [LeViT.tflite](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.tflite) |
41
+ | LeViT | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 1.096 ms | 0 - 75 MB | NPU | [LeViT.tflite](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.tflite) |
42
+ | LeViT | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 1.658 ms | 0 - 44 MB | NPU | [LeViT.onnx](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.onnx) |
43
+ | LeViT | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 0.789 ms | 0 - 47 MB | NPU | [LeViT.tflite](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.tflite) |
44
+ | LeViT | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 1.103 ms | 0 - 53 MB | NPU | [LeViT.onnx](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.onnx) |
45
+ | LeViT | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 0.754 ms | 0 - 41 MB | NPU | [LeViT.tflite](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.tflite) |
46
+ | LeViT | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 1.178 ms | 1 - 44 MB | NPU | [LeViT.onnx](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.onnx) |
47
+ | LeViT | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 1.721 ms | 16 - 16 MB | NPU | [LeViT.onnx](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.onnx) |
48
+ | LeViT | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 16.085 ms | 2 - 18 MB | NPU | [LeViT.onnx](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT_w8a16.onnx) |
49
+ | LeViT | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 14.021 ms | 0 - 25 MB | NPU | [LeViT.onnx](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT_w8a16.onnx) |
50
+ | LeViT | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 13.415 ms | 0 - 23 MB | NPU | [LeViT.onnx](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT_w8a16.onnx) |
51
+ | LeViT | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 16.213 ms | 8 - 8 MB | NPU | [LeViT.onnx](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT_w8a16.onnx) |
52
 
53
 
54
 
 
110
  Profiling Results
111
  ------------------------------------------------------------
112
  LeViT
113
+ Device : cs_8275 (ANDROID 14)
114
+ Runtime : TFLITE
115
+ Estimated inference time (ms) : 3.3
116
+ Estimated peak memory usage (MB): [0, 36]
117
+ Total # Ops : 306
118
+ Compute Unit(s) : npu (306 ops) gpu (0 ops) cpu (0 ops)
119
  ```
120
 
121