Hugging Face's logo

qualcomm
/
VIT

Image Classification
PyTorch
backbone
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
acf87bd
·
verified ·
1 Parent(s): 6c96959

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +14 -16
README.md CHANGED
@@ -1,7 +1,4 @@
1
  ---
2
- datasets:
3
- - imagenet-1k
4
- - imagenet-22k
5
  library_name: pytorch
6
  license: bsd-3-clause
7
  pipeline_tag: image-classification
@@ -38,18 +35,19 @@ More details on model performance across various devices, can be found
38
 
39
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
40
  |---|---|---|---|---|---|---|---|---|
41
- | VIT | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 19.821 ms | 0 - 3 MB | FP16 | NPU | [VIT.tflite](https://huggingface.co/qualcomm/VIT/blob/main/VIT.tflite) |
42
- | VIT | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 15.505 ms | 0 - 193 MB | FP16 | NPU | [VIT.onnx](https://huggingface.co/qualcomm/VIT/blob/main/VIT.onnx) |
43
- | VIT | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 16.903 ms | 0 - 382 MB | FP16 | NPU | [VIT.tflite](https://huggingface.co/qualcomm/VIT/blob/main/VIT.tflite) |
44
- | VIT | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 11.372 ms | 0 - 149 MB | FP16 | NPU | [VIT.onnx](https://huggingface.co/qualcomm/VIT/blob/main/VIT.onnx) |
45
- | VIT | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 19.788 ms | 0 - 3 MB | FP16 | NPU | [VIT.tflite](https://huggingface.co/qualcomm/VIT/blob/main/VIT.tflite) |
46
- | VIT | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 19.83 ms | 0 - 3 MB | FP16 | NPU | [VIT.tflite](https://huggingface.co/qualcomm/VIT/blob/main/VIT.tflite) |
47
- | VIT | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 20.031 ms | 0 - 3 MB | FP16 | NPU | [VIT.tflite](https://huggingface.co/qualcomm/VIT/blob/main/VIT.tflite) |
48
- | VIT | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 20.358 ms | 0 - 3 MB | FP16 | NPU | [VIT.tflite](https://huggingface.co/qualcomm/VIT/blob/main/VIT.tflite) |
49
- | VIT | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 24.972 ms | 0 - 368 MB | FP16 | NPU | [VIT.tflite](https://huggingface.co/qualcomm/VIT/blob/main/VIT.tflite) |
50
- | VIT | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 11.489 ms | 0 - 207 MB | FP16 | NPU | [VIT.tflite](https://huggingface.co/qualcomm/VIT/blob/main/VIT.tflite) |
51
- | VIT | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 9.01 ms | 1 - 112 MB | FP16 | NPU | [VIT.onnx](https://huggingface.co/qualcomm/VIT/blob/main/VIT.onnx) |
52
- | VIT | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 21.624 ms | 171 - 171 MB | FP16 | NPU | [VIT.onnx](https://huggingface.co/qualcomm/VIT/blob/main/VIT.onnx) |
 
53
 
54
 
55
 
@@ -113,7 +111,7 @@ Profiling Results
113
  VIT
114
  Device : Samsung Galaxy S23 (13)
115
  Runtime : TFLITE
116
- Estimated inference time (ms) : 19.8
117
  Estimated peak memory usage (MB): [0, 3]
118
  Total # Ops : 1579
119
  Compute Unit(s) : NPU (1579 ops)
 
1
  ---
 
 
 
2
  library_name: pytorch
3
  license: bsd-3-clause
4
  pipeline_tag: image-classification
 
35
 
36
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
+ | VIT | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 20.389 ms | 0 - 3 MB | FP16 | NPU | [VIT.tflite](https://huggingface.co/qualcomm/VIT/blob/main/VIT.tflite) |
39
+ | VIT | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 15.365 ms | 0 - 193 MB | FP16 | NPU | [VIT.onnx](https://huggingface.co/qualcomm/VIT/blob/main/VIT.onnx) |
40
+ | VIT | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 14.533 ms | 0 - 384 MB | FP16 | NPU | [VIT.tflite](https://huggingface.co/qualcomm/VIT/blob/main/VIT.tflite) |
41
+ | VIT | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 11.082 ms | 1 - 149 MB | FP16 | NPU | [VIT.onnx](https://huggingface.co/qualcomm/VIT/blob/main/VIT.onnx) |
42
+ | VIT | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 13.463 ms | 0 - 207 MB | FP16 | NPU | [VIT.tflite](https://huggingface.co/qualcomm/VIT/blob/main/VIT.tflite) |
43
+ | VIT | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 10.643 ms | 0 - 112 MB | FP16 | NPU | [VIT.onnx](https://huggingface.co/qualcomm/VIT/blob/main/VIT.onnx) |
44
+ | VIT | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 20.185 ms | 0 - 3 MB | FP16 | NPU | [VIT.tflite](https://huggingface.co/qualcomm/VIT/blob/main/VIT.tflite) |
45
+ | VIT | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 19.972 ms | 0 - 3 MB | FP16 | NPU | [VIT.tflite](https://huggingface.co/qualcomm/VIT/blob/main/VIT.tflite) |
46
+ | VIT | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 19.912 ms | 0 - 3 MB | FP16 | NPU | [VIT.tflite](https://huggingface.co/qualcomm/VIT/blob/main/VIT.tflite) |
47
+ | VIT | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 20.015 ms | 0 - 3 MB | FP16 | NPU | [VIT.tflite](https://huggingface.co/qualcomm/VIT/blob/main/VIT.tflite) |
48
+ | VIT | SA8295P ADP | SA8295P | TFLITE | 28.052 ms | 0 - 193 MB | FP16 | NPU | [VIT.tflite](https://huggingface.co/qualcomm/VIT/blob/main/VIT.tflite) |
49
+ | VIT | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 25.082 ms | 0 - 367 MB | FP16 | NPU | [VIT.tflite](https://huggingface.co/qualcomm/VIT/blob/main/VIT.tflite) |
50
+ | VIT | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 21.681 ms | 171 - 171 MB | FP16 | NPU | [VIT.onnx](https://huggingface.co/qualcomm/VIT/blob/main/VIT.onnx) |
51
 
52
 
53
 
 
111
  VIT
112
  Device : Samsung Galaxy S23 (13)
113
  Runtime : TFLITE
114
+ Estimated inference time (ms) : 20.4
115
  Estimated peak memory usage (MB): [0, 3]
116
  Total # Ops : 1579
117
  Compute Unit(s) : NPU (1579 ops)