Hugging Face's logo

qualcomm
/
ResNet101

Image Classification
PyTorch
LiteRT
ONNX
backbone
android
Model card Files Community
qaihm-bot commited on
Commit
6ae6d74
·
verified ·
1 Parent(s): 422d20f

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +31 -27
README.md CHANGED
@@ -1,10 +1,10 @@
1
  ---
2
  library_name: pytorch
3
  license: bsd-3-clause
4
- pipeline_tag: image-classification
5
  tags:
6
  - backbone
7
  - android
 
8
 
9
  ---
10
 
@@ -35,31 +35,35 @@ More details on model performance across various devices, can be found
35
 
36
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
- | ResNet101 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 3.372 ms | 0 - 200 MB | FP16 | NPU | [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite) |
39
- | ResNet101 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 3.468 ms | 0 - 190 MB | FP16 | NPU | [ResNet101.so](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.so) |
40
- | ResNet101 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 3.485 ms | 0 - 205 MB | FP16 | NPU | [ResNet101.onnx](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.onnx) |
41
- | ResNet101 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 2.424 ms | 0 - 35 MB | FP16 | NPU | [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite) |
42
- | ResNet101 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 2.491 ms | 1 - 40 MB | FP16 | NPU | [ResNet101.so](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.so) |
43
- | ResNet101 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 2.645 ms | 0 - 41 MB | FP16 | NPU | [ResNet101.onnx](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.onnx) |
44
- | ResNet101 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 2.351 ms | 0 - 37 MB | FP16 | NPU | [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite) |
45
- | ResNet101 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 2.4 ms | 1 - 36 MB | FP16 | NPU | Use Export Script |
46
- | ResNet101 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 2.543 ms | 1 - 36 MB | FP16 | NPU | [ResNet101.onnx](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.onnx) |
47
- | ResNet101 | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 3.363 ms | 0 - 290 MB | FP16 | NPU | [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite) |
48
- | ResNet101 | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 3.298 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
49
- | ResNet101 | SA7255P ADP | SA7255P | TFLITE | 135.271 ms | 0 - 32 MB | FP16 | NPU | [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite) |
50
- | ResNet101 | SA7255P ADP | SA7255P | QNN | 136.315 ms | 1 - 10 MB | FP16 | NPU | Use Export Script |
51
- | ResNet101 | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 3.383 ms | 0 - 260 MB | FP16 | NPU | [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite) |
52
- | ResNet101 | SA8255 (Proxy) | SA8255P Proxy | QNN | 3.317 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
53
- | ResNet101 | SA8295P ADP | SA8295P | TFLITE | 5.695 ms | 0 - 24 MB | FP16 | NPU | [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite) |
54
- | ResNet101 | SA8295P ADP | SA8295P | QNN | 5.9 ms | 1 - 15 MB | FP16 | NPU | Use Export Script |
55
- | ResNet101 | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 3.371 ms | 0 - 280 MB | FP16 | NPU | [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite) |
56
- | ResNet101 | SA8650 (Proxy) | SA8650P Proxy | QNN | 3.308 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
57
- | ResNet101 | SA8775P ADP | SA8775P | TFLITE | 6.632 ms | 0 - 32 MB | FP16 | NPU | [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite) |
58
- | ResNet101 | SA8775P ADP | SA8775P | QNN | 6.707 ms | 1 - 11 MB | FP16 | NPU | Use Export Script |
59
- | ResNet101 | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 4.734 ms | 0 - 27 MB | FP16 | NPU | [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite) |
60
- | ResNet101 | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 4.802 ms | 1 - 27 MB | FP16 | NPU | Use Export Script |
61
- | ResNet101 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 3.451 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
62
- | ResNet101 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 3.492 ms | 86 - 86 MB | FP16 | NPU | [ResNet101.onnx](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.onnx) |
 
 
 
 
63
 
64
 
65
 
@@ -124,7 +128,7 @@ ResNet101
124
  Device : Samsung Galaxy S23 (13)
125
  Runtime : TFLITE
126
  Estimated inference time (ms) : 3.4
127
- Estimated peak memory usage (MB): [0, 200]
128
  Total # Ops : 147
129
  Compute Unit(s) : NPU (147 ops)
130
  ```
 
1
  ---
2
  library_name: pytorch
3
  license: bsd-3-clause
 
4
  tags:
5
  - backbone
6
  - android
7
+ pipeline_tag: image-classification
8
 
9
  ---
10
 
 
35
 
36
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
+ | ResNet101 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 3.372 ms | 0 - 290 MB | FP16 | NPU | [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite) |
39
+ | ResNet101 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 3.289 ms | 1 - 3 MB | FP16 | NPU | [ResNet101.so](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.so) |
40
+ | ResNet101 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 3.537 ms | 0 - 237 MB | FP16 | NPU | [ResNet101.onnx](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.onnx) |
41
+ | ResNet101 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 2.419 ms | 0 - 37 MB | FP16 | NPU | [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite) |
42
+ | ResNet101 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 2.422 ms | 0 - 16 MB | FP16 | NPU | [ResNet101.so](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.so) |
43
+ | ResNet101 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 2.601 ms | 0 - 41 MB | FP16 | NPU | [ResNet101.onnx](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.onnx) |
44
+ | ResNet101 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 2.376 ms | 0 - 37 MB | FP16 | NPU | [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite) |
45
+ | ResNet101 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 2.405 ms | 1 - 35 MB | FP16 | NPU | Use Export Script |
46
+ | ResNet101 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 2.557 ms | 1 - 38 MB | FP16 | NPU | [ResNet101.onnx](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.onnx) |
47
+ | ResNet101 | SA7255P ADP | SA7255P | TFLITE | 135.244 ms | 0 - 31 MB | FP16 | NPU | [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite) |
48
+ | ResNet101 | SA7255P ADP | SA7255P | QNN | 136.309 ms | 1 - 8 MB | FP16 | NPU | Use Export Script |
49
+ | ResNet101 | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 3.402 ms | 0 - 285 MB | FP16 | NPU | [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite) |
50
+ | ResNet101 | SA8255 (Proxy) | SA8255P Proxy | QNN | 3.289 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
51
+ | ResNet101 | SA8295P ADP | SA8295P | TFLITE | 5.674 ms | 0 - 21 MB | FP16 | NPU | [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite) |
52
+ | ResNet101 | SA8295P ADP | SA8295P | QNN | 5.854 ms | 1 - 12 MB | FP16 | NPU | Use Export Script |
53
+ | ResNet101 | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 3.413 ms | 0 - 220 MB | FP16 | NPU | [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite) |
54
+ | ResNet101 | SA8650 (Proxy) | SA8650P Proxy | QNN | 3.29 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
55
+ | ResNet101 | SA8775P ADP | SA8775P | TFLITE | 6.611 ms | 0 - 31 MB | FP16 | NPU | [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite) |
56
+ | ResNet101 | SA8775P ADP | SA8775P | QNN | 6.724 ms | 1 - 8 MB | FP16 | NPU | Use Export Script |
57
+ | ResNet101 | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 135.244 ms | 0 - 31 MB | FP16 | NPU | [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite) |
58
+ | ResNet101 | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 136.309 ms | 1 - 8 MB | FP16 | NPU | Use Export Script |
59
+ | ResNet101 | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 3.384 ms | 0 - 290 MB | FP16 | NPU | [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite) |
60
+ | ResNet101 | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 3.291 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
61
+ | ResNet101 | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 6.611 ms | 0 - 31 MB | FP16 | NPU | [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite) |
62
+ | ResNet101 | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 6.724 ms | 1 - 8 MB | FP16 | NPU | Use Export Script |
63
+ | ResNet101 | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 4.74 ms | 0 - 28 MB | FP16 | NPU | [ResNet101.tflite](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.tflite) |
64
+ | ResNet101 | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 4.825 ms | 1 - 25 MB | FP16 | NPU | Use Export Script |
65
+ | ResNet101 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 3.444 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
66
+ | ResNet101 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 3.491 ms | 87 - 87 MB | FP16 | NPU | [ResNet101.onnx](https://huggingface.co/qualcomm/ResNet101/blob/main/ResNet101.onnx) |
67
 
68
 
69
 
 
128
  Device : Samsung Galaxy S23 (13)
129
  Runtime : TFLITE
130
  Estimated inference time (ms) : 3.4
131
+ Estimated peak memory usage (MB): [0, 290]
132
  Total # Ops : 147
133
  Compute Unit(s) : NPU (147 ops)
134
  ```