Hugging Face's logo

qualcomm
/
ConvNext-Tiny

Image Classification
PyTorch
LiteRT
bu_auto
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
0c89961
·
verified ·
1 Parent(s): efeefb9

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +58 -39
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  library_name: pytorch
3
- license: bsd-3-clause
4
  tags:
5
  - android
6
  pipeline_tag: image-classification
@@ -25,44 +25,63 @@ 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: Imagenet
31
  - Input resolution: 224x224
32
  - Number of parameters: 28.6M
33
- - Model size: 109 MB
 
34
 
35
- | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
36
  |---|---|---|---|---|---|---|---|---|
37
- | ConvNext-Tiny | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 3.022 ms | 0 - 445 MB | FP16 | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
38
- | ConvNext-Tiny | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 3.361 ms | 0 - 421 MB | FP16 | NPU | [ConvNext-Tiny.so](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.so) |
39
- | ConvNext-Tiny | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 2.977 ms | 0 - 190 MB | FP16 | NPU | [ConvNext-Tiny.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.onnx) |
40
- | ConvNext-Tiny | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 2.282 ms | 0 - 103 MB | FP16 | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
41
- | ConvNext-Tiny | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 2.487 ms | 1 - 99 MB | FP16 | NPU | [ConvNext-Tiny.so](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.so) |
42
- | ConvNext-Tiny | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 2.184 ms | 0 - 101 MB | FP16 | NPU | [ConvNext-Tiny.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.onnx) |
43
- | ConvNext-Tiny | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 1.696 ms | 0 - 95 MB | FP16 | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
44
- | ConvNext-Tiny | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 1.945 ms | 0 - 95 MB | FP16 | NPU | Use Export Script |
45
- | ConvNext-Tiny | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 1.773 ms | 1 - 96 MB | FP16 | NPU | [ConvNext-Tiny.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.onnx) |
46
- | ConvNext-Tiny | SA7255P ADP | SA7255P | TFLITE | 96.237 ms | 0 - 92 MB | FP16 | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
47
- | ConvNext-Tiny | SA7255P ADP | SA7255P | QNN | 96.72 ms | 1 - 10 MB | FP16 | NPU | Use Export Script |
48
- | ConvNext-Tiny | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 3.033 ms | 0 - 438 MB | FP16 | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
49
- | ConvNext-Tiny | SA8255 (Proxy) | SA8255P Proxy | QNN | 3.352 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
50
- | ConvNext-Tiny | SA8295P ADP | SA8295P | TFLITE | 8.99 ms | 0 - 94 MB | FP16 | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
51
- | ConvNext-Tiny | SA8295P ADP | SA8295P | QNN | 9.209 ms | 1 - 18 MB | FP16 | NPU | Use Export Script |
52
- | ConvNext-Tiny | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 3.02 ms | 0 - 450 MB | FP16 | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
53
- | ConvNext-Tiny | SA8650 (Proxy) | SA8650P Proxy | QNN | 3.333 ms | 1 - 12 MB | FP16 | NPU | Use Export Script |
54
- | ConvNext-Tiny | SA8775P ADP | SA8775P | TFLITE | 5.198 ms | 0 - 92 MB | FP16 | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
55
- | ConvNext-Tiny | SA8775P ADP | SA8775P | QNN | 5.542 ms | 1 - 10 MB | FP16 | NPU | Use Export Script |
56
- | ConvNext-Tiny | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 96.237 ms | 0 - 92 MB | FP16 | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
57
- | ConvNext-Tiny | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 96.72 ms | 1 - 10 MB | FP16 | NPU | Use Export Script |
58
- | ConvNext-Tiny | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 3.023 ms | 0 - 449 MB | FP16 | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
59
- | ConvNext-Tiny | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 3.333 ms | 1 - 4 MB | FP16 | NPU | Use Export Script |
60
- | ConvNext-Tiny | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 5.198 ms | 0 - 92 MB | FP16 | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
61
- | ConvNext-Tiny | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 5.542 ms | 1 - 10 MB | FP16 | NPU | Use Export Script |
62
- | ConvNext-Tiny | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 8.24 ms | 0 - 103 MB | FP16 | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
63
- | ConvNext-Tiny | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 8.398 ms | 1 - 103 MB | FP16 | NPU | Use Export Script |
64
- | ConvNext-Tiny | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 3.496 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
65
- | ConvNext-Tiny | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 3.062 ms | 57 - 57 MB | FP16 | NPU | [ConvNext-Tiny.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.onnx) |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
66
 
67
 
68
 
@@ -124,12 +143,12 @@ python -m qai_hub_models.models.convnext_tiny.export
124
  Profiling Results
125
  ------------------------------------------------------------
126
  ConvNext-Tiny
127
- Device : Samsung Galaxy S23 (13)
128
- Runtime : TFLITE
129
- Estimated inference time (ms) : 3.0
130
- Estimated peak memory usage (MB): [0, 445]
131
- Total # Ops : 328
132
- Compute Unit(s) : NPU (328 ops)
133
  ```
134
 
135
 
 
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: Imagenet
31
  - Input resolution: 224x224
32
  - Number of parameters: 28.6M
33
+ - Model size (float): 109 MB
34
+ - Model size (w8a16): 28 MB
35
 
36
+ | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
+ | ConvNext-Tiny | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 14.23 ms | 0 - 91 MB | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
39
+ | ConvNext-Tiny | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 14.666 ms | 1 - 10 MB | NPU | Use Export Script |
40
+ | ConvNext-Tiny | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 8.208 ms | 0 - 102 MB | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
41
+ | ConvNext-Tiny | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 10.081 ms | 1 - 104 MB | NPU | Use Export Script |
42
+ | ConvNext-Tiny | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 3.021 ms | 0 - 450 MB | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
43
+ | ConvNext-Tiny | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 3.35 ms | 1 - 3 MB | NPU | Use Export Script |
44
+ | ConvNext-Tiny | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 4.36 ms | 0 - 92 MB | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
45
+ | ConvNext-Tiny | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 4.614 ms | 1 - 12 MB | NPU | Use Export Script |
46
+ | ConvNext-Tiny | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 14.23 ms | 0 - 91 MB | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
47
+ | ConvNext-Tiny | float | SA7255P ADP | Qualcomm® SA7255P | QNN | 14.666 ms | 1 - 10 MB | NPU | Use Export Script |
48
+ | ConvNext-Tiny | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 3.02 ms | 0 - 438 MB | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
49
+ | ConvNext-Tiny | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 3.33 ms | 1 - 2 MB | NPU | Use Export Script |
50
+ | ConvNext-Tiny | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 8.978 ms | 0 - 92 MB | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
51
+ | ConvNext-Tiny | float | SA8295P ADP | Qualcomm® SA8295P | QNN | 9.162 ms | 1 - 17 MB | NPU | Use Export Script |
52
+ | ConvNext-Tiny | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 3.021 ms | 0 - 443 MB | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
53
+ | ConvNext-Tiny | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 3.314 ms | 1 - 4 MB | NPU | Use Export Script |
54
+ | ConvNext-Tiny | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 4.36 ms | 0 - 92 MB | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
55
+ | ConvNext-Tiny | float | SA8775P ADP | Qualcomm® SA8775P | QNN | 4.614 ms | 1 - 12 MB | NPU | Use Export Script |
56
+ | ConvNext-Tiny | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 3.062 ms | 0 - 432 MB | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
57
+ | ConvNext-Tiny | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 3.334 ms | 0 - 14 MB | NPU | Use Export Script |
58
+ | ConvNext-Tiny | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 3.065 ms | 0 - 191 MB | NPU | [ConvNext-Tiny.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.onnx) |
59
+ | ConvNext-Tiny | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 2.274 ms | 0 - 97 MB | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
60
+ | ConvNext-Tiny | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 2.386 ms | 0 - 100 MB | NPU | Use Export Script |
61
+ | ConvNext-Tiny | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 2.234 ms | 0 - 103 MB | NPU | [ConvNext-Tiny.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.onnx) |
62
+ | ConvNext-Tiny | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 1.699 ms | 0 - 95 MB | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
63
+ | ConvNext-Tiny | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 2.063 ms | 0 - 96 MB | NPU | Use Export Script |
64
+ | ConvNext-Tiny | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 1.958 ms | 1 - 98 MB | NPU | [ConvNext-Tiny.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.onnx) |
65
+ | ConvNext-Tiny | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 3.514 ms | 1 - 1 MB | NPU | Use Export Script |
66
+ | ConvNext-Tiny | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 3.108 ms | 57 - 57 MB | NPU | [ConvNext-Tiny.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.onnx) |
67
+ | ConvNext-Tiny | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 6.91 ms | 0 - 10 MB | NPU | Use Export Script |
68
+ | ConvNext-Tiny | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 4.582 ms | 0 - 64 MB | NPU | Use Export Script |
69
+ | ConvNext-Tiny | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 3.195 ms | 0 - 2 MB | NPU | Use Export Script |
70
+ | ConvNext-Tiny | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 3.484 ms | 0 - 13 MB | NPU | Use Export Script |
71
+ | ConvNext-Tiny | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN | 12.574 ms | 0 - 12 MB | NPU | Use Export Script |
72
+ | ConvNext-Tiny | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN | 6.91 ms | 0 - 10 MB | NPU | Use Export Script |
73
+ | ConvNext-Tiny | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 3.187 ms | 0 - 2 MB | NPU | Use Export Script |
74
+ | ConvNext-Tiny | w8a16 | SA8295P ADP | Qualcomm® SA8295P | QNN | 4.778 ms | 0 - 18 MB | NPU | Use Export Script |
75
+ | ConvNext-Tiny | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 3.175 ms | 0 - 3 MB | NPU | Use Export Script |
76
+ | ConvNext-Tiny | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN | 3.484 ms | 0 - 13 MB | NPU | Use Export Script |
77
+ | ConvNext-Tiny | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 3.182 ms | 0 - 16 MB | NPU | Use Export Script |
78
+ | ConvNext-Tiny | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 83.113 ms | 208 - 340 MB | NPU | [ConvNext-Tiny.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny_w8a16.onnx) |
79
+ | ConvNext-Tiny | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 2.214 ms | 0 - 64 MB | NPU | Use Export Script |
80
+ | ConvNext-Tiny | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 75.889 ms | 218 - 552 MB | NPU | [ConvNext-Tiny.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny_w8a16.onnx) |
81
+ | ConvNext-Tiny | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 1.819 ms | 0 - 58 MB | NPU | Use Export Script |
82
+ | ConvNext-Tiny | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 70.084 ms | 200 - 501 MB | NPU | [ConvNext-Tiny.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny_w8a16.onnx) |
83
+ | ConvNext-Tiny | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 3.436 ms | 0 - 0 MB | NPU | Use Export Script |
84
+ | ConvNext-Tiny | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 89.298 ms | 231 - 231 MB | NPU | [ConvNext-Tiny.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny_w8a16.onnx) |
85
 
86
 
87
 
 
143
  Profiling Results
144
  ------------------------------------------------------------
145
  ConvNext-Tiny
146
+ Device : cs_8275 (ANDROID 14)
147
+ Runtime : TFLITE
148
+ Estimated inference time (ms) : 14.2
149
+ Estimated peak memory usage (MB): [0, 91]
150
+ Total # Ops : 328
151
+ Compute Unit(s) : npu (328 ops) gpu (0 ops) cpu (0 ops)
152
  ```
153
 
154