Hugging Face's logo

qualcomm
/
FFNet-78S

Image Segmentation
PyTorch
LiteRT
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
cbf6b66
·
verified ·
1 Parent(s): e69d777

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +32 -28
README.md CHANGED
@@ -1,9 +1,9 @@
1
  ---
2
  library_name: pytorch
3
  license: bsd-3-clause
4
- pipeline_tag: image-segmentation
5
  tags:
6
  - android
 
7
 
8
  ---
9
 
@@ -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
- | FFNet-78S | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 50.784 ms | 2 - 32 MB | FP16 | NPU | [FFNet-78S.tflite](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.tflite) |
39
- | FFNet-78S | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 61.079 ms | 24 - 43 MB | FP16 | NPU | [FFNet-78S.so](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.so) |
40
- | FFNet-78S | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 39.841 ms | 5 - 166 MB | FP16 | NPU | [FFNet-78S.onnx](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.onnx) |
41
- | FFNet-78S | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 34.461 ms | 0 - 54 MB | FP16 | NPU | [FFNet-78S.tflite](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.tflite) |
42
- | FFNet-78S | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 41.668 ms | 24 - 67 MB | FP16 | NPU | [FFNet-78S.so](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.so) |
43
- | FFNet-78S | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 32.25 ms | 30 - 91 MB | FP16 | NPU | [FFNet-78S.onnx](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.onnx) |
44
- | FFNet-78S | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 27.435 ms | 1 - 55 MB | FP16 | NPU | [FFNet-78S.tflite](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.tflite) |
45
- | FFNet-78S | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 44.458 ms | 24 - 71 MB | FP16 | NPU | Use Export Script |
46
- | FFNet-78S | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 29.263 ms | 24 - 77 MB | FP16 | NPU | [FFNet-78S.onnx](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.onnx) |
47
- | FFNet-78S | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 50.816 ms | 2 - 27 MB | FP16 | NPU | [FFNet-78S.tflite](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.tflite) |
48
- | FFNet-78S | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 47.059 ms | 24 - 27 MB | FP16 | NPU | Use Export Script |
49
- | FFNet-78S | SA7255P ADP | SA7255P | TFLITE | 1255.948 ms | 0 - 51 MB | FP16 | NPU | [FFNet-78S.tflite](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.tflite) |
50
- | FFNet-78S | SA7255P ADP | SA7255P | QNN | 1243.805 ms | 24 - 32 MB | FP16 | NPU | Use Export Script |
51
- | FFNet-78S | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 50.912 ms | 2 - 34 MB | FP16 | NPU | [FFNet-78S.tflite](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.tflite) |
52
- | FFNet-78S | SA8255 (Proxy) | SA8255P Proxy | QNN | 47.189 ms | 24 - 27 MB | FP16 | NPU | Use Export Script |
53
- | FFNet-78S | SA8295P ADP | SA8295P | TFLITE | 78.897 ms | 2 - 49 MB | FP16 | NPU | [FFNet-78S.tflite](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.tflite) |
54
- | FFNet-78S | SA8295P ADP | SA8295P | QNN | 74.199 ms | 24 - 38 MB | FP16 | NPU | Use Export Script |
55
- | FFNet-78S | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 50.693 ms | 2 - 27 MB | FP16 | NPU | [FFNet-78S.tflite](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.tflite) |
56
- | FFNet-78S | SA8650 (Proxy) | SA8650P Proxy | QNN | 47.286 ms | 24 - 27 MB | FP16 | NPU | Use Export Script |
57
- | FFNet-78S | SA8775P ADP | SA8775P | TFLITE | 86.123 ms | 3 - 54 MB | FP16 | NPU | [FFNet-78S.tflite](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.tflite) |
58
- | FFNet-78S | SA8775P ADP | SA8775P | QNN | 78.836 ms | 24 - 34 MB | FP16 | NPU | Use Export Script |
59
- | FFNet-78S | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 68.773 ms | 2 - 48 MB | FP16 | NPU | [FFNet-78S.tflite](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.tflite) |
60
- | FFNet-78S | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 80.603 ms | 22 - 65 MB | FP16 | NPU | Use Export Script |
61
- | FFNet-78S | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 47.452 ms | 24 - 24 MB | FP16 | NPU | Use Export Script |
62
- | FFNet-78S | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 44.519 ms | 31 - 31 MB | FP16 | NPU | [FFNet-78S.onnx](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.onnx) |
 
 
 
 
63
 
64
 
65
 
@@ -123,8 +127,8 @@ Profiling Results
123
  FFNet-78S
124
  Device : Samsung Galaxy S23 (13)
125
  Runtime : TFLITE
126
- Estimated inference time (ms) : 50.8
127
- Estimated peak memory usage (MB): [2, 32]
128
  Total # Ops : 151
129
  Compute Unit(s) : NPU (151 ops)
130
  ```
 
1
  ---
2
  library_name: pytorch
3
  license: bsd-3-clause
 
4
  tags:
5
  - android
6
+ pipeline_tag: image-segmentation
7
 
8
  ---
9
 
 
35
 
36
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
+ | FFNet-78S | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 50.919 ms | 2 - 34 MB | FP16 | NPU | [FFNet-78S.tflite](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.tflite) |
39
+ | FFNet-78S | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 47.146 ms | 24 - 27 MB | FP16 | NPU | [FFNet-78S.so](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.so) |
40
+ | FFNet-78S | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 40.297 ms | 7 - 138 MB | FP16 | NPU | [FFNet-78S.onnx](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.onnx) |
41
+ | FFNet-78S | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 34.416 ms | 1 - 55 MB | FP16 | NPU | [FFNet-78S.tflite](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.tflite) |
42
+ | FFNet-78S | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 33.693 ms | 24 - 43 MB | FP16 | NPU | [FFNet-78S.so](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.so) |
43
+ | FFNet-78S | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 31.861 ms | 27 - 79 MB | FP16 | NPU | [FFNet-78S.onnx](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.onnx) |
44
+ | FFNet-78S | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 28.009 ms | 1 - 55 MB | FP16 | NPU | [FFNet-78S.tflite](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.tflite) |
45
+ | FFNet-78S | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 44.258 ms | 24 - 71 MB | FP16 | NPU | Use Export Script |
46
+ | FFNet-78S | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 29.717 ms | 24 - 77 MB | FP16 | NPU | [FFNet-78S.onnx](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.onnx) |
47
+ | FFNet-78S | SA7255P ADP | SA7255P | TFLITE | 1255.952 ms | 0 - 50 MB | FP16 | NPU | [FFNet-78S.tflite](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.tflite) |
48
+ | FFNet-78S | SA7255P ADP | SA7255P | QNN | 1243.803 ms | 24 - 31 MB | FP16 | NPU | Use Export Script |
49
+ | FFNet-78S | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 50.74 ms | 2 - 33 MB | FP16 | NPU | [FFNet-78S.tflite](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.tflite) |
50
+ | FFNet-78S | SA8255 (Proxy) | SA8255P Proxy | QNN | 47.605 ms | 24 - 27 MB | FP16 | NPU | Use Export Script |
51
+ | FFNet-78S | SA8295P ADP | SA8295P | TFLITE | 78.884 ms | 0 - 44 MB | FP16 | NPU | [FFNet-78S.tflite](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.tflite) |
52
+ | FFNet-78S | SA8295P ADP | SA8295P | QNN | 74.549 ms | 24 - 34 MB | FP16 | NPU | Use Export Script |
53
+ | FFNet-78S | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 51.089 ms | 2 - 34 MB | FP16 | NPU | [FFNet-78S.tflite](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.tflite) |
54
+ | FFNet-78S | SA8650 (Proxy) | SA8650P Proxy | QNN | 47.338 ms | 24 - 27 MB | FP16 | NPU | Use Export Script |
55
+ | FFNet-78S | SA8775P ADP | SA8775P | TFLITE | 86.124 ms | 2 - 53 MB | FP16 | NPU | [FFNet-78S.tflite](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.tflite) |
56
+ | FFNet-78S | SA8775P ADP | SA8775P | QNN | 78.869 ms | 24 - 32 MB | FP16 | NPU | Use Export Script |
57
+ | FFNet-78S | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 1255.952 ms | 0 - 50 MB | FP16 | NPU | [FFNet-78S.tflite](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.tflite) |
58
+ | FFNet-78S | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 1243.803 ms | 24 - 31 MB | FP16 | NPU | Use Export Script |
59
+ | FFNet-78S | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 51.017 ms | 2 - 35 MB | FP16 | NPU | [FFNet-78S.tflite](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.tflite) |
60
+ | FFNet-78S | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 47.139 ms | 24 - 27 MB | FP16 | NPU | Use Export Script |
61
+ | FFNet-78S | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 86.124 ms | 2 - 53 MB | FP16 | NPU | [FFNet-78S.tflite](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.tflite) |
62
+ | FFNet-78S | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 78.869 ms | 24 - 32 MB | FP16 | NPU | Use Export Script |
63
+ | FFNet-78S | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 68.993 ms | 2 - 48 MB | FP16 | NPU | [FFNet-78S.tflite](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.tflite) |
64
+ | FFNet-78S | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 80.197 ms | 24 - 62 MB | FP16 | NPU | Use Export Script |
65
+ | FFNet-78S | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 47.448 ms | 24 - 24 MB | FP16 | NPU | Use Export Script |
66
+ | FFNet-78S | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 44.497 ms | 32 - 32 MB | FP16 | NPU | [FFNet-78S.onnx](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.onnx) |
67
 
68
 
69
 
 
127
  FFNet-78S
128
  Device : Samsung Galaxy S23 (13)
129
  Runtime : TFLITE
130
+ Estimated inference time (ms) : 50.9
131
+ Estimated peak memory usage (MB): [2, 34]
132
  Total # Ops : 151
133
  Compute Unit(s) : NPU (151 ops)
134
  ```