Hugging Face's logo

qualcomm
/
FFNet-54S

Image Segmentation
PyTorch
LiteRT
ONNX
android
Model card Files Community
qaihm-bot commited on
Commit
9ad0465
·
verified ·
1 Parent(s): 94d3a45

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +31 -31
README.md CHANGED
@@ -35,45 +35,44 @@ 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-54S | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 47.363 ms | 2 - 26 MB | FP16 | NPU | [FFNet-54S.tflite](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.tflite) |
39
- | FFNet-54S | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 57.655 ms | 24 - 39 MB | FP16 | NPU | [FFNet-54S.so](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.so) |
40
- | FFNet-54S | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 36.817 ms | 30 - 124 MB | FP16 | NPU | [FFNet-54S.onnx](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.onnx) |
41
- | FFNet-54S | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 31.641 ms | 1 - 51 MB | FP16 | NPU | [FFNet-54S.tflite](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.tflite) |
42
- | FFNet-54S | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 38.98 ms | 23 - 65 MB | FP16 | NPU | [FFNet-54S.so](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.so) |
43
- | FFNet-54S | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 26.357 ms | 28 - 78 MB | FP16 | NPU | [FFNet-54S.onnx](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.onnx) |
44
- | FFNet-54S | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 30.957 ms | 2 - 50 MB | FP16 | NPU | [FFNet-54S.tflite](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.tflite) |
45
- | FFNet-54S | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 34.57 ms | 24 - 69 MB | FP16 | NPU | Use Export Script |
46
- | FFNet-54S | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 26.233 ms | 27 - 74 MB | FP16 | NPU | [FFNet-54S.onnx](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.onnx) |
47
- | FFNet-54S | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 47.215 ms | 2 - 39 MB | FP16 | NPU | [FFNet-54S.tflite](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.tflite) |
48
- | FFNet-54S | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 43.73 ms | 24 - 28 MB | FP16 | NPU | Use Export Script |
49
- | FFNet-54S | SA7255P ADP | SA7255P | TFLITE | 1013.394 ms | 0 - 46 MB | FP16 | NPU | [FFNet-54S.tflite](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.tflite) |
50
- | FFNet-54S | SA7255P ADP | SA7255P | QNN | 1003.265 ms | 24 - 32 MB | FP16 | NPU | Use Export Script |
51
- | FFNet-54S | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 47.659 ms | 2 - 30 MB | FP16 | NPU | [FFNet-54S.tflite](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.tflite) |
52
- | FFNet-54S | SA8255 (Proxy) | SA8255P Proxy | QNN | 44.228 ms | 24 - 27 MB | FP16 | NPU | Use Export Script |
53
- | FFNet-54S | SA8295P ADP | SA8295P | TFLITE | 71.233 ms | 2 - 46 MB | FP16 | NPU | [FFNet-54S.tflite](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.tflite) |
54
- | FFNet-54S | SA8295P ADP | SA8295P | QNN | 69.467 ms | 24 - 38 MB | FP16 | NPU | Use Export Script |
55
- | FFNet-54S | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 47.196 ms | 2 - 26 MB | FP16 | NPU | [FFNet-54S.tflite](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.tflite) |
56
- | FFNet-54S | SA8650 (Proxy) | SA8650P Proxy | QNN | 44.316 ms | 24 - 27 MB | FP16 | NPU | Use Export Script |
57
- | FFNet-54S | SA8775P ADP | SA8775P | TFLITE | 77.496 ms | 2 - 49 MB | FP16 | NPU | [FFNet-54S.tflite](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.tflite) |
58
  | FFNet-54S | SA8775P ADP | SA8775P | QNN | 71.435 ms | 24 - 34 MB | FP16 | NPU | Use Export Script |
59
- | FFNet-54S | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 62.309 ms | 0 - 45 MB | FP16 | NPU | [FFNet-54S.tflite](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.tflite) |
60
- | FFNet-54S | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 72.426 ms | 24 - 63 MB | FP16 | NPU | Use Export Script |
61
- | FFNet-54S | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 44.545 ms | 24 - 24 MB | FP16 | NPU | Use Export Script |
62
- | FFNet-54S | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 40.897 ms | 24 - 24 MB | FP16 | NPU | [FFNet-54S.onnx](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.onnx) |
63
 
64
 
65
 
66
 
67
  ## Installation
68
 
69
- This model can be installed as a Python package via pip.
70
 
 
71
  ```bash
72
- pip install "qai-hub-models[ffnet_54s]"
73
  ```
74
 
75
 
76
-
77
  ## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
78
 
79
  Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
@@ -124,8 +123,8 @@ Profiling Results
124
  FFNet-54S
125
  Device : Samsung Galaxy S23 (13)
126
  Runtime : TFLITE
127
- Estimated inference time (ms) : 47.4
128
- Estimated peak memory usage (MB): [2, 26]
129
  Total # Ops : 115
130
  Compute Unit(s) : NPU (115 ops)
131
  ```
@@ -152,7 +151,7 @@ from qai_hub_models.models.ffnet_54s import Model
152
  torch_model = Model.from_pretrained()
153
 
154
  # Device
155
- device = hub.Device("Samsung Galaxy S23")
156
 
157
  # Trace model
158
  input_shape = torch_model.get_input_spec()
@@ -244,7 +243,8 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
244
 
245
 
246
  ## License
247
- * The license for the original implementation of FFNet-54S can be found [here](https://github.com/Qualcomm-AI-research/FFNet/blob/master/LICENSE).
 
248
  * The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)
249
 
250
 
 
35
 
36
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
+ | FFNet-54S | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 47.258 ms | 2 - 29 MB | FP16 | NPU | [FFNet-54S.tflite](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.tflite) |
39
+ | FFNet-54S | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 57.733 ms | 24 - 42 MB | FP16 | NPU | [FFNet-54S.so](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.so) |
40
+ | FFNet-54S | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 38.058 ms | 22 - 118 MB | FP16 | NPU | [FFNet-54S.onnx](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.onnx) |
41
+ | FFNet-54S | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 31.509 ms | 2 - 48 MB | FP16 | NPU | [FFNet-54S.tflite](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.tflite) |
42
+ | FFNet-54S | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 39.01 ms | 23 - 65 MB | FP16 | NPU | [FFNet-54S.so](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.so) |
43
+ | FFNet-54S | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 26.299 ms | 28 - 77 MB | FP16 | NPU | [FFNet-54S.onnx](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.onnx) |
44
+ | FFNet-54S | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 25.725 ms | 2 - 51 MB | FP16 | NPU | [FFNet-54S.tflite](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.tflite) |
45
+ | FFNet-54S | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 42.637 ms | 8 - 53 MB | FP16 | NPU | Use Export Script |
46
+ | FFNet-54S | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 26.684 ms | 26 - 71 MB | FP16 | NPU | [FFNet-54S.onnx](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.onnx) |
47
+ | FFNet-54S | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 47.297 ms | 2 - 21 MB | FP16 | NPU | [FFNet-54S.tflite](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.tflite) |
48
+ | FFNet-54S | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 44.317 ms | 24 - 27 MB | FP16 | NPU | Use Export Script |
49
+ | FFNet-54S | SA7255P ADP | SA7255P | TFLITE | 1013.284 ms | 0 - 46 MB | FP16 | NPU | [FFNet-54S.tflite](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.tflite) |
50
+ | FFNet-54S | SA7255P ADP | SA7255P | QNN | 1003.133 ms | 24 - 33 MB | FP16 | NPU | Use Export Script |
51
+ | FFNet-54S | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 47.314 ms | 2 - 37 MB | FP16 | NPU | [FFNet-54S.tflite](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.tflite) |
52
+ | FFNet-54S | SA8255 (Proxy) | SA8255P Proxy | QNN | 44.32 ms | 24 - 27 MB | FP16 | NPU | Use Export Script |
53
+ | FFNet-54S | SA8295P ADP | SA8295P | TFLITE | 71.213 ms | 2 - 47 MB | FP16 | NPU | [FFNet-54S.tflite](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.tflite) |
54
+ | FFNet-54S | SA8295P ADP | SA8295P | QNN | 69.328 ms | 24 - 38 MB | FP16 | NPU | Use Export Script |
55
+ | FFNet-54S | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 47.144 ms | 2 - 28 MB | FP16 | NPU | [FFNet-54S.tflite](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.tflite) |
56
+ | FFNet-54S | SA8650 (Proxy) | SA8650P Proxy | QNN | 43.988 ms | 24 - 27 MB | FP16 | NPU | Use Export Script |
57
+ | FFNet-54S | SA8775P ADP | SA8775P | TFLITE | 77.552 ms | 2 - 49 MB | FP16 | NPU | [FFNet-54S.tflite](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.tflite) |
58
  | FFNet-54S | SA8775P ADP | SA8775P | QNN | 71.435 ms | 24 - 34 MB | FP16 | NPU | Use Export Script |
59
+ | FFNet-54S | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 62.274 ms | 0 - 46 MB | FP16 | NPU | [FFNet-54S.tflite](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.tflite) |
60
+ | FFNet-54S | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 73.367 ms | 23 - 64 MB | FP16 | NPU | Use Export Script |
61
+ | FFNet-54S | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 44.689 ms | 24 - 24 MB | FP16 | NPU | Use Export Script |
62
+ | FFNet-54S | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 40.899 ms | 24 - 24 MB | FP16 | NPU | [FFNet-54S.onnx](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.onnx) |
63
 
64
 
65
 
66
 
67
  ## Installation
68
 
 
69
 
70
+ Install the package via pip:
71
  ```bash
72
+ pip install "qai-hub-models[ffnet-54s]"
73
  ```
74
 
75
 
 
76
  ## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
77
 
78
  Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
 
123
  FFNet-54S
124
  Device : Samsung Galaxy S23 (13)
125
  Runtime : TFLITE
126
+ Estimated inference time (ms) : 47.3
127
+ Estimated peak memory usage (MB): [2, 29]
128
  Total # Ops : 115
129
  Compute Unit(s) : NPU (115 ops)
130
  ```
 
151
  torch_model = Model.from_pretrained()
152
 
153
  # Device
154
+ device = hub.Device("Samsung Galaxy S24")
155
 
156
  # Trace model
157
  input_shape = torch_model.get_input_spec()
 
243
 
244
 
245
  ## License
246
+ * The license for the original implementation of FFNet-54S can be found
247
+ [here](https://github.com/Qualcomm-AI-research/FFNet/blob/master/LICENSE).
248
  * The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)
249
 
250