Hugging Face's logo

qualcomm
/
FFNet-78S-LowRes

Image Segmentation
PyTorch
real_time
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
d4e72cb
·
verified ·
1 Parent(s): d7edfd5

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +32 -32
README.md CHANGED
@@ -36,45 +36,44 @@ More details on model performance across various devices, can be found
36
 
37
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
- | FFNet-78S-LowRes | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 13.45 ms | 0 - 64 MB | FP16 | NPU | [FFNet-78S-LowRes.tflite](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.tflite) |
40
- | FFNet-78S-LowRes | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 14.517 ms | 6 - 34 MB | FP16 | NPU | [FFNet-78S-LowRes.so](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.so) |
41
- | FFNet-78S-LowRes | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 8.773 ms | 2 - 150 MB | FP16 | NPU | [FFNet-78S-LowRes.onnx](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.onnx) |
42
- | FFNet-78S-LowRes | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 9.178 ms | 0 - 30 MB | FP16 | NPU | [FFNet-78S-LowRes.tflite](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.tflite) |
43
- | FFNet-78S-LowRes | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 9.86 ms | 6 - 36 MB | FP16 | NPU | [FFNet-78S-LowRes.so](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.so) |
44
- | FFNet-78S-LowRes | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 6.653 ms | 8 - 54 MB | FP16 | NPU | [FFNet-78S-LowRes.onnx](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.onnx) |
45
- | FFNet-78S-LowRes | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 9.47 ms | 1 - 28 MB | FP16 | NPU | [FFNet-78S-LowRes.tflite](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.tflite) |
46
- | FFNet-78S-LowRes | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 8.678 ms | 6 - 32 MB | FP16 | NPU | Use Export Script |
47
- | FFNet-78S-LowRes | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 6.208 ms | 8 - 43 MB | FP16 | NPU | [FFNet-78S-LowRes.onnx](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.onnx) |
48
- | FFNet-78S-LowRes | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 13.45 ms | 0 - 64 MB | FP16 | NPU | [FFNet-78S-LowRes.tflite](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.tflite) |
49
- | FFNet-78S-LowRes | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 11.256 ms | 6 - 9 MB | FP16 | NPU | Use Export Script |
50
- | FFNet-78S-LowRes | SA7255P ADP | SA7255P | TFLITE | 297.162 ms | 0 - 24 MB | FP16 | NPU | [FFNet-78S-LowRes.tflite](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.tflite) |
51
- | FFNet-78S-LowRes | SA7255P ADP | SA7255P | QNN | 293.971 ms | 5 - 15 MB | FP16 | NPU | Use Export Script |
52
- | FFNet-78S-LowRes | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 13.426 ms | 0 - 74 MB | FP16 | NPU | [FFNet-78S-LowRes.tflite](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.tflite) |
53
- | FFNet-78S-LowRes | SA8255 (Proxy) | SA8255P Proxy | QNN | 11.372 ms | 6 - 9 MB | FP16 | NPU | Use Export Script |
54
- | FFNet-78S-LowRes | SA8295P ADP | SA8295P | TFLITE | 19.851 ms | 1 - 24 MB | FP16 | NPU | [FFNet-78S-LowRes.tflite](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.tflite) |
55
- | FFNet-78S-LowRes | SA8295P ADP | SA8295P | QNN | 18.361 ms | 0 - 14 MB | FP16 | NPU | Use Export Script |
56
- | FFNet-78S-LowRes | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 13.44 ms | 0 - 81 MB | FP16 | NPU | [FFNet-78S-LowRes.tflite](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.tflite) |
57
- | FFNet-78S-LowRes | SA8650 (Proxy) | SA8650P Proxy | QNN | 11.236 ms | 6 - 9 MB | FP16 | NPU | Use Export Script |
58
- | FFNet-78S-LowRes | SA8775P ADP | SA8775P | TFLITE | 22.181 ms | 1 - 24 MB | FP16 | NPU | [FFNet-78S-LowRes.tflite](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.tflite) |
59
- | FFNet-78S-LowRes | SA8775P ADP | SA8775P | QNN | 19.688 ms | 2 - 12 MB | FP16 | NPU | Use Export Script |
60
- | FFNet-78S-LowRes | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 16.869 ms | 1 - 29 MB | FP16 | NPU | [FFNet-78S-LowRes.tflite](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.tflite) |
61
- | FFNet-78S-LowRes | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 19.373 ms | 6 - 29 MB | FP16 | NPU | Use Export Script |
62
- | FFNet-78S-LowRes | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 11.79 ms | 6 - 6 MB | FP16 | NPU | Use Export Script |
63
- | FFNet-78S-LowRes | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 9.244 ms | 48 - 48 MB | FP16 | NPU | [FFNet-78S-LowRes.onnx](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.onnx) |
64
 
65
 
66
 
67
 
68
  ## Installation
69
 
70
- This model can be installed as a Python package via pip.
71
 
 
72
  ```bash
73
- pip install "qai-hub-models[ffnet_78s_lowres]"
74
  ```
75
 
76
 
77
-
78
  ## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
79
 
80
  Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
@@ -125,8 +124,8 @@ Profiling Results
125
  FFNet-78S-LowRes
126
  Device : Samsung Galaxy S23 (13)
127
  Runtime : TFLITE
128
- Estimated inference time (ms) : 13.4
129
- Estimated peak memory usage (MB): [0, 64]
130
  Total # Ops : 151
131
  Compute Unit(s) : NPU (151 ops)
132
  ```
@@ -153,7 +152,7 @@ from qai_hub_models.models.ffnet_78s_lowres import Model
153
  torch_model = Model.from_pretrained()
154
 
155
  # Device
156
- device = hub.Device("Samsung Galaxy S23")
157
 
158
  # Trace model
159
  input_shape = torch_model.get_input_spec()
@@ -245,7 +244,8 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
245
 
246
 
247
  ## License
248
- * The license for the original implementation of FFNet-78S-LowRes can be found [here](https://github.com/Qualcomm-AI-research/FFNet/blob/master/LICENSE).
 
249
  * 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)
250
 
251
 
 
36
 
37
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
+ | FFNet-78S-LowRes | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 13.542 ms | 0 - 74 MB | FP16 | NPU | [FFNet-78S-LowRes.tflite](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.tflite) |
40
+ | FFNet-78S-LowRes | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 14.49 ms | 6 - 30 MB | FP16 | NPU | [FFNet-78S-LowRes.so](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.so) |
41
+ | FFNet-78S-LowRes | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 8.737 ms | 2 - 155 MB | FP16 | NPU | [FFNet-78S-LowRes.onnx](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.onnx) |
42
+ | FFNet-78S-LowRes | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 9.178 ms | 0 - 32 MB | FP16 | NPU | [FFNet-78S-LowRes.tflite](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.tflite) |
43
+ | FFNet-78S-LowRes | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 9.881 ms | 6 - 34 MB | FP16 | NPU | [FFNet-78S-LowRes.so](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.so) |
44
+ | FFNet-78S-LowRes | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 6.193 ms | 6 - 50 MB | FP16 | NPU | [FFNet-78S-LowRes.onnx](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.onnx) |
45
+ | FFNet-78S-LowRes | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 9.49 ms | 1 - 28 MB | FP16 | NPU | [FFNet-78S-LowRes.tflite](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.tflite) |
46
+ | FFNet-78S-LowRes | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 8.494 ms | 6 - 32 MB | FP16 | NPU | Use Export Script |
47
+ | FFNet-78S-LowRes | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 6.079 ms | 8 - 43 MB | FP16 | NPU | [FFNet-78S-LowRes.onnx](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.onnx) |
48
+ | FFNet-78S-LowRes | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 13.546 ms | 0 - 83 MB | FP16 | NPU | [FFNet-78S-LowRes.tflite](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.tflite) |
49
+ | FFNet-78S-LowRes | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 11.385 ms | 6 - 9 MB | FP16 | NPU | Use Export Script |
50
+ | FFNet-78S-LowRes | SA7255P ADP | SA7255P | TFLITE | 297.228 ms | 1 - 23 MB | FP16 | NPU | [FFNet-78S-LowRes.tflite](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.tflite) |
51
+ | FFNet-78S-LowRes | SA7255P ADP | SA7255P | QNN | 293.848 ms | 4 - 13 MB | FP16 | NPU | Use Export Script |
52
+ | FFNet-78S-LowRes | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 13.469 ms | 0 - 73 MB | FP16 | NPU | [FFNet-78S-LowRes.tflite](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.tflite) |
53
+ | FFNet-78S-LowRes | SA8255 (Proxy) | SA8255P Proxy | QNN | 11.255 ms | 6 - 9 MB | FP16 | NPU | Use Export Script |
54
+ | FFNet-78S-LowRes | SA8295P ADP | SA8295P | TFLITE | 19.835 ms | 1 - 24 MB | FP16 | NPU | [FFNet-78S-LowRes.tflite](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.tflite) |
55
+ | FFNet-78S-LowRes | SA8295P ADP | SA8295P | QNN | 18.353 ms | 0 - 15 MB | FP16 | NPU | Use Export Script |
56
+ | FFNet-78S-LowRes | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 13.447 ms | 0 - 54 MB | FP16 | NPU | [FFNet-78S-LowRes.tflite](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.tflite) |
57
+ | FFNet-78S-LowRes | SA8650 (Proxy) | SA8650P Proxy | QNN | 11.247 ms | 6 - 9 MB | FP16 | NPU | Use Export Script |
58
+ | FFNet-78S-LowRes | SA8775P ADP | SA8775P | TFLITE | 22.218 ms | 1 - 24 MB | FP16 | NPU | [FFNet-78S-LowRes.tflite](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.tflite) |
59
+ | FFNet-78S-LowRes | SA8775P ADP | SA8775P | QNN | 19.757 ms | 2 - 12 MB | FP16 | NPU | Use Export Script |
60
+ | FFNet-78S-LowRes | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 16.944 ms | 1 - 27 MB | FP16 | NPU | [FFNet-78S-LowRes.tflite](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.tflite) |
61
+ | FFNet-78S-LowRes | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 19.731 ms | 6 - 26 MB | FP16 | NPU | Use Export Script |
62
+ | FFNet-78S-LowRes | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 11.846 ms | 6 - 6 MB | FP16 | NPU | Use Export Script |
63
+ | FFNet-78S-LowRes | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 9.251 ms | 48 - 48 MB | FP16 | NPU | [FFNet-78S-LowRes.onnx](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.onnx) |
64
 
65
 
66
 
67
 
68
  ## Installation
69
 
 
70
 
71
+ Install the package via pip:
72
  ```bash
73
+ pip install "qai-hub-models[ffnet-78s-lowres]"
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
  FFNet-78S-LowRes
125
  Device : Samsung Galaxy S23 (13)
126
  Runtime : TFLITE
127
+ Estimated inference time (ms) : 13.5
128
+ Estimated peak memory usage (MB): [0, 74]
129
  Total # Ops : 151
130
  Compute Unit(s) : NPU (151 ops)
131
  ```
 
152
  torch_model = Model.from_pretrained()
153
 
154
  # Device
155
+ device = hub.Device("Samsung Galaxy S24")
156
 
157
  # Trace model
158
  input_shape = torch_model.get_input_spec()
 
244
 
245
 
246
  ## License
247
+ * The license for the original implementation of FFNet-78S-LowRes can be found
248
+ [here](https://github.com/Qualcomm-AI-research/FFNet/blob/master/LICENSE).
249
  * 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)
250
 
251