Hugging Face's logo

qualcomm
/
FastSam-X

Image Segmentation
PyTorch
TF Lite
ONNX
android
Model card Files Community
qaihm-bot commited on
Commit
396f835
·
verified ·
1 Parent(s): accd274

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +32 -32
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
- | FastSam-X | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 44.074 ms | 2 - 52 MB | FP16 | NPU | [FastSam-X.tflite](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.tflite) |
39
- | FastSam-X | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 44.877 ms | 5 - 20 MB | FP16 | NPU | [FastSam-X.so](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.so) |
40
- | FastSam-X | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 47.005 ms | 0 - 311 MB | FP16 | NPU | [FastSam-X.onnx](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.onnx) |
41
- | FastSam-X | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 35.035 ms | 3 - 63 MB | FP16 | NPU | [FastSam-X.tflite](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.tflite) |
42
- | FastSam-X | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 35.147 ms | 5 - 65 MB | FP16 | NPU | [FastSam-X.so](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.so) |
43
- | FastSam-X | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 34.912 ms | 12 - 72 MB | FP16 | NPU | [FastSam-X.onnx](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.onnx) |
44
- | FastSam-X | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 30.623 ms | 3 - 63 MB | FP16 | NPU | [FastSam-X.tflite](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.tflite) |
45
- | FastSam-X | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 30.562 ms | 5 - 64 MB | FP16 | NPU | Use Export Script |
46
- | FastSam-X | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 32.508 ms | 17 - 73 MB | FP16 | NPU | [FastSam-X.onnx](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.onnx) |
47
- | FastSam-X | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 46.23 ms | 4 - 56 MB | FP16 | NPU | [FastSam-X.tflite](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.tflite) |
48
- | FastSam-X | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 43.53 ms | 5 - 7 MB | FP16 | NPU | Use Export Script |
49
- | FastSam-X | SA7255P ADP | SA7255P | TFLITE | 2097.68 ms | 0 - 60 MB | FP16 | NPU | [FastSam-X.tflite](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.tflite) |
50
- | FastSam-X | SA7255P ADP | SA7255P | QNN | 2095.625 ms | 2 - 12 MB | FP16 | NPU | Use Export Script |
51
- | FastSam-X | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 46.582 ms | 4 - 52 MB | FP16 | NPU | [FastSam-X.tflite](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.tflite) |
52
- | FastSam-X | SA8255 (Proxy) | SA8255P Proxy | QNN | 44.361 ms | 5 - 7 MB | FP16 | NPU | Use Export Script |
53
- | FastSam-X | SA8295P ADP | SA8295P | TFLITE | 93.97 ms | 4 - 60 MB | FP16 | NPU | [FastSam-X.tflite](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.tflite) |
54
- | FastSam-X | SA8295P ADP | SA8295P | QNN | 83.006 ms | 0 - 14 MB | FP16 | NPU | Use Export Script |
55
- | FastSam-X | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 48.788 ms | 4 - 57 MB | FP16 | NPU | [FastSam-X.tflite](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.tflite) |
56
- | FastSam-X | SA8650 (Proxy) | SA8650P Proxy | QNN | 43.511 ms | 5 - 7 MB | FP16 | NPU | Use Export Script |
57
- | FastSam-X | SA8775P ADP | SA8775P | TFLITE | 87.601 ms | 4 - 64 MB | FP16 | NPU | [FastSam-X.tflite](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.tflite) |
58
- | FastSam-X | SA8775P ADP | SA8775P | QNN | 85.621 ms | 2 - 12 MB | FP16 | NPU | Use Export Script |
59
- | FastSam-X | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 90.872 ms | 4 - 65 MB | FP16 | NPU | [FastSam-X.tflite](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.tflite) |
60
- | FastSam-X | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 88.944 ms | 4 - 63 MB | FP16 | NPU | Use Export Script |
61
- | FastSam-X | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 44.486 ms | 5 - 5 MB | FP16 | NPU | Use Export Script |
62
- | FastSam-X | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 49.572 ms | 140 - 140 MB | FP16 | NPU | [FastSam-X.onnx](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.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[fastsam_x]"
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
  FastSam-X
125
  Device : Samsung Galaxy S23 (13)
126
  Runtime : TFLITE
127
- Estimated inference time (ms) : 44.1
128
- Estimated peak memory usage (MB): [2, 52]
129
  Total # Ops : 419
130
  Compute Unit(s) : NPU (419 ops)
131
  ```
@@ -152,7 +151,7 @@ from qai_hub_models.models.fastsam_x 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 FastSam-X can be found [here](https://github.com/CASIA-IVA-Lab/FastSAM/blob/main/LICENSE).
 
248
  * The license for the compiled assets for on-device deployment can be found [here](https://github.com/CASIA-IVA-Lab/FastSAM/blob/main/LICENSE)
249
 
250
 
 
35
 
36
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
+ | FastSam-X | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 46.279 ms | 4 - 19 MB | FP16 | NPU | [FastSam-X.tflite](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.tflite) |
39
+ | FastSam-X | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 45.042 ms | 4 - 21 MB | FP16 | NPU | [FastSam-X.so](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.so) |
40
+ | FastSam-X | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 49.854 ms | 5 - 318 MB | FP16 | NPU | [FastSam-X.onnx](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.onnx) |
41
+ | FastSam-X | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 34.909 ms | 1 - 61 MB | FP16 | NPU | [FastSam-X.tflite](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.tflite) |
42
+ | FastSam-X | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 34.417 ms | 5 - 64 MB | FP16 | NPU | [FastSam-X.so](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.so) |
43
+ | FastSam-X | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 34.958 ms | 14 - 79 MB | FP16 | NPU | [FastSam-X.onnx](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.onnx) |
44
+ | FastSam-X | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 27.589 ms | 4 - 64 MB | FP16 | NPU | [FastSam-X.tflite](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.tflite) |
45
+ | FastSam-X | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 27.389 ms | 5 - 64 MB | FP16 | NPU | Use Export Script |
46
+ | FastSam-X | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 31.897 ms | 21 - 76 MB | FP16 | NPU | [FastSam-X.onnx](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.onnx) |
47
+ | FastSam-X | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 45.14 ms | 4 - 56 MB | FP16 | NPU | [FastSam-X.tflite](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.tflite) |
48
+ | FastSam-X | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 45.059 ms | 5 - 8 MB | FP16 | NPU | Use Export Script |
49
+ | FastSam-X | SA7255P ADP | SA7255P | TFLITE | 2097.686 ms | 0 - 60 MB | FP16 | NPU | [FastSam-X.tflite](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.tflite) |
50
+ | FastSam-X | SA7255P ADP | SA7255P | QNN | 2095.613 ms | 5 - 14 MB | FP16 | NPU | Use Export Script |
51
+ | FastSam-X | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 46.078 ms | 4 - 51 MB | FP16 | NPU | [FastSam-X.tflite](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.tflite) |
52
+ | FastSam-X | SA8255 (Proxy) | SA8255P Proxy | QNN | 44.533 ms | 5 - 7 MB | FP16 | NPU | Use Export Script |
53
+ | FastSam-X | SA8295P ADP | SA8295P | TFLITE | 93.938 ms | 0 - 56 MB | FP16 | NPU | [FastSam-X.tflite](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.tflite) |
54
+ | FastSam-X | SA8295P ADP | SA8295P | QNN | 82.809 ms | 0 - 14 MB | FP16 | NPU | Use Export Script |
55
+ | FastSam-X | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 46.425 ms | 4 - 51 MB | FP16 | NPU | [FastSam-X.tflite](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.tflite) |
56
+ | FastSam-X | SA8650 (Proxy) | SA8650P Proxy | QNN | 43.452 ms | 5 - 7 MB | FP16 | NPU | Use Export Script |
57
+ | FastSam-X | SA8775P ADP | SA8775P | TFLITE | 87.589 ms | 0 - 57 MB | FP16 | NPU | [FastSam-X.tflite](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.tflite) |
58
+ | FastSam-X | SA8775P ADP | SA8775P | QNN | 85.645 ms | 2 - 12 MB | FP16 | NPU | Use Export Script |
59
+ | FastSam-X | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 90.22 ms | 4 - 63 MB | FP16 | NPU | [FastSam-X.tflite](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.tflite) |
60
+ | FastSam-X | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 88.072 ms | 0 - 59 MB | FP16 | NPU | Use Export Script |
61
+ | FastSam-X | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 44.542 ms | 5 - 5 MB | FP16 | NPU | Use Export Script |
62
+ | FastSam-X | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 49.563 ms | 141 - 141 MB | FP16 | NPU | [FastSam-X.onnx](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.onnx) |
63
 
64
 
65
 
66
 
67
  ## Installation
68
 
 
69
 
70
+ Install the package via pip:
71
  ```bash
72
+ pip install "qai-hub-models[fastsam-x]"
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
  FastSam-X
124
  Device : Samsung Galaxy S23 (13)
125
  Runtime : TFLITE
126
+ Estimated inference time (ms) : 46.3
127
+ Estimated peak memory usage (MB): [4, 19]
128
  Total # Ops : 419
129
  Compute Unit(s) : NPU (419 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 FastSam-X can be found
247
+ [here](https://github.com/CASIA-IVA-Lab/FastSAM/blob/main/LICENSE).
248
  * The license for the compiled assets for on-device deployment can be found [here](https://github.com/CASIA-IVA-Lab/FastSAM/blob/main/LICENSE)
249
 
250