Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
---
|
| 2 |
library_name: pytorch
|
| 3 |
-
license:
|
| 4 |
tags:
|
| 5 |
- android
|
| 6 |
pipeline_tag: image-segmentation
|
|
@@ -25,7 +25,7 @@ More details on model performance across various devices, can be found
|
|
| 25 |
|
| 26 |
### Model Details
|
| 27 |
|
| 28 |
-
- **Model Type:**
|
| 29 |
- **Model Stats:**
|
| 30 |
- Model checkpoint: fastsam-x.pt
|
| 31 |
- Inference latency: RealTime
|
|
@@ -33,37 +33,37 @@ More details on model performance across various devices, can be found
|
|
| 33 |
- Number of parameters: 72.2M
|
| 34 |
- Model size: 276 MB
|
| 35 |
|
| 36 |
-
| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) |
|
| 37 |
|---|---|---|---|---|---|---|---|---|
|
| 38 |
-
| FastSam-X |
|
| 39 |
-
| FastSam-X |
|
| 40 |
-
| FastSam-X |
|
| 41 |
-
| FastSam-X |
|
| 42 |
-
| FastSam-X |
|
| 43 |
-
| FastSam-X |
|
| 44 |
-
| FastSam-X |
|
| 45 |
-
| FastSam-X |
|
| 46 |
-
| FastSam-X |
|
| 47 |
-
| FastSam-X | SA7255P ADP | SA7255P |
|
| 48 |
-
| FastSam-X |
|
| 49 |
-
| FastSam-X | SA8255 (Proxy) | SA8255P Proxy |
|
| 50 |
-
| FastSam-X |
|
| 51 |
-
| FastSam-X | SA8295P ADP | SA8295P |
|
| 52 |
-
| FastSam-X |
|
| 53 |
-
| FastSam-X | SA8650 (Proxy) | SA8650P Proxy |
|
| 54 |
-
| FastSam-X |
|
| 55 |
-
| FastSam-X | SA8775P ADP | SA8775P |
|
| 56 |
-
| FastSam-X |
|
| 57 |
-
| FastSam-X |
|
| 58 |
-
| FastSam-X |
|
| 59 |
-
| FastSam-X |
|
| 60 |
-
| FastSam-X |
|
| 61 |
-
| FastSam-X |
|
| 62 |
-
| FastSam-X |
|
| 63 |
-
| FastSam-X |
|
| 64 |
-
| FastSam-X |
|
| 65 |
-
| FastSam-X | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 43.
|
| 66 |
-
| FastSam-X | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 46.
|
| 67 |
|
| 68 |
|
| 69 |
|
|
@@ -125,12 +125,12 @@ python -m qai_hub_models.models.fastsam_x.export
|
|
| 125 |
Profiling Results
|
| 126 |
------------------------------------------------------------
|
| 127 |
FastSam-X
|
| 128 |
-
Device :
|
| 129 |
-
Runtime : TFLITE
|
| 130 |
-
Estimated inference time (ms) :
|
| 131 |
-
Estimated peak memory usage (MB): [4,
|
| 132 |
-
Total # Ops : 419
|
| 133 |
-
Compute Unit(s) :
|
| 134 |
```
|
| 135 |
|
| 136 |
|
|
|
|
| 1 |
---
|
| 2 |
library_name: pytorch
|
| 3 |
+
license: other
|
| 4 |
tags:
|
| 5 |
- android
|
| 6 |
pipeline_tag: image-segmentation
|
|
|
|
| 25 |
|
| 26 |
### Model Details
|
| 27 |
|
| 28 |
+
- **Model Type:** Model_use_case.semantic_segmentation
|
| 29 |
- **Model Stats:**
|
| 30 |
- Model checkpoint: fastsam-x.pt
|
| 31 |
- Inference latency: RealTime
|
|
|
|
| 33 |
- Number of parameters: 72.2M
|
| 34 |
- Model size: 276 MB
|
| 35 |
|
| 36 |
+
| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
|
| 37 |
|---|---|---|---|---|---|---|---|---|
|
| 38 |
+
| FastSam-X | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 280.805 ms | 4 - 98 MB | NPU | [FastSam-X.tflite](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.tflite) |
|
| 39 |
+
| FastSam-X | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 277.446 ms | 5 - 14 MB | NPU | Use Export Script |
|
| 40 |
+
| FastSam-X | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 91.198 ms | 4 - 193 MB | NPU | [FastSam-X.tflite](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.tflite) |
|
| 41 |
+
| FastSam-X | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 101.603 ms | 0 - 70 MB | NPU | Use Export Script |
|
| 42 |
+
| FastSam-X | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 46.334 ms | 4 - 56 MB | NPU | [FastSam-X.tflite](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.tflite) |
|
| 43 |
+
| FastSam-X | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 42.629 ms | 5 - 7 MB | NPU | Use Export Script |
|
| 44 |
+
| FastSam-X | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 70.592 ms | 3 - 96 MB | NPU | [FastSam-X.tflite](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.tflite) |
|
| 45 |
+
| FastSam-X | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 68.113 ms | 3 - 12 MB | NPU | Use Export Script |
|
| 46 |
+
| FastSam-X | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 280.805 ms | 4 - 98 MB | NPU | [FastSam-X.tflite](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.tflite) |
|
| 47 |
+
| FastSam-X | float | SA7255P ADP | Qualcomm® SA7255P | QNN | 277.446 ms | 5 - 14 MB | NPU | Use Export Script |
|
| 48 |
+
| FastSam-X | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 45.381 ms | 4 - 58 MB | NPU | [FastSam-X.tflite](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.tflite) |
|
| 49 |
+
| FastSam-X | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 44.411 ms | 5 - 8 MB | NPU | Use Export Script |
|
| 50 |
+
| FastSam-X | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 89.678 ms | 1 - 91 MB | NPU | [FastSam-X.tflite](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.tflite) |
|
| 51 |
+
| FastSam-X | float | SA8295P ADP | Qualcomm® SA8295P | QNN | 80.098 ms | 0 - 18 MB | NPU | Use Export Script |
|
| 52 |
+
| FastSam-X | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 46.409 ms | 4 - 56 MB | NPU | [FastSam-X.tflite](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.tflite) |
|
| 53 |
+
| FastSam-X | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 42.767 ms | 5 - 12 MB | NPU | Use Export Script |
|
| 54 |
+
| FastSam-X | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 70.592 ms | 3 - 96 MB | NPU | [FastSam-X.tflite](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.tflite) |
|
| 55 |
+
| FastSam-X | float | SA8775P ADP | Qualcomm® SA8775P | QNN | 68.113 ms | 3 - 12 MB | NPU | Use Export Script |
|
| 56 |
+
| FastSam-X | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 47.026 ms | 4 - 63 MB | NPU | [FastSam-X.tflite](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.tflite) |
|
| 57 |
+
| FastSam-X | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 42.984 ms | 5 - 27 MB | NPU | Use Export Script |
|
| 58 |
+
| FastSam-X | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 46.412 ms | 13 - 323 MB | NPU | [FastSam-X.onnx](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.onnx) |
|
| 59 |
+
| FastSam-X | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 34.752 ms | 2 - 186 MB | NPU | [FastSam-X.tflite](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.tflite) |
|
| 60 |
+
| FastSam-X | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 32.74 ms | 5 - 65 MB | NPU | Use Export Script |
|
| 61 |
+
| FastSam-X | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 33.399 ms | 15 - 79 MB | NPU | [FastSam-X.onnx](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.onnx) |
|
| 62 |
+
| FastSam-X | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 31.038 ms | 4 - 100 MB | NPU | [FastSam-X.tflite](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.tflite) |
|
| 63 |
+
| FastSam-X | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 26.405 ms | 5 - 60 MB | NPU | Use Export Script |
|
| 64 |
+
| FastSam-X | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 30.363 ms | 10 - 67 MB | NPU | [FastSam-X.onnx](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.onnx) |
|
| 65 |
+
| FastSam-X | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 43.548 ms | 5 - 5 MB | NPU | Use Export Script |
|
| 66 |
+
| FastSam-X | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 46.794 ms | 139 - 139 MB | NPU | [FastSam-X.onnx](https://huggingface.co/qualcomm/FastSam-X/blob/main/FastSam-X.onnx) |
|
| 67 |
|
| 68 |
|
| 69 |
|
|
|
|
| 125 |
Profiling Results
|
| 126 |
------------------------------------------------------------
|
| 127 |
FastSam-X
|
| 128 |
+
Device : cs_8275 (ANDROID 14)
|
| 129 |
+
Runtime : TFLITE
|
| 130 |
+
Estimated inference time (ms) : 280.8
|
| 131 |
+
Estimated peak memory usage (MB): [4, 98]
|
| 132 |
+
Total # Ops : 419
|
| 133 |
+
Compute Unit(s) : npu (419 ops) gpu (0 ops) cpu (0 ops)
|
| 134 |
```
|
| 135 |
|
| 136 |
|