Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -35,22 +35,24 @@ 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 |
-
| SAMDecoder | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 29.
|
39 |
-
| SAMDecoder | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 20.232 ms |
|
40 |
-
| SAMDecoder |
|
41 |
-
| SAMDecoder |
|
42 |
-
| SAMDecoder |
|
43 |
-
| SAMDecoder |
|
44 |
-
| SAMDecoder |
|
45 |
-
| SAMDecoder |
|
46 |
-
|
|
47 |
-
| SAMEncoder | Samsung Galaxy
|
48 |
-
| SAMEncoder |
|
49 |
-
| SAMEncoder |
|
50 |
-
| SAMEncoder |
|
51 |
-
| SAMEncoder |
|
52 |
-
| SAMEncoder |
|
53 |
-
| SAMEncoder |
|
|
|
|
|
54 |
|
55 |
|
56 |
|
@@ -115,8 +117,8 @@ Profiling Results
|
|
115 |
SAMDecoder
|
116 |
Device : Samsung Galaxy S23 (13)
|
117 |
Runtime : TFLITE
|
118 |
-
Estimated inference time (ms) : 29.
|
119 |
-
Estimated peak memory usage (MB): [
|
120 |
Total # Ops : 337
|
121 |
Compute Unit(s) : NPU (337 ops)
|
122 |
|
@@ -124,8 +126,8 @@ Compute Unit(s) : NPU (337 ops)
|
|
124 |
SAMEncoder
|
125 |
Device : Samsung Galaxy S23 (13)
|
126 |
Runtime : TFLITE
|
127 |
-
Estimated inference time (ms) :
|
128 |
-
Estimated peak memory usage (MB): [
|
129 |
Total # Ops : 818
|
130 |
Compute Unit(s) : GPU (36 ops) CPU (782 ops)
|
131 |
```
|
|
|
35 |
|
36 |
| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
37 |
|---|---|---|---|---|---|---|---|---|
|
38 |
+
| SAMDecoder | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 29.177 ms | 4 - 12 MB | FP16 | NPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMDecoder.tflite) |
|
39 |
+
| SAMDecoder | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 20.232 ms | 3 - 230 MB | FP16 | NPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMDecoder.tflite) |
|
40 |
+
| SAMDecoder | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 16.874 ms | 2 - 163 MB | FP16 | NPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMDecoder.tflite) |
|
41 |
+
| SAMDecoder | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 29.037 ms | 4 - 12 MB | FP16 | NPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMDecoder.tflite) |
|
42 |
+
| SAMDecoder | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 28.98 ms | 4 - 12 MB | FP16 | NPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMDecoder.tflite) |
|
43 |
+
| SAMDecoder | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 29.066 ms | 4 - 6 MB | FP16 | NPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMDecoder.tflite) |
|
44 |
+
| SAMDecoder | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 29.012 ms | 4 - 12 MB | FP16 | NPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMDecoder.tflite) |
|
45 |
+
| SAMDecoder | SA8295P ADP | SA8295P | TFLITE | 36.365 ms | 0 - 153 MB | FP16 | NPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMDecoder.tflite) |
|
46 |
+
| SAMDecoder | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 32.973 ms | 4 - 220 MB | FP16 | NPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMDecoder.tflite) |
|
47 |
+
| SAMEncoder | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 10578.004 ms | 124 - 127 MB | FP32 | CPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMEncoder.tflite) |
|
48 |
+
| SAMEncoder | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 9199.727 ms | 121 - 1628 MB | FP32 | CPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMEncoder.tflite) |
|
49 |
+
| SAMEncoder | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 6686.187 ms | 122 - 1592 MB | FP32 | CPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMEncoder.tflite) |
|
50 |
+
| SAMEncoder | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 10519.059 ms | 123 - 127 MB | FP32 | CPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMEncoder.tflite) |
|
51 |
+
| SAMEncoder | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 10234.058 ms | 123 - 126 MB | FP32 | CPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMEncoder.tflite) |
|
52 |
+
| SAMEncoder | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 10476.142 ms | 123 - 126 MB | FP32 | CPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMEncoder.tflite) |
|
53 |
+
| SAMEncoder | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 11261.132 ms | 124 - 286 MB | FP32 | CPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMEncoder.tflite) |
|
54 |
+
| SAMEncoder | SA8295P ADP | SA8295P | TFLITE | 10774.664 ms | 124 - 1647 MB | FP32 | CPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMEncoder.tflite) |
|
55 |
+
| SAMEncoder | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 14281.656 ms | 127 - 1691 MB | FP32 | CPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMEncoder.tflite) |
|
56 |
|
57 |
|
58 |
|
|
|
117 |
SAMDecoder
|
118 |
Device : Samsung Galaxy S23 (13)
|
119 |
Runtime : TFLITE
|
120 |
+
Estimated inference time (ms) : 29.2
|
121 |
+
Estimated peak memory usage (MB): [4, 12]
|
122 |
Total # Ops : 337
|
123 |
Compute Unit(s) : NPU (337 ops)
|
124 |
|
|
|
126 |
SAMEncoder
|
127 |
Device : Samsung Galaxy S23 (13)
|
128 |
Runtime : TFLITE
|
129 |
+
Estimated inference time (ms) : 10578.0
|
130 |
+
Estimated peak memory usage (MB): [124, 127]
|
131 |
Total # Ops : 818
|
132 |
Compute Unit(s) : GPU (36 ops) CPU (782 ops)
|
133 |
```
|