Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
---
|
| 2 |
library_name: pytorch
|
| 3 |
license: mit
|
| 4 |
-
pipeline_tag: depth-estimation
|
| 5 |
tags:
|
| 6 |
- android
|
|
|
|
| 7 |
|
| 8 |
---
|
| 9 |
|
|
@@ -34,31 +34,35 @@ More details on model performance across various devices, can be found
|
|
| 34 |
|
| 35 |
| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
| 36 |
|---|---|---|---|---|---|---|---|---|
|
| 37 |
-
| Midas-V2 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 3.
|
| 38 |
-
| Midas-V2 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 3.
|
| 39 |
-
| Midas-V2 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 3.
|
| 40 |
-
| Midas-V2 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 2.
|
| 41 |
-
| Midas-V2 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 2.
|
| 42 |
-
| Midas-V2 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 2.
|
| 43 |
-
| Midas-V2 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE |
|
| 44 |
-
| Midas-V2 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN |
|
| 45 |
-
| Midas-V2 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX |
|
| 46 |
-
| Midas-V2 |
|
| 47 |
-
| Midas-V2 |
|
| 48 |
-
| Midas-V2 |
|
| 49 |
-
| Midas-V2 |
|
| 50 |
-
| Midas-V2 |
|
| 51 |
-
| Midas-V2 |
|
| 52 |
-
| Midas-V2 |
|
| 53 |
-
| Midas-V2 |
|
| 54 |
-
| Midas-V2 |
|
| 55 |
-
| Midas-V2 |
|
| 56 |
-
| Midas-V2 |
|
| 57 |
-
| Midas-V2 |
|
| 58 |
-
| Midas-V2 |
|
| 59 |
-
| Midas-V2 |
|
| 60 |
-
| Midas-V2 |
|
| 61 |
-
| Midas-V2 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
|
| 63 |
|
| 64 |
|
|
@@ -122,8 +126,8 @@ Profiling Results
|
|
| 122 |
Midas-V2
|
| 123 |
Device : Samsung Galaxy S23 (13)
|
| 124 |
Runtime : TFLITE
|
| 125 |
-
Estimated inference time (ms) : 3.
|
| 126 |
-
Estimated peak memory usage (MB): [0,
|
| 127 |
Total # Ops : 138
|
| 128 |
Compute Unit(s) : NPU (138 ops)
|
| 129 |
```
|
|
|
|
| 1 |
---
|
| 2 |
library_name: pytorch
|
| 3 |
license: mit
|
|
|
|
| 4 |
tags:
|
| 5 |
- android
|
| 6 |
+
pipeline_tag: depth-estimation
|
| 7 |
|
| 8 |
---
|
| 9 |
|
|
|
|
| 34 |
|
| 35 |
| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
| 36 |
|---|---|---|---|---|---|---|---|---|
|
| 37 |
+
| Midas-V2 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 3.164 ms | 0 - 141 MB | FP16 | NPU | [Midas-V2.tflite](https://huggingface.co/qualcomm/Midas-V2/blob/main/Midas-V2.tflite) |
|
| 38 |
+
| Midas-V2 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 3.036 ms | 1 - 4 MB | FP16 | NPU | [Midas-V2.so](https://huggingface.co/qualcomm/Midas-V2/blob/main/Midas-V2.so) |
|
| 39 |
+
| Midas-V2 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 3.401 ms | 0 - 107 MB | FP16 | NPU | [Midas-V2.onnx](https://huggingface.co/qualcomm/Midas-V2/blob/main/Midas-V2.onnx) |
|
| 40 |
+
| Midas-V2 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 2.25 ms | 0 - 31 MB | FP16 | NPU | [Midas-V2.tflite](https://huggingface.co/qualcomm/Midas-V2/blob/main/Midas-V2.tflite) |
|
| 41 |
+
| Midas-V2 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 2.131 ms | 1 - 20 MB | FP16 | NPU | [Midas-V2.so](https://huggingface.co/qualcomm/Midas-V2/blob/main/Midas-V2.so) |
|
| 42 |
+
| Midas-V2 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 2.356 ms | 0 - 35 MB | FP16 | NPU | [Midas-V2.onnx](https://huggingface.co/qualcomm/Midas-V2/blob/main/Midas-V2.onnx) |
|
| 43 |
+
| Midas-V2 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 1.745 ms | 0 - 27 MB | FP16 | NPU | [Midas-V2.tflite](https://huggingface.co/qualcomm/Midas-V2/blob/main/Midas-V2.tflite) |
|
| 44 |
+
| Midas-V2 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 2.117 ms | 1 - 27 MB | FP16 | NPU | Use Export Script |
|
| 45 |
+
| Midas-V2 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 2.261 ms | 1 - 32 MB | FP16 | NPU | [Midas-V2.onnx](https://huggingface.co/qualcomm/Midas-V2/blob/main/Midas-V2.onnx) |
|
| 46 |
+
| Midas-V2 | SA7255P ADP | SA7255P | TFLITE | 84.349 ms | 0 - 22 MB | FP16 | NPU | [Midas-V2.tflite](https://huggingface.co/qualcomm/Midas-V2/blob/main/Midas-V2.tflite) |
|
| 47 |
+
| Midas-V2 | SA7255P ADP | SA7255P | QNN | 84.169 ms | 1 - 9 MB | FP16 | NPU | Use Export Script |
|
| 48 |
+
| Midas-V2 | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 3.17 ms | 0 - 150 MB | FP16 | NPU | [Midas-V2.tflite](https://huggingface.co/qualcomm/Midas-V2/blob/main/Midas-V2.tflite) |
|
| 49 |
+
| Midas-V2 | SA8255 (Proxy) | SA8255P Proxy | QNN | 3.044 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
|
| 50 |
+
| Midas-V2 | SA8295P ADP | SA8295P | TFLITE | 5.895 ms | 0 - 22 MB | FP16 | NPU | [Midas-V2.tflite](https://huggingface.co/qualcomm/Midas-V2/blob/main/Midas-V2.tflite) |
|
| 51 |
+
| Midas-V2 | SA8295P ADP | SA8295P | QNN | 5.731 ms | 1 - 12 MB | FP16 | NPU | Use Export Script |
|
| 52 |
+
| Midas-V2 | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 3.168 ms | 0 - 151 MB | FP16 | NPU | [Midas-V2.tflite](https://huggingface.co/qualcomm/Midas-V2/blob/main/Midas-V2.tflite) |
|
| 53 |
+
| Midas-V2 | SA8650 (Proxy) | SA8650P Proxy | QNN | 3.034 ms | 0 - 2 MB | FP16 | NPU | Use Export Script |
|
| 54 |
+
| Midas-V2 | SA8775P ADP | SA8775P | TFLITE | 5.393 ms | 0 - 21 MB | FP16 | NPU | [Midas-V2.tflite](https://huggingface.co/qualcomm/Midas-V2/blob/main/Midas-V2.tflite) |
|
| 55 |
+
| Midas-V2 | SA8775P ADP | SA8775P | QNN | 5.245 ms | 1 - 8 MB | FP16 | NPU | Use Export Script |
|
| 56 |
+
| Midas-V2 | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 84.349 ms | 0 - 22 MB | FP16 | NPU | [Midas-V2.tflite](https://huggingface.co/qualcomm/Midas-V2/blob/main/Midas-V2.tflite) |
|
| 57 |
+
| Midas-V2 | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 84.169 ms | 1 - 9 MB | FP16 | NPU | Use Export Script |
|
| 58 |
+
| Midas-V2 | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 3.171 ms | 0 - 160 MB | FP16 | NPU | [Midas-V2.tflite](https://huggingface.co/qualcomm/Midas-V2/blob/main/Midas-V2.tflite) |
|
| 59 |
+
| Midas-V2 | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 3.037 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
|
| 60 |
+
| Midas-V2 | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 5.393 ms | 0 - 21 MB | FP16 | NPU | [Midas-V2.tflite](https://huggingface.co/qualcomm/Midas-V2/blob/main/Midas-V2.tflite) |
|
| 61 |
+
| Midas-V2 | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 5.245 ms | 1 - 8 MB | FP16 | NPU | Use Export Script |
|
| 62 |
+
| Midas-V2 | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 4.948 ms | 0 - 27 MB | FP16 | NPU | [Midas-V2.tflite](https://huggingface.co/qualcomm/Midas-V2/blob/main/Midas-V2.tflite) |
|
| 63 |
+
| Midas-V2 | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 4.826 ms | 1 - 27 MB | FP16 | NPU | Use Export Script |
|
| 64 |
+
| Midas-V2 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 3.189 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
|
| 65 |
+
| Midas-V2 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 3.349 ms | 37 - 37 MB | FP16 | NPU | [Midas-V2.onnx](https://huggingface.co/qualcomm/Midas-V2/blob/main/Midas-V2.onnx) |
|
| 66 |
|
| 67 |
|
| 68 |
|
|
|
|
| 126 |
Midas-V2
|
| 127 |
Device : Samsung Galaxy S23 (13)
|
| 128 |
Runtime : TFLITE
|
| 129 |
+
Estimated inference time (ms) : 3.2
|
| 130 |
+
Estimated peak memory usage (MB): [0, 141]
|
| 131 |
Total # Ops : 138
|
| 132 |
Compute Unit(s) : NPU (138 ops)
|
| 133 |
```
|