Upload README.md with huggingface_hub

README.md

@@ -15,7 +15,7 @@ tags:
 
 Midas is designed for estimating depth at each point in an image.
 
-This model is an implementation of Midas-V2-Quantized found [here](https://github.com/isl-org/MiDaS).
+This model is an implementation of Midas-V2-Quantized found [here]({source_repo}).
 This repository provides scripts to run Midas-V2-Quantized on Qualcomm® devices.
 More details on model performance across various devices, can be found
 [here](https://aihub.qualcomm.com/models/midas_quantized).
@@ -30,15 +30,31 @@ More details on model performance across various devices, can be found
   - Number of parameters: 16.6M
   - Model size: 16.6 MB
 
+| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
+|---|---|---|---|---|---|---|---|---|
+| Midas-V2-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 1.112 ms | 0 - 8 MB | INT8 | NPU | [Midas-V2-Quantized.tflite](https://huggingface.co/qualcomm/Midas-V2-Quantized/blob/main/Midas-V2-Quantized.tflite) |
+| Midas-V2-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 1.434 ms | 0 - 52 MB | INT8 | NPU | [Midas-V2-Quantized.so](https://huggingface.co/qualcomm/Midas-V2-Quantized/blob/main/Midas-V2-Quantized.so) |
+| Midas-V2-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.774 ms | 0 - 89 MB | INT8 | NPU | [Midas-V2-Quantized.tflite](https://huggingface.co/qualcomm/Midas-V2-Quantized/blob/main/Midas-V2-Quantized.tflite) |
+| Midas-V2-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 1.013 ms | 0 - 21 MB | INT8 | NPU | [Midas-V2-Quantized.so](https://huggingface.co/qualcomm/Midas-V2-Quantized/blob/main/Midas-V2-Quantized.so) |
+| Midas-V2-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 3.827 ms | 0 - 50 MB | INT8 | NPU | [Midas-V2-Quantized.tflite](https://huggingface.co/qualcomm/Midas-V2-Quantized/blob/main/Midas-V2-Quantized.tflite) |
+| Midas-V2-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 6.19 ms | 0 - 8 MB | INT8 | NPU | Use Export Script |
+| Midas-V2-Quantized | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 15.542 ms | 0 - 6 MB | INT8 | NPU | [Midas-V2-Quantized.tflite](https://huggingface.co/qualcomm/Midas-V2-Quantized/blob/main/Midas-V2-Quantized.tflite) |
+| Midas-V2-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 1.083 ms | 0 - 222 MB | INT8 | NPU | [Midas-V2-Quantized.tflite](https://huggingface.co/qualcomm/Midas-V2-Quantized/blob/main/Midas-V2-Quantized.tflite) |
+| Midas-V2-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 1.306 ms | 0 - 1 MB | INT8 | NPU | Use Export Script |
+| Midas-V2-Quantized | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 1.092 ms | 0 - 5 MB | INT8 | NPU | [Midas-V2-Quantized.tflite](https://huggingface.co/qualcomm/Midas-V2-Quantized/blob/main/Midas-V2-Quantized.tflite) |
+| Midas-V2-Quantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 1.32 ms | 0 - 1 MB | INT8 | NPU | Use Export Script |
+| Midas-V2-Quantized | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 1.089 ms | 0 - 2 MB | INT8 | NPU | [Midas-V2-Quantized.tflite](https://huggingface.co/qualcomm/Midas-V2-Quantized/blob/main/Midas-V2-Quantized.tflite) |
+| Midas-V2-Quantized | SA8775 (Proxy) | SA8775P Proxy | QNN | 1.315 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
+| Midas-V2-Quantized | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 1.092 ms | 0 - 2 MB | INT8 | NPU | [Midas-V2-Quantized.tflite](https://huggingface.co/qualcomm/Midas-V2-Quantized/blob/main/Midas-V2-Quantized.tflite) |
+| Midas-V2-Quantized | SA8650 (Proxy) | SA8650P Proxy | QNN | 1.319 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
+| Midas-V2-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 1.431 ms | 0 - 88 MB | INT8 | NPU | [Midas-V2-Quantized.tflite](https://huggingface.co/qualcomm/Midas-V2-Quantized/blob/main/Midas-V2-Quantized.tflite) |
+| Midas-V2-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 1.772 ms | 0 - 25 MB | INT8 | NPU | Use Export Script |
+| Midas-V2-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.731 ms | 0 - 47 MB | INT8 | NPU | [Midas-V2-Quantized.tflite](https://huggingface.co/qualcomm/Midas-V2-Quantized/blob/main/Midas-V2-Quantized.tflite) |
+| Midas-V2-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 1.001 ms | 0 - 21 MB | INT8 | NPU | Use Export Script |
+| Midas-V2-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 1.461 ms | 0 - 0 MB | INT8 | NPU | Use Export Script |
 
 
 
-| Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
-| ---|---|---|---|---|---|---|---|
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 1.094 ms | 0 - 3 MB | INT8 | NPU |  [Midas-V2-Quantized.tflite](https://huggingface.co/qualcomm/Midas-V2-Quantized/blob/main/Midas-V2-Quantized.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 1.435 ms | 0 - 301 MB | INT8 | NPU |  [Midas-V2-Quantized.so](https://huggingface.co/qualcomm/Midas-V2-Quantized/blob/main/Midas-V2-Quantized.so) 
-
-
 
 ## Installation
 
@@ -94,16 +110,16 @@ device. This script does the following:
 ```bash
 python -m qai_hub_models.models.midas_quantized.export
 ```
-
 ```
-Profile Job summary of Midas-V2-Quantized
---------------------------------------------------
-Device: Snapdragon X Elite CRD (11)
-Estimated Inference Time: 1.48 ms
-Estimated Peak Memory Range: 0.33-0.33 MB
-Compute Units: NPU (146) | Total (146)
-
-
+Profiling Results
+------------------------------------------------------------
+Midas-V2-Quantized
+Device                          : Samsung Galaxy S23 (13)
+Runtime                         : TFLITE                 
+Estimated inference time (ms)   : 1.1                    
+Estimated peak memory usage (MB): [0, 8]                 
+Total # Ops                     : 145                    
+Compute Unit(s)                 : NPU (145 ops)          
 ```
 
 
@@ -142,15 +158,19 @@ provides instructions on how to use the `.so` shared library  in an Android appl
 Get more details on Midas-V2-Quantized's performance across various devices [here](https://aihub.qualcomm.com/models/midas_quantized).
 Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
 
+
 ## License
-- The license for the original implementation of Midas-V2-Quantized can be found
-  [here](https://github.com/isl-org/MiDaS/blob/master/LICENSE).
-- 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)
+* The license for the original implementation of Midas-V2-Quantized can be found [here](https://github.com/isl-org/MiDaS/blob/master/LICENSE).
+* 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)
+
+
 
 ## References
 * [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://arxiv.org/abs/1907.01341v3)
 * [Source Model Implementation](https://github.com/isl-org/MiDaS)
 
+
+
 ## Community
 * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
 * For questions or feedback please [reach out to us](mailto:[email protected]).