Upload README.md with huggingface_hub

README.md

@@ -1,6 +1,6 @@
 ---
 library_name: pytorch
-license: apache-2.0
+license: other
 tags:
 - android
 pipeline_tag: image-classification
@@ -25,7 +25,7 @@ More details on model performance across various devices, can be found
 
 ### Model Details
 
-- **Model Type:** Image classification
+- **Model Type:** Model_use_case.image_classification
 - **Model Stats:**
   - Model checkpoint: nasnetalarge.tf_in1k
   - Input resolution: 224x224
@@ -34,15 +34,15 @@ More details on model performance across various devices, can be found
   - Number of parameters: 88.7M
   - Model size: 338 MB
 
-| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
+| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
 |---|---|---|---|---|---|---|---|---|
-| NASNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 7.625 ms | 0 - 24 MB | FP16 | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
-| NASNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 5.718 ms | 13 - 362 MB | FP16 | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
-| NASNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 4.605 ms | 0 - 292 MB | FP16 | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
-| NASNet | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 279.671 ms | 0 - 292 MB | FP16 | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
-| NASNet | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 7.638 ms | 0 - 23 MB | FP16 | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
-| NASNet | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 13.052 ms | 0 - 292 MB | FP16 | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
-| NASNet | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 15.868 ms | 0 - 304 MB | FP16 | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
+| NASNet | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 37.955 ms | 0 - 291 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
+| NASNet | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 15.61 ms | 0 - 306 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
+| NASNet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 7.658 ms | 0 - 20 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
+| NASNet | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 11.02 ms | 0 - 291 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
+| NASNet | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 7.653 ms | 0 - 20 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
+| NASNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 5.589 ms | 0 - 348 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
+| NASNet | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 5.37 ms | 0 - 291 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
 
 
 
@@ -104,12 +104,12 @@ python -m qai_hub_models.models.nasnet.export
 Profiling Results
 ------------------------------------------------------------
 NASNet
-Device                          : Samsung Galaxy S23 (13)
-Runtime                         : TFLITE                 
-Estimated inference time (ms)   : 7.6                    
-Estimated peak memory usage (MB): [0, 24]                
-Total # Ops                     : 772                    
-Compute Unit(s)                 : NPU (772 ops)          
+Device                          : cs_8275 (ANDROID 14)                 
+Runtime                         : TFLITE                               
+Estimated inference time (ms)   : 38.0                                 
+Estimated peak memory usage (MB): [0, 291]                             
+Total # Ops                     : 776                                  
+Compute Unit(s)                 : npu (776 ops) gpu (0 ops) cpu (0 ops)
 ```