v0.34.0

See https://github.com/quic/ai-hub-models/releases/v0.34.0 for changelog.

README.md

@@ -23,6 +23,7 @@ More details on model performance across various devices, can be found
 [here](https://aihub.qualcomm.com/models/nasnet).
 
 
+
 ### Model Details
 
 - **Model Type:** Model_use_case.image_classification
@@ -36,13 +37,13 @@ More details on model performance across various devices, can be found
 
 | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
 |---|---|---|---|---|---|---|---|---|
-| NASNet | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 37.489 ms | 0 - 331 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
-| NASNet | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 15.652 ms | 0 - 332 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
-| NASNet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 7.58 ms | 0 - 23 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
-| NASNet | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 10.713 ms | 0 - 331 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
-| NASNet | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 7.617 ms | 0 - 25 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
-| NASNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 5.528 ms | 0 - 384 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
-| NASNet | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 5.212 ms | 0 - 329 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
+| NASNet | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 37.512 ms | 0 - 331 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
+| NASNet | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 15.451 ms | 0 - 334 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
+| NASNet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 7.642 ms | 0 - 26 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
+| NASNet | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 10.735 ms | 0 - 331 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
+| NASNet | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 7.618 ms | 0 - 27 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
+| NASNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 5.536 ms | 0 - 386 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
+| NASNet | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 5.188 ms | 0 - 329 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
 
 
 
@@ -100,17 +101,7 @@ device. This script does the following:
 ```bash
 python -m qai_hub_models.models.nasnet.export
 ```
-```
-Profiling Results
-------------------------------------------------------------
-NASNet
-Device                          : cs_8275 (ANDROID 14)                 
-Runtime                         : TFLITE                               
-Estimated inference time (ms)   : 37.5                                 
-Estimated peak memory usage (MB): [0, 331]                             
-Total # Ops                     : 776                                  
-Compute Unit(s)                 : npu (776 ops) gpu (0 ops) cpu (0 ops)
-```
+
 
 
 ## How does this work?