v0.30.5

See https://github.com/quic/ai-hub-models/releases/v0.30.5 for changelog.

README.md

@@ -1,6 +1,6 @@
 ---
 library_name: pytorch
-license: bsd-3-clause
+license: other
 tags:
 - android
 pipeline_tag: unconditional-image-generation
@@ -10,10 +10,10 @@ pipeline_tag: unconditional-image-generation
 ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/simple_bev_cam/web-assets/model_demo.png)
 
 # Simple-Bev: Optimized for Mobile Deployment
-## Construct a bird’s eye view from sensors mounted on a vehicle
+## Construct a bird's eye view from sensors mounted on a vehicle
 
 
-Simple_bev is a machine learning model for generating a birds eye view represenation from the sensors(cameras) mounted on a vehicle. It uses the ResNet-101 as the backbone and segnet as a segmentation model for specific use cases.
+Simple-Bev is a machine learning model for generating a bird's eye view representation from the sensors (cameras) mounted on a vehicle. It uses ResNet-101 as the backbone and segnet as a segmentation model for specific use cases.
 
 This model is an implementation of Simple-Bev found [here](https://github.com/aharley/simple_bev/blob/main/nets/segnet.py).
 
@@ -25,19 +25,19 @@ More details on model performance across various devices, can be found
 
 ### Model Details
 
-- **Model Type:** Image generation
+- **Model Type:** Model_use_case.image_generation
 - **Model Stats:**
   - Model checkpoint: model-000025000.pth
   - Input resolution: 448 x 800
   - Number of parameters: 42M
   - Model size: 505 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
 |---|---|---|---|---|---|---|---|---|
-| Simple-Bev | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 1533.805 ms | 1235 - 1552 MB | FP32 | CPU | [Simple-Bev.tflite](https://huggingface.co/qualcomm/Simple-Bev/blob/main/Simple-Bev.tflite) |
-| Simple-Bev | SA8295P ADP | SA8295P | TFLITE | 1908.015 ms | 1249 - 1560 MB | FP32 | CPU | [Simple-Bev.tflite](https://huggingface.co/qualcomm/Simple-Bev/blob/main/Simple-Bev.tflite) |
-| Simple-Bev | SA8775P ADP | SA8775P | TFLITE | 3593.07 ms | 1249 - 1546 MB | FP32 | CPU | [Simple-Bev.tflite](https://huggingface.co/qualcomm/Simple-Bev/blob/main/Simple-Bev.tflite) |
-| Simple-Bev | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 3593.07 ms | 1249 - 1546 MB | FP32 | CPU | [Simple-Bev.tflite](https://huggingface.co/qualcomm/Simple-Bev/blob/main/Simple-Bev.tflite) |
+| Simple-Bev | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 3357.93 ms | 1248 - 1733 MB | CPU | [Simple-Bev.tflite](https://huggingface.co/qualcomm/Simple-Bev/blob/main/Simple-Bev.tflite) |
+| Simple-Bev | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 1934.042 ms | 1250 - 1733 MB | CPU | [Simple-Bev.tflite](https://huggingface.co/qualcomm/Simple-Bev/blob/main/Simple-Bev.tflite) |
+| Simple-Bev | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 3357.93 ms | 1248 - 1733 MB | CPU | [Simple-Bev.tflite](https://huggingface.co/qualcomm/Simple-Bev/blob/main/Simple-Bev.tflite) |
+| Simple-Bev | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 1706.168 ms | 1229 - 1702 MB | CPU | [Simple-Bev.tflite](https://huggingface.co/qualcomm/Simple-Bev/blob/main/Simple-Bev.tflite) |
 
 
 
@@ -99,12 +99,12 @@ python -m qai_hub_models.models.simple_bev_cam.export
 Profiling Results
 ------------------------------------------------------------
 Simple-Bev
-Device                          : Snapdragon 8 Elite QRD (15)
-Runtime                         : TFLITE                     
-Estimated inference time (ms)   : 1533.8                     
-Estimated peak memory usage (MB): [1235, 1552]               
-Total # Ops                     : 397                        
-Compute Unit(s)                 : GPU (191 ops) CPU (206 ops)
+Device                          : cs_9075 (ANDROID 14)                   
+Runtime                         : TFLITE                                 
+Estimated inference time (ms)   : 3357.9                                 
+Estimated peak memory usage (MB): [1248, 1733]                           
+Total # Ops                     : 423                                    
+Compute Unit(s)                 : npu (0 ops) gpu (197 ops) cpu (226 ops)
 ```
 
 

Simple-Bev.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fe19e5d393936cd764ea03d6a50fd73e6287198f7f5a2ba9117bae92e987664a
-size 113112688

Simple-Bev.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:716a2e7c3e698d6aadf286f3996a61d9d4458978a2390eb37b9286c59c844a64
-size 198850565

Simple-Bev.tflite

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87e6e792b5f58350db47b499b4039458e6a5bd92594562f03c8ab28b8c592b44
-size 198844036
+oid sha256:ef31681341cb7ce3ff780e6ce54753ce9b95eafb0fe360585ec753ce72b7ba14
+size 198848476