qaihm-bot commited on
Commit
e681ec2
·
verified ·
1 Parent(s): 8b8181c

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

Files changed (1) hide show
  1. README.md +6 -15
README.md CHANGED
@@ -23,6 +23,7 @@ More details on model performance across various devices, can be found
23
  [here](https://aihub.qualcomm.com/models/simple_bev_cam).
24
 
25
 
 
26
  ### Model Details
27
 
28
  - **Model Type:** Model_use_case.image_generation
@@ -34,10 +35,10 @@ More details on model performance across various devices, can be found
34
 
35
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
36
  |---|---|---|---|---|---|---|---|---|
37
- | Simple-Bev | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 3496.02 ms | 1249 - 1746 MB | CPU | [Simple-Bev.tflite](https://huggingface.co/qualcomm/Simple-Bev/blob/main/Simple-Bev.tflite) |
38
- | Simple-Bev | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 1926.08 ms | 1250 - 1733 MB | CPU | [Simple-Bev.tflite](https://huggingface.co/qualcomm/Simple-Bev/blob/main/Simple-Bev.tflite) |
39
- | Simple-Bev | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 3496.02 ms | 1249 - 1746 MB | CPU | [Simple-Bev.tflite](https://huggingface.co/qualcomm/Simple-Bev/blob/main/Simple-Bev.tflite) |
40
- | Simple-Bev | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 1769.725 ms | 1227 - 1699 MB | CPU | [Simple-Bev.tflite](https://huggingface.co/qualcomm/Simple-Bev/blob/main/Simple-Bev.tflite) |
41
 
42
 
43
 
@@ -95,17 +96,7 @@ device. This script does the following:
95
  ```bash
96
  python -m qai_hub_models.models.simple_bev_cam.export
97
  ```
98
- ```
99
- Profiling Results
100
- ------------------------------------------------------------
101
- Simple-Bev
102
- Device : cs_9075 (ANDROID 14)
103
- Runtime : TFLITE
104
- Estimated inference time (ms) : 3496.0
105
- Estimated peak memory usage (MB): [1249, 1746]
106
- Total # Ops : 423
107
- Compute Unit(s) : npu (0 ops) gpu (197 ops) cpu (226 ops)
108
- ```
109
 
110
 
111
  ## How does this work?
 
23
  [here](https://aihub.qualcomm.com/models/simple_bev_cam).
24
 
25
 
26
+
27
  ### Model Details
28
 
29
  - **Model Type:** Model_use_case.image_generation
 
35
 
36
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
+ | Simple-Bev | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 3375.562 ms | 1249 - 1747 MB | CPU | [Simple-Bev.tflite](https://huggingface.co/qualcomm/Simple-Bev/blob/main/Simple-Bev.tflite) |
39
+ | Simple-Bev | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 1931.126 ms | 1248 - 1730 MB | CPU | [Simple-Bev.tflite](https://huggingface.co/qualcomm/Simple-Bev/blob/main/Simple-Bev.tflite) |
40
+ | Simple-Bev | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 3375.562 ms | 1249 - 1747 MB | CPU | [Simple-Bev.tflite](https://huggingface.co/qualcomm/Simple-Bev/blob/main/Simple-Bev.tflite) |
41
+ | Simple-Bev | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 1700.437 ms | 1227 - 1698 MB | CPU | [Simple-Bev.tflite](https://huggingface.co/qualcomm/Simple-Bev/blob/main/Simple-Bev.tflite) |
42
 
43
 
44
 
 
96
  ```bash
97
  python -m qai_hub_models.models.simple_bev_cam.export
98
  ```
99
+
 
 
 
 
 
 
 
 
 
 
100
 
101
 
102
  ## How does this work?