qaihm-bot commited on
Commit
dcc67ee
1 Parent(s): 9b565ed

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +6 -5
README.md CHANGED
@@ -30,14 +30,15 @@ More details on model performance across various devices, can be found
30
  - Input resolution: 2048x1024
31
  - Number of parameters: 18.0M
32
  - Model size: 68.8 MB
 
33
 
34
 
35
 
36
 
37
  | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
38
  | ---|---|---|---|---|---|---|---|
39
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 20.186 ms | 2 - 4 MB | FP16 | NPU | [FFNet-54S.tflite](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.tflite)
40
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 20.279 ms | 24 - 43 MB | FP16 | NPU | [FFNet-54S.so](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.so)
41
 
42
 
43
 
@@ -99,9 +100,9 @@ python -m qai_hub_models.models.ffnet_54s.export
99
  ```
100
  Profile Job summary of FFNet-54S
101
  --------------------------------------------------
102
- Device: Snapdragon X Elite CRD (11)
103
- Estimated Inference Time: 20.20 ms
104
- Estimated Peak Memory Range: 24.05-24.05 MB
105
  Compute Units: NPU (175) | Total (175)
106
 
107
 
 
30
  - Input resolution: 2048x1024
31
  - Number of parameters: 18.0M
32
  - Model size: 68.8 MB
33
+ - Number of output classes: 19
34
 
35
 
36
 
37
 
38
  | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
39
  | ---|---|---|---|---|---|---|---|
40
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 20.654 ms | 2 - 5 MB | FP16 | NPU | [FFNet-54S.tflite](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.tflite)
41
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 20.395 ms | 24 - 40 MB | FP16 | NPU | [FFNet-54S.so](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.so)
42
 
43
 
44
 
 
100
  ```
101
  Profile Job summary of FFNet-54S
102
  --------------------------------------------------
103
+ Device: SA8255 (Proxy) (13)
104
+ Estimated Inference Time: 20.07 ms
105
+ Estimated Peak Memory Range: 24.03-39.14 MB
106
  Compute Units: NPU (175) | Total (175)
107
 
108