Hugging Face's logo

qualcomm
/
QuickSRNetMedium-Quantized

Image-to-Image
PyTorch
TF Lite
quantized
android
Model card Files Community
qaihm-bot commited on
Commit
39573ce
•
1 Parent(s): b700a24

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -26,7 +26,7 @@ More details on model performance across various devices, can be found
26
  - **Model Type:** Super resolution
27
  - **Model Stats:**
28
  - Model checkpoint: quicksrnet_medium_3x_checkpoint
29
- - Input resolution: 640x360
30
  - Number of parameters: 55.0K
31
  - Model size: 67.2 KB
32
 
@@ -35,8 +35,8 @@ More details on model performance across various devices, can be found
35
 
36
  | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
37
  | ---|---|---|---|---|---|---|---|
38
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 1.0 ms | 0 - 5 MB | INT8 | NPU | [QuickSRNetMedium-Quantized.tflite](https://huggingface.co/qualcomm/QuickSRNetMedium-Quantized/blob/main/QuickSRNetMedium-Quantized.tflite)
39
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.803 ms | 0 - 10 MB | INT8 | NPU | [QuickSRNetMedium-Quantized.so](https://huggingface.co/qualcomm/QuickSRNetMedium-Quantized/blob/main/QuickSRNetMedium-Quantized.so)
40
 
41
 
42
 
@@ -99,8 +99,8 @@ python -m qai_hub_models.models.quicksrnetmedium_quantized.export
99
  Profile Job summary of QuickSRNetMedium-Quantized
100
  --------------------------------------------------
101
  Device: Snapdragon X Elite CRD (11)
102
- Estimated Inference Time: 0.76 ms
103
- Estimated Peak Memory Range: 1.14-1.14 MB
104
  Compute Units: NPU (11) | Total (11)
105
 
106
 
 
26
  - **Model Type:** Super resolution
27
  - **Model Stats:**
28
  - Model checkpoint: quicksrnet_medium_3x_checkpoint
29
+ - Input resolution: 128x128
30
  - Number of parameters: 55.0K
31
  - Model size: 67.2 KB
32
 
 
35
 
36
  | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
37
  | ---|---|---|---|---|---|---|---|
38
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 0.997 ms | 0 - 2 MB | INT8 | NPU | [QuickSRNetMedium-Quantized.tflite](https://huggingface.co/qualcomm/QuickSRNetMedium-Quantized/blob/main/QuickSRNetMedium-Quantized.tflite)
39
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.804 ms | 0 - 3 MB | INT8 | NPU | [QuickSRNetMedium-Quantized.so](https://huggingface.co/qualcomm/QuickSRNetMedium-Quantized/blob/main/QuickSRNetMedium-Quantized.so)
40
 
41
 
42
 
 
99
  Profile Job summary of QuickSRNetMedium-Quantized
100
  --------------------------------------------------
101
  Device: Snapdragon X Elite CRD (11)
102
+ Estimated Inference Time: 0.71 ms
103
+ Estimated Peak Memory Range: 0.09-0.09 MB
104
  Compute Units: NPU (11) | Total (11)
105
 
106