qaihm-bot commited on
Commit
71a2e90
·
verified ·
1 Parent(s): 3ee9a7d

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +4 -5
README.md CHANGED
@@ -25,7 +25,7 @@ More details on model performance across various devices, can be found
25
  - **Model Type:** Super resolution
26
  - **Model Stats:**
27
  - Model checkpoint: quicksrnet_medium_3x_checkpoint
28
- - Input resolution: 640x360
29
  - Number of parameters: 55.0K
30
  - Model size: 220 KB
31
 
@@ -34,8 +34,8 @@ More details on model performance across various devices, can be found
34
 
35
  | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
36
  | ---|---|---|---|---|---|---|---|
37
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 1.343 ms | 0 - 1 MB | FP16 | NPU | [QuickSRNetMedium.tflite](https://huggingface.co/qualcomm/QuickSRNetMedium/blob/main/QuickSRNetMedium.tflite)
38
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.988 ms | 0 - 2 MB | FP16 | NPU | [QuickSRNetMedium.so](https://huggingface.co/qualcomm/QuickSRNetMedium/blob/main/QuickSRNetMedium.so)
39
 
40
 
41
 
@@ -97,7 +97,7 @@ python -m qai_hub_models.models.quicksrnetmedium.export
97
  Profile Job summary of QuickSRNetMedium
98
  --------------------------------------------------
99
  Device: Snapdragon X Elite CRD (11)
100
- Estimated Inference Time: 1.07 ms
101
  Estimated Peak Memory Range: 0.20-0.20 MB
102
  Compute Units: NPU (17) | Total (17)
103
 
@@ -124,7 +124,6 @@ from qai_hub_models.models.quicksrnetmedium import Model
124
 
125
  # Load the model
126
  torch_model = Model.from_pretrained()
127
- torch_model.eval()
128
 
129
  # Device
130
  device = hub.Device("Samsung Galaxy S23")
 
25
  - **Model Type:** Super resolution
26
  - **Model Stats:**
27
  - Model checkpoint: quicksrnet_medium_3x_checkpoint
28
+ - Input resolution: 128x128
29
  - Number of parameters: 55.0K
30
  - Model size: 220 KB
31
 
 
34
 
35
  | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
36
  | ---|---|---|---|---|---|---|---|
37
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 1.382 ms | 0 - 2 MB | FP16 | NPU | [QuickSRNetMedium.tflite](https://huggingface.co/qualcomm/QuickSRNetMedium/blob/main/QuickSRNetMedium.tflite)
38
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.998 ms | 0 - 65 MB | FP16 | NPU | [QuickSRNetMedium.so](https://huggingface.co/qualcomm/QuickSRNetMedium/blob/main/QuickSRNetMedium.so)
39
 
40
 
41
 
 
97
  Profile Job summary of QuickSRNetMedium
98
  --------------------------------------------------
99
  Device: Snapdragon X Elite CRD (11)
100
+ Estimated Inference Time: 1.14 ms
101
  Estimated Peak Memory Range: 0.20-0.20 MB
102
  Compute Units: NPU (17) | Total (17)
103
 
 
124
 
125
  # Load the model
126
  torch_model = Model.from_pretrained()
 
127
 
128
  # Device
129
  device = hub.Device("Samsung Galaxy S23")