qaihm-bot commited on
Commit
fd7ba92
·
verified ·
1 Parent(s): 4daf78e

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +6 -30
README.md CHANGED
@@ -33,10 +33,7 @@ More details on model performance across various devices, can be found
33
 
34
  | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
35
  | ---|---|---|---|---|---|---|---|
36
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 1.365 ms | 0 - 1 MB | FP16 | NPU | [QuickSRNetSmall-Quantized.tflite](https://huggingface.co/qualcomm/QuickSRNetSmall-Quantized/blob/main/QuickSRNetSmall-Quantized.tflite)
37
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 1.359 ms | 0 - 2 MB | INT8 | NPU | [QuickSRNet_Small_Quantized.tflite](https://huggingface.co/qualcomm/QuickSRNetSmall-Quantized/blob/main/QuickSRNet_Small_Quantized.tflite)
38
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.997 ms | 0 - 2 MB | FP16 | NPU | [QuickSRNetSmall-Quantized.so](https://huggingface.co/qualcomm/QuickSRNetSmall-Quantized/blob/main/QuickSRNetSmall-Quantized.so)
39
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 1.023 ms | 0 - 8 MB | INT8 | NPU | [QuickSRNet_Small_Quantized.so](https://huggingface.co/qualcomm/QuickSRNetSmall-Quantized/blob/main/QuickSRNet_Small_Quantized.so)
40
 
41
 
42
  ## Installation
@@ -96,31 +93,10 @@ python -m qai_hub_models.models.quicksrnetsmall_quantized.export
96
  ```
97
  Profile Job summary of QuickSRNetSmall-Quantized
98
  --------------------------------------------------
99
- Device: Samsung Galaxy S23 (13)
100
- Estimated Inference Time: 1.36 ms
101
- Estimated Peak Memory Range: 0.02-1.37 MB
102
- Compute Units: NPU (8),CPU (3) | Total (11)
103
-
104
- Profile Job summary of QuickSRNet_Small_Quantized
105
- --------------------------------------------------
106
- Device: Samsung Galaxy S23 (13)
107
- Estimated Inference Time: 1.36 ms
108
- Estimated Peak Memory Range: 0.03-1.52 MB
109
- Compute Units: NPU (8),CPU (3) | Total (11)
110
-
111
- Profile Job summary of QuickSRNetSmall-Quantized
112
- --------------------------------------------------
113
- Device: Samsung Galaxy S23 (13)
114
- Estimated Inference Time: 1.00 ms
115
- Estimated Peak Memory Range: 0.21-2.20 MB
116
- Compute Units: NPU (12) | Total (12)
117
-
118
- Profile Job summary of QuickSRNet_Small_Quantized
119
- --------------------------------------------------
120
- Device: Samsung Galaxy S23 (13)
121
- Estimated Inference Time: 1.02 ms
122
- Estimated Peak Memory Range: 0.22-7.55 MB
123
- Compute Units: NPU (12) | Total (12)
124
 
125
 
126
  ```
@@ -239,7 +215,7 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
239
  ## License
240
  - The license for the original implementation of QuickSRNetSmall-Quantized can be found
241
  [here](https://github.com/quic/aimet-model-zoo/blob/develop/LICENSE.pdf).
242
- - The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf).
243
 
244
  ## References
245
  * [QuickSRNet: Plain Single-Image Super-Resolution Architecture for Faster Inference on Mobile Platforms](https://arxiv.org/abs/2303.04336)
 
33
 
34
  | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
35
  | ---|---|---|---|---|---|---|---|
36
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 1.355 ms | 0 - 2 MB | INT8 | NPU | [QuickSRNetSmall-Quantized.tflite](https://huggingface.co/qualcomm/QuickSRNetSmall-Quantized/blob/main/QuickSRNetSmall-Quantized.tflite)
 
 
 
37
 
38
 
39
  ## Installation
 
93
  ```
94
  Profile Job summary of QuickSRNetSmall-Quantized
95
  --------------------------------------------------
96
+ Device: Samsung Galaxy S24 (14)
97
+ Estimated Inference Time: 1.10 ms
98
+ Estimated Peak Memory Range: 0.02-19.27 MB
99
+ Compute Units: NPU (10),CPU (3) | Total (13)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
100
 
101
 
102
  ```
 
215
  ## License
216
  - The license for the original implementation of QuickSRNetSmall-Quantized can be found
217
  [here](https://github.com/quic/aimet-model-zoo/blob/develop/LICENSE.pdf).
218
+ - The license for the compiled assets for on-device deployment can be found [here]({deploy_license_url})
219
 
220
  ## References
221
  * [QuickSRNet: Plain Single-Image Super-Resolution Architecture for Faster Inference on Mobile Platforms](https://arxiv.org/abs/2303.04336)