Hugging Face's logo

qualcomm
/
ESRGAN

Image-to-Image
PyTorch
LiteRT
android
Model card Files Community
qaihm-bot commited on
Commit
d2e5282
·
verified ·
1 Parent(s): c318088

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +31 -28
README.md CHANGED
@@ -34,37 +34,39 @@ More details on model performance across various devices, can be found
34
 
35
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
36
  |---|---|---|---|---|---|---|---|---|
37
- | ESRGAN | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 67.747 ms | 1 - 122 MB | FP16 | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
38
- | ESRGAN | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 65.514 ms | 0 - 111 MB | FP16 | NPU | [ESRGAN.so](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.so) |
39
- | ESRGAN | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 72.407 ms | 6 - 119 MB | FP16 | NPU | [ESRGAN.onnx](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.onnx) |
40
- | ESRGAN | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 51.406 ms | 3 - 112 MB | FP16 | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
41
- | ESRGAN | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 50.128 ms | 0 - 105 MB | FP16 | NPU | [ESRGAN.so](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.so) |
42
- | ESRGAN | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 51.885 ms | 6 - 173 MB | FP16 | NPU | [ESRGAN.onnx](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.onnx) |
43
- | ESRGAN | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 42.304 ms | 3 - 135 MB | FP16 | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
44
- | ESRGAN | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 38.151 ms | 0 - 130 MB | FP16 | NPU | Use Export Script |
45
- | ESRGAN | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 38.676 ms | 6 - 134 MB | FP16 | NPU | [ESRGAN.onnx](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.onnx) |
46
- | ESRGAN | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 68.975 ms | 0 - 117 MB | FP16 | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
47
- | ESRGAN | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 64.855 ms | 0 - 3 MB | FP16 | NPU | Use Export Script |
48
- | ESRGAN | SA7255P ADP | SA7255P | TFLITE | 3549.015 ms | 0 - 134 MB | FP16 | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
49
- | ESRGAN | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 70.358 ms | 1 - 115 MB | FP16 | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
50
- | ESRGAN | SA8255 (Proxy) | SA8255P Proxy | QNN | 65.555 ms | 0 - 3 MB | FP16 | NPU | Use Export Script |
51
- | ESRGAN | SA8295P ADP | SA8295P | TFLITE | 112.186 ms | 3 - 128 MB | FP16 | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
52
- | ESRGAN | SA8295P ADP | SA8295P | QNN | 111.099 ms | 0 - 15 MB | FP16 | NPU | Use Export Script |
53
- | ESRGAN | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 69.171 ms | 0 - 37 MB | FP16 | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
54
- | ESRGAN | SA8650 (Proxy) | SA8650P Proxy | QNN | 64.685 ms | 0 - 2 MB | FP16 | NPU | Use Export Script |
55
- | ESRGAN | SA8775P ADP | SA8775P | TFLITE | 131.609 ms | 3 - 136 MB | FP16 | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
56
- | ESRGAN | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 116.467 ms | 3 - 106 MB | FP16 | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
57
- | ESRGAN | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 123.622 ms | 0 - 86 MB | FP16 | NPU | Use Export Script |
58
- | ESRGAN | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 68.455 ms | 0 - 0 MB | FP16 | NPU | Use Export Script |
59
- | ESRGAN | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 65.85 ms | 39 - 39 MB | FP16 | NPU | [ESRGAN.onnx](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.onnx) |
 
 
60
 
61
 
62
 
63
 
64
  ## Installation
65
 
66
- This model can be installed as a Python package via pip.
67
 
 
68
  ```bash
69
  pip install qai-hub-models
70
  ```
@@ -120,8 +122,8 @@ Profiling Results
120
  ESRGAN
121
  Device : Samsung Galaxy S23 (13)
122
  Runtime : TFLITE
123
- Estimated inference time (ms) : 67.7
124
- Estimated peak memory usage (MB): [1, 122]
125
  Total # Ops : 1024
126
  Compute Unit(s) : NPU (1024 ops)
127
  ```
@@ -148,7 +150,7 @@ from qai_hub_models.models.esrgan import Model
148
  torch_model = Model.from_pretrained()
149
 
150
  # Device
151
- device = hub.Device("Samsung Galaxy S23")
152
 
153
  # Trace model
154
  input_shape = torch_model.get_input_spec()
@@ -240,7 +242,8 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
240
 
241
 
242
  ## License
243
- * The license for the original implementation of ESRGAN can be found [here](https://github.com/xinntao/ESRGAN/blob/master/LICENSE).
 
244
  * 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)
245
 
246
 
 
34
 
35
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
36
  |---|---|---|---|---|---|---|---|---|
37
+ | ESRGAN | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 66.773 ms | 0 - 116 MB | FP16 | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
38
+ | ESRGAN | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 65.37 ms | 0 - 109 MB | FP16 | NPU | [ESRGAN.so](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.so) |
39
+ | ESRGAN | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 76.54 ms | 0 - 109 MB | FP16 | NPU | [ESRGAN.onnx](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.onnx) |
40
+ | ESRGAN | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 49.333 ms | 1 - 107 MB | FP16 | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
41
+ | ESRGAN | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 49.311 ms | 0 - 109 MB | FP16 | NPU | [ESRGAN.so](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.so) |
42
+ | ESRGAN | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 50.517 ms | 6 - 176 MB | FP16 | NPU | [ESRGAN.onnx](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.onnx) |
43
+ | ESRGAN | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 42.478 ms | 3 - 136 MB | FP16 | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
44
+ | ESRGAN | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 39.466 ms | 0 - 131 MB | FP16 | NPU | Use Export Script |
45
+ | ESRGAN | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 43.104 ms | 6 - 134 MB | FP16 | NPU | [ESRGAN.onnx](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.onnx) |
46
+ | ESRGAN | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 66.403 ms | 0 - 218 MB | FP16 | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
47
+ | ESRGAN | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 68.136 ms | 0 - 3 MB | FP16 | NPU | Use Export Script |
48
+ | ESRGAN | SA7255P ADP | SA7255P | TFLITE | 3548.777 ms | 0 - 133 MB | FP16 | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
49
+ | ESRGAN | SA7255P ADP | SA7255P | QNN | 3549.059 ms | 1 - 9 MB | FP16 | NPU | Use Export Script |
50
+ | ESRGAN | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 65.221 ms | 0 - 118 MB | FP16 | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
51
+ | ESRGAN | SA8255 (Proxy) | SA8255P Proxy | QNN | 64.694 ms | 0 - 2 MB | FP16 | NPU | Use Export Script |
52
+ | ESRGAN | SA8295P ADP | SA8295P | TFLITE | 112.217 ms | 3 - 125 MB | FP16 | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
53
+ | ESRGAN | SA8295P ADP | SA8295P | QNN | 111.136 ms | 0 - 15 MB | FP16 | NPU | Use Export Script |
54
+ | ESRGAN | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 70.101 ms | 0 - 118 MB | FP16 | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
55
+ | ESRGAN | SA8650 (Proxy) | SA8650P Proxy | QNN | 72.194 ms | 0 - 3 MB | FP16 | NPU | Use Export Script |
56
+ | ESRGAN | SA8775P ADP | SA8775P | TFLITE | 131.575 ms | 3 - 136 MB | FP16 | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
57
+ | ESRGAN | SA8775P ADP | SA8775P | QNN | 131.073 ms | 0 - 10 MB | FP16 | NPU | Use Export Script |
58
+ | ESRGAN | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 121.886 ms | 0 - 99 MB | FP16 | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
59
+ | ESRGAN | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 137.13 ms | 0 - 90 MB | FP16 | NPU | Use Export Script |
60
+ | ESRGAN | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 64.887 ms | 0 - 0 MB | FP16 | NPU | Use Export Script |
61
+ | ESRGAN | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 65.684 ms | 39 - 39 MB | FP16 | NPU | [ESRGAN.onnx](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.onnx) |
62
 
63
 
64
 
65
 
66
  ## Installation
67
 
 
68
 
69
+ Install the package via pip:
70
  ```bash
71
  pip install qai-hub-models
72
  ```
 
122
  ESRGAN
123
  Device : Samsung Galaxy S23 (13)
124
  Runtime : TFLITE
125
+ Estimated inference time (ms) : 66.8
126
+ Estimated peak memory usage (MB): [0, 116]
127
  Total # Ops : 1024
128
  Compute Unit(s) : NPU (1024 ops)
129
  ```
 
150
  torch_model = Model.from_pretrained()
151
 
152
  # Device
153
+ device = hub.Device("Samsung Galaxy S24")
154
 
155
  # Trace model
156
  input_shape = torch_model.get_input_spec()
 
242
 
243
 
244
  ## License
245
+ * The license for the original implementation of ESRGAN can be found
246
+ [here](https://github.com/xinntao/ESRGAN/blob/master/LICENSE).
247
  * 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)
248
 
249