Hugging Face's logo

qualcomm
/
ESRGAN

Image-to-Image
PyTorch
LiteRT
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
7b40654
·
verified ·
1 Parent(s): adf559e

v0.32.0

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.32.0 for changelog.

Files changed (5) hide show
  1. .gitattributes +1 -0
  2. DEPLOYMENT_MODEL_LICENSE.pdf +3 -0
  3. ESRGAN.onnx +2 -2
  4. LICENSE +2 -0
  5. README.md +5 -5
.gitattributes CHANGED
@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  ESRGAN.so filter=lfs diff=lfs merge=lfs -text
37
  ESRGAN.dlc filter=lfs diff=lfs merge=lfs -text
 
 
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  ESRGAN.so filter=lfs diff=lfs merge=lfs -text
37
  ESRGAN.dlc filter=lfs diff=lfs merge=lfs -text
38
+ DEPLOYMENT_MODEL_LICENSE.pdf filter=lfs diff=lfs merge=lfs -text
DEPLOYMENT_MODEL_LICENSE.pdf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4409f93b0e82531303b3e10f52f1fdfb56467a25f05b7441c6bbd8bb8a64b42c
3
+ size 109629
ESRGAN.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72091f6b50b1fb8f6542dc78f46d01248fb8e6a55f2b9045d3c58c0d9652bcf6
3
- size 67162409
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3831800353f8354b2e7e8bc24f4fe4d497925bbe98261a4a8d6514c088e28eef
3
+ size 67202936
LICENSE ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ The license of the original trained model can be found at https://github.com/xinntao/ESRGAN/blob/master/LICENSE.
2
+ The license for the deployable model files (.tflite, .onnx, .dlc, .bin, etc.) can be found in DEPLOYMENT_MODEL_LICENSE.pdf.
README.md CHANGED
@@ -30,7 +30,7 @@ More details on model performance across various devices, can be found
30
  - Model checkpoint: ESRGAN_x4
31
  - Input resolution: 128x128
32
  - Number of parameters: 16.7M
33
- - Model size: 64.0 MB
34
 
35
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
36
  |---|---|---|---|---|---|---|---|---|
@@ -54,15 +54,15 @@ More details on model performance across various devices, can be found
54
  | ESRGAN | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 105.274 ms | 0 - 130 MB | NPU | [ESRGAN.dlc](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.dlc) |
55
  | ESRGAN | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 67.727 ms | 0 - 106 MB | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
56
  | ESRGAN | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 64.021 ms | 0 - 43 MB | NPU | [ESRGAN.dlc](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.dlc) |
57
- | ESRGAN | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 68.603 ms | 6 - 112 MB | NPU | [ESRGAN.onnx](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.onnx) |
58
  | ESRGAN | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 51.329 ms | 0 - 205 MB | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
59
  | ESRGAN | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 48.631 ms | 0 - 134 MB | NPU | [ESRGAN.dlc](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.dlc) |
60
- | ESRGAN | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 51.448 ms | 6 - 209 MB | NPU | [ESRGAN.onnx](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.onnx) |
61
  | ESRGAN | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 40.502 ms | 3 - 200 MB | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
62
  | ESRGAN | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 42.33 ms | 0 - 126 MB | NPU | [ESRGAN.dlc](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.dlc) |
63
- | ESRGAN | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 42.879 ms | 6 - 135 MB | NPU | [ESRGAN.onnx](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.onnx) |
64
  | ESRGAN | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 65.21 ms | 134 - 134 MB | NPU | [ESRGAN.dlc](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.dlc) |
65
- | ESRGAN | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 65.597 ms | 38 - 38 MB | NPU | [ESRGAN.onnx](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.onnx) |
66
 
67
 
68
 
 
30
  - Model checkpoint: ESRGAN_x4
31
  - Input resolution: 128x128
32
  - Number of parameters: 16.7M
33
+ - Model size (float): 63.9 MB
34
 
35
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
36
  |---|---|---|---|---|---|---|---|---|
 
54
  | ESRGAN | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 105.274 ms | 0 - 130 MB | NPU | [ESRGAN.dlc](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.dlc) |
55
  | ESRGAN | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 67.727 ms | 0 - 106 MB | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
56
  | ESRGAN | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 64.021 ms | 0 - 43 MB | NPU | [ESRGAN.dlc](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.dlc) |
57
+ | ESRGAN | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 73.805 ms | 6 - 111 MB | NPU | [ESRGAN.onnx](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.onnx) |
58
  | ESRGAN | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 51.329 ms | 0 - 205 MB | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
59
  | ESRGAN | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 48.631 ms | 0 - 134 MB | NPU | [ESRGAN.dlc](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.dlc) |
60
+ | ESRGAN | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 51.277 ms | 5 - 205 MB | NPU | [ESRGAN.onnx](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.onnx) |
61
  | ESRGAN | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 40.502 ms | 3 - 200 MB | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
62
  | ESRGAN | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 42.33 ms | 0 - 126 MB | NPU | [ESRGAN.dlc](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.dlc) |
63
+ | ESRGAN | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 39.079 ms | 6 - 136 MB | NPU | [ESRGAN.onnx](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.onnx) |
64
  | ESRGAN | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 65.21 ms | 134 - 134 MB | NPU | [ESRGAN.dlc](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.dlc) |
65
+ | ESRGAN | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 65.575 ms | 37 - 37 MB | NPU | [ESRGAN.onnx](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.onnx) |
66
 
67
 
68