Hugging Face's logo

qualcomm
/
ESRGAN

Image-to-Image
PyTorch
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
cc18d8a
·
verified ·
1 Parent(s): ae73a41

v0.46.1

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.46.1 for changelog.

Files changed (5) hide show
  1. ESRGAN_float.dlc +0 -3
  2. ESRGAN_float.onnx.zip +0 -3
  3. ESRGAN_float.tflite +0 -3
  4. README.md +73 -226
  5. tool-versions.yaml +0 -4
ESRGAN_float.dlc DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:86fcd79c5bda96b17f64d1d83239bd4860b53fde83f3cb09dc040c5a52b22d29
3
- size 67922324
 
 
 
 
ESRGAN_float.onnx.zip DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5cbcfd2448d3d7a51b2a284875a8c3814e52f50877b25455ba62841e3c1aa7e0
3
- size 62221488
 
 
 
 
ESRGAN_float.tflite DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8fa7a0b119f3849ca06d823ce447389a8b41966640e8faf95a045e59df75cfee
3
- size 67032316
 
 
 
 
README.md CHANGED
@@ -9,244 +9,91 @@ pipeline_tag: image-to-image
9
 
10
  ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/esrgan/web-assets/model_demo.png)
11
 
12
- # ESRGAN: Optimized for Mobile Deployment
13
- ## Upscale images and remove image noise
14
-
15
 
16
  ESRGAN is a machine learning model that upscales an image with minimal loss in quality.
17
 
18
- This model is an implementation of ESRGAN found [here](https://github.com/xinntao/ESRGAN/).
19
-
20
-
21
- This repository provides scripts to run ESRGAN on Qualcomm® devices.
22
- More details on model performance across various devices, can be found
23
- [here](https://aihub.qualcomm.com/models/esrgan).
24
-
25
-
26
-
27
- ### Model Details
28
-
29
- - **Model Type:** Model_use_case.super_resolution
30
- - **Model Stats:**
31
- - Model checkpoint: ESRGAN_x4
32
- - Input resolution: 128x128
33
- - Number of parameters: 16.7M
34
- - Model size (float): 63.9 MB
35
-
36
- | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
37
- |---|---|---|---|---|---|---|---|---|
38
- | ESRGAN | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 448.729 ms | 3 - 319 MB | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
39
- | ESRGAN | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 448.654 ms | 0 - 278 MB | NPU | [ESRGAN.dlc](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.dlc) |
40
- | ESRGAN | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 130.63 ms | 3 - 730 MB | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
41
- | ESRGAN | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 118.728 ms | 1 - 694 MB | NPU | [ESRGAN.dlc](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.dlc) |
42
- | ESRGAN | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 65.593 ms | 2 - 5 MB | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
43
- | ESRGAN | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 68.161 ms | 0 - 3 MB | NPU | [ESRGAN.dlc](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.dlc) |
44
- | ESRGAN | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 67.464 ms | 0 - 43 MB | NPU | [ESRGAN.onnx.zip](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.onnx.zip) |
45
- | ESRGAN | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 105.399 ms | 3 - 318 MB | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
46
- | ESRGAN | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 496.068 ms | 0 - 277 MB | NPU | [ESRGAN.dlc](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.dlc) |
47
- | ESRGAN | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 448.729 ms | 3 - 319 MB | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
48
- | ESRGAN | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 448.654 ms | 0 - 278 MB | NPU | [ESRGAN.dlc](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.dlc) |
49
- | ESRGAN | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 111.285 ms | 3 - 331 MB | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
50
- | ESRGAN | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 111.274 ms | 0 - 297 MB | NPU | [ESRGAN.dlc](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.dlc) |
51
- | ESRGAN | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 105.399 ms | 3 - 318 MB | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
52
- | ESRGAN | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 496.068 ms | 0 - 277 MB | NPU | [ESRGAN.dlc](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.dlc) |
53
- | ESRGAN | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 50.392 ms | 3 - 728 MB | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
54
- | ESRGAN | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 48.83 ms | 0 - 685 MB | NPU | [ESRGAN.dlc](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.dlc) |
55
- | ESRGAN | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 50.253 ms | 8 - 698 MB | NPU | [ESRGAN.onnx.zip](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.onnx.zip) |
56
- | ESRGAN | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 38.193 ms | 3 - 303 MB | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
57
- | ESRGAN | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 38.092 ms | 0 - 268 MB | NPU | [ESRGAN.dlc](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.dlc) |
58
- | ESRGAN | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 39.247 ms | 7 - 258 MB | NPU | [ESRGAN.onnx.zip](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.onnx.zip) |
59
- | ESRGAN | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen 5 Mobile | TFLITE | 26.103 ms | 3 - 310 MB | NPU | [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) |
60
- | ESRGAN | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen 5 Mobile | QNN_DLC | 25.976 ms | 0 - 276 MB | NPU | [ESRGAN.dlc](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.dlc) |
61
- | ESRGAN | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen 5 Mobile | ONNX | 29.96 ms | 7 - 266 MB | NPU | [ESRGAN.onnx.zip](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.onnx.zip) |
62
- | ESRGAN | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 64.764 ms | 0 - 0 MB | NPU | [ESRGAN.dlc](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.dlc) |
63
- | ESRGAN | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 65.553 ms | 37 - 37 MB | NPU | [ESRGAN.onnx.zip](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.onnx.zip) |
64
-
65
-
66
-
67
-
68
- ## Installation
69
-
70
-
71
- Install the package via pip:
72
- ```bash
73
- pip install qai-hub-models
74
- ```
75
-
76
-
77
- ## Configure Qualcomm® AI Hub Workbench to run this model on a cloud-hosted device
78
-
79
- Sign-in to [Qualcomm® AI Hub Workbench](https://workbench.aihub.qualcomm.com/) with your
80
- Qualcomm® ID. Once signed in navigate to `Account -> Settings -> API Token`.
81
-
82
- With this API token, you can configure your client to run models on the cloud
83
- hosted devices.
84
- ```bash
85
- qai-hub configure --api_token API_TOKEN
86
- ```
87
- Navigate to [docs](https://workbench.aihub.qualcomm.com/docs/) for more information.
88
-
89
-
90
-
91
- ## Demo off target
92
-
93
- The package contains a simple end-to-end demo that downloads pre-trained
94
- weights and runs this model on a sample input.
95
-
96
- ```bash
97
- python -m qai_hub_models.models.esrgan.demo
98
- ```
99
-
100
- The above demo runs a reference implementation of pre-processing, model
101
- inference, and post processing.
102
-
103
- **NOTE**: If you want running in a Jupyter Notebook or Google Colab like
104
- environment, please add the following to your cell (instead of the above).
105
- ```
106
- %run -m qai_hub_models.models.esrgan.demo
107
- ```
108
-
109
-
110
- ### Run model on a cloud-hosted device
111
-
112
- In addition to the demo, you can also run the model on a cloud-hosted Qualcomm®
113
- device. This script does the following:
114
- * Performance check on-device on a cloud-hosted device
115
- * Downloads compiled assets that can be deployed on-device for Android.
116
- * Accuracy check between PyTorch and on-device outputs.
117
-
118
- ```bash
119
- python -m qai_hub_models.models.esrgan.export
120
- ```
121
-
122
-
123
-
124
- ## How does this work?
125
-
126
- This [export script](https://aihub.qualcomm.com/models/esrgan/qai_hub_models/models/ESRGAN/export.py)
127
- leverages [Qualcomm® AI Hub](https://aihub.qualcomm.com/) to optimize, validate, and deploy this model
128
- on-device. Lets go through each step below in detail:
129
-
130
- Step 1: **Compile model for on-device deployment**
131
-
132
- To compile a PyTorch model for on-device deployment, we first trace the model
133
- in memory using the `jit.trace` and then call the `submit_compile_job` API.
134
-
135
- ```python
136
- import torch
137
-
138
- import qai_hub as hub
139
- from qai_hub_models.models.esrgan import Model
140
-
141
- # Load the model
142
- torch_model = Model.from_pretrained()
143
-
144
- # Device
145
- device = hub.Device("Samsung Galaxy S25")
146
-
147
- # Trace model
148
- input_shape = torch_model.get_input_spec()
149
- sample_inputs = torch_model.sample_inputs()
150
-
151
- pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()])
152
-
153
- # Compile model on a specific device
154
- compile_job = hub.submit_compile_job(
155
- model=pt_model,
156
- device=device,
157
- input_specs=torch_model.get_input_spec(),
158
- )
159
-
160
- # Get target model to run on-device
161
- target_model = compile_job.get_target_model()
162
-
163
- ```
164
-
165
-
166
- Step 2: **Performance profiling on cloud-hosted device**
167
-
168
- After compiling models from step 1. Models can be profiled model on-device using the
169
- `target_model`. Note that this scripts runs the model on a device automatically
170
- provisioned in the cloud. Once the job is submitted, you can navigate to a
171
- provided job URL to view a variety of on-device performance metrics.
172
- ```python
173
- profile_job = hub.submit_profile_job(
174
- model=target_model,
175
- device=device,
176
- )
177
-
178
- ```
179
-
180
- Step 3: **Verify on-device accuracy**
181
-
182
- To verify the accuracy of the model on-device, you can run on-device inference
183
- on sample input data on the same cloud hosted device.
184
- ```python
185
- input_data = torch_model.sample_inputs()
186
- inference_job = hub.submit_inference_job(
187
- model=target_model,
188
- device=device,
189
- inputs=input_data,
190
- )
191
- on_device_output = inference_job.download_output_data()
192
-
193
- ```
194
- With the output of the model, you can compute like PSNR, relative errors or
195
- spot check the output with expected output.
196
-
197
- **Note**: This on-device profiling and inference requires access to Qualcomm®
198
- AI Hub Workbench. [Sign up for access](https://myaccount.qualcomm.com/signup).
199
-
200
-
201
-
202
- ## Run demo on a cloud-hosted device
203
-
204
- You can also run the demo on-device.
205
-
206
- ```bash
207
- python -m qai_hub_models.models.esrgan.demo --eval-mode on-device
208
- ```
209
-
210
- **NOTE**: If you want running in a Jupyter Notebook or Google Colab like
211
- environment, please add the following to your cell (instead of the above).
212
- ```
213
- %run -m qai_hub_models.models.esrgan.demo -- --eval-mode on-device
214
- ```
215
-
216
-
217
- ## Deploying compiled model to Android
218
-
219
-
220
- The models can be deployed using multiple runtimes:
221
- - TensorFlow Lite (`.tflite` export): [This
222
- tutorial](https://www.tensorflow.org/lite/android/quickstart) provides a
223
- guide to deploy the .tflite model in an Android application.
224
-
225
-
226
- - QNN (`.so` export ): This [sample
227
- app](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-50/sample_app.html)
228
- provides instructions on how to use the `.so` shared library in an Android application.
229
-
230
-
231
- ## View on Qualcomm® AI Hub
232
- Get more details on ESRGAN's performance across various devices [here](https://aihub.qualcomm.com/models/esrgan).
233
- Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
234
-
235
 
236
  ## License
237
  * The license for the original implementation of ESRGAN can be found
238
  [here](https://github.com/xinntao/ESRGAN/blob/master/LICENSE).
239
 
240
-
241
-
242
  ## References
243
  * [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://arxiv.org/abs/1809.00219)
244
  * [Source Model Implementation](https://github.com/xinntao/ESRGAN/)
245
 
246
-
247
-
248
  ## Community
249
  * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
250
  * For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).
251
-
252
-
 
9
 
10
  ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/esrgan/web-assets/model_demo.png)
11
 
12
+ # ESRGAN: Optimized for Qualcomm Devices
 
 
13
 
14
  ESRGAN is a machine learning model that upscales an image with minimal loss in quality.
15
 
16
+ This is based on the implementation of ESRGAN found [here](https://github.com/xinntao/ESRGAN/).
17
+ This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/esrgan) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
18
+
19
+ Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.
20
+
21
+ ## Getting Started
22
+ There are two ways to deploy this model on your device:
23
+
24
+ ### Option 1: Download Pre-Exported Models
25
+
26
+ Below are pre-exported model assets ready for deployment.
27
+
28
+ | Runtime | Precision | Chipset | SDK Versions | Download |
29
+ |---|---|---|---|---|
30
+ | ONNX | float | Universal | QAIRT 2.37, ONNX Runtime 1.23.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/esrgan/releases/v0.46.1/esrgan-onnx-float.zip)
31
+ | QNN_DLC | float | Universal | QAIRT 2.42 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/esrgan/releases/v0.46.1/esrgan-qnn_dlc-float.zip)
32
+ | TFLITE | float | Universal | QAIRT 2.42, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/esrgan/releases/v0.46.1/esrgan-tflite-float.zip)
33
+
34
+ For more device-specific assets and performance metrics, visit **[ESRGAN on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/esrgan)**.
35
+
36
+
37
+ ### Option 2: Export with Custom Configurations
38
+
39
+ Use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/esrgan) Python library to compile and export the model with your own:
40
+ - Custom weights (e.g., fine-tuned checkpoints)
41
+ - Custom input shapes
42
+ - Target device and runtime configurations
43
+
44
+ This option is ideal if you need to customize the model beyond the default configuration provided here.
45
+
46
+ See our repository for [ESRGAN on GitHub](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/esrgan) for usage instructions.
47
+
48
+ ## Model Details
49
+
50
+ **Model Type:** Model_use_case.super_resolution
51
+
52
+ **Model Stats:**
53
+ - Model checkpoint: ESRGAN_x4
54
+ - Input resolution: 128x128
55
+ - Number of parameters: 16.7M
56
+ - Model size (float): 63.9 MB
57
+
58
+ ## Performance Summary
59
+ | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
60
+ |---|---|---|---|---|---|---
61
+ | ESRGAN | ONNX | float | Snapdragon® X Elite | 65.559 ms | 38 - 38 MB | NPU
62
+ | ESRGAN | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 51.0 ms | 7 - 697 MB | NPU
63
+ | ESRGAN | ONNX | float | Qualcomm® QCS8550 (Proxy) | 65.676 ms | 0 - 45 MB | NPU
64
+ | ESRGAN | ONNX | float | Qualcomm® QCS9075 | 106.901 ms | 6 - 9 MB | NPU
65
+ | ESRGAN | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 38.988 ms | 7 - 257 MB | NPU
66
+ | ESRGAN | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 28.071 ms | 0 - 261 MB | NPU
67
+ | ESRGAN | QNN_DLC | float | Snapdragon® X Elite | 64.947 ms | 0 - 0 MB | NPU
68
+ | ESRGAN | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 49.399 ms | 0 - 748 MB | NPU
69
+ | ESRGAN | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 451.839 ms | 0 - 347 MB | NPU
70
+ | ESRGAN | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 62.453 ms | 0 - 3 MB | NPU
71
+ | ESRGAN | QNN_DLC | float | Qualcomm® SA8775P | 105.38 ms | 0 - 347 MB | NPU
72
+ | ESRGAN | QNN_DLC | float | Qualcomm® QCS9075 | 106.848 ms | 0 - 5 MB | NPU
73
+ | ESRGAN | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 112.556 ms | 0 - 753 MB | NPU
74
+ | ESRGAN | QNN_DLC | float | Qualcomm® SA7255P | 451.839 ms | 0 - 347 MB | NPU
75
+ | ESRGAN | QNN_DLC | float | Qualcomm® SA8295P | 111.274 ms | 0 - 357 MB | NPU
76
+ | ESRGAN | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 38.15 ms | 0 - 332 MB | NPU
77
+ | ESRGAN | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 25.883 ms | 0 - 331 MB | NPU
78
+ | ESRGAN | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 49.641 ms | 3 - 798 MB | NPU
79
+ | ESRGAN | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 451.971 ms | 7 - 398 MB | NPU
80
+ | ESRGAN | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 59.589 ms | 3 - 6 MB | NPU
81
+ | ESRGAN | TFLITE | float | Qualcomm® SA8775P | 105.469 ms | 3 - 394 MB | NPU
82
+ | ESRGAN | TFLITE | float | Qualcomm® QCS9075 | 107.96 ms | 3 - 47 MB | NPU
83
+ | ESRGAN | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 122.167 ms | 3 - 797 MB | NPU
84
+ | ESRGAN | TFLITE | float | Qualcomm® SA7255P | 451.971 ms | 7 - 398 MB | NPU
85
+ | ESRGAN | TFLITE | float | Qualcomm® SA8295P | 111.299 ms | 3 - 398 MB | NPU
86
+ | ESRGAN | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 38.09 ms | 3 - 376 MB | NPU
87
+ | ESRGAN | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 27.14 ms | 1 - 374 MB | NPU
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88
 
89
  ## License
90
  * The license for the original implementation of ESRGAN can be found
91
  [here](https://github.com/xinntao/ESRGAN/blob/master/LICENSE).
92
 
 
 
93
  ## References
94
  * [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://arxiv.org/abs/1809.00219)
95
  * [Source Model Implementation](https://github.com/xinntao/ESRGAN/)
96
 
 
 
97
  ## Community
98
  * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
99
  * For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).
 
 
tool-versions.yaml DELETED
@@ -1,4 +0,0 @@
1
- tool_versions:
2
- onnx:
3
- qairt: 2.37.1.250807093845_124904
4
- onnx_runtime: 1.23.0