Hugging Face's logo

qualcomm
/
LaMa-Dilated

Image-to-Image
PyTorch
LiteRT
backbone
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
1180c26
·
verified ·
1 Parent(s): ddd5545

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +32 -32
README.md CHANGED
@@ -35,45 +35,44 @@ More details on model performance across various devices, can be found
35
 
36
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
- | LaMa-Dilated | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 75.0 ms | 3 - 318 MB | FP16 | NPU | [LaMa-Dilated.tflite](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.tflite) |
39
- | LaMa-Dilated | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 70.443 ms | 4 - 36 MB | FP16 | NPU | [LaMa-Dilated.so](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.so) |
40
- | LaMa-Dilated | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 73.987 ms | 6 - 236 MB | FP16 | NPU | [LaMa-Dilated.onnx](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.onnx) |
41
- | LaMa-Dilated | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 51.815 ms | 2 - 93 MB | FP16 | NPU | [LaMa-Dilated.tflite](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.tflite) |
42
- | LaMa-Dilated | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 48.452 ms | 4 - 91 MB | FP16 | NPU | [LaMa-Dilated.so](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.so) |
43
- | LaMa-Dilated | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 51.211 ms | 10 - 105 MB | FP16 | NPU | [LaMa-Dilated.onnx](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.onnx) |
44
- | LaMa-Dilated | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 49.16 ms | 2 - 92 MB | FP16 | NPU | [LaMa-Dilated.tflite](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.tflite) |
45
- | LaMa-Dilated | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 38.087 ms | 1 - 89 MB | FP16 | NPU | Use Export Script |
46
- | LaMa-Dilated | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 48.244 ms | 10 - 104 MB | FP16 | NPU | [LaMa-Dilated.onnx](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.onnx) |
47
- | LaMa-Dilated | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 74.602 ms | 3 - 327 MB | FP16 | NPU | [LaMa-Dilated.tflite](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.tflite) |
48
- | LaMa-Dilated | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 66.984 ms | 4 - 7 MB | FP16 | NPU | Use Export Script |
49
- | LaMa-Dilated | SA7255P ADP | SA7255P | TFLITE | 3020.451 ms | 0 - 88 MB | FP16 | NPU | [LaMa-Dilated.tflite](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.tflite) |
50
- | LaMa-Dilated | SA7255P ADP | SA7255P | QNN | 3006.542 ms | 3 - 12 MB | FP16 | NPU | Use Export Script |
51
- | LaMa-Dilated | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 74.723 ms | 3 - 318 MB | FP16 | NPU | [LaMa-Dilated.tflite](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.tflite) |
52
- | LaMa-Dilated | SA8255 (Proxy) | SA8255P Proxy | QNN | 67.001 ms | 4 - 7 MB | FP16 | NPU | Use Export Script |
53
- | LaMa-Dilated | SA8295P ADP | SA8295P | TFLITE | 115.877 ms | 3 - 46 MB | FP16 | NPU | [LaMa-Dilated.tflite](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.tflite) |
54
- | LaMa-Dilated | SA8295P ADP | SA8295P | QNN | 103.904 ms | 2 - 16 MB | FP16 | NPU | Use Export Script |
55
- | LaMa-Dilated | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 75.019 ms | 3 - 332 MB | FP16 | NPU | [LaMa-Dilated.tflite](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.tflite) |
56
- | LaMa-Dilated | SA8650 (Proxy) | SA8650P Proxy | QNN | 67.037 ms | 4 - 7 MB | FP16 | NPU | Use Export Script |
57
- | LaMa-Dilated | SA8775P ADP | SA8775P | TFLITE | 129.787 ms | 3 - 91 MB | FP16 | NPU | [LaMa-Dilated.tflite](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.tflite) |
58
- | LaMa-Dilated | SA8775P ADP | SA8775P | QNN | 119.075 ms | 2 - 12 MB | FP16 | NPU | Use Export Script |
59
- | LaMa-Dilated | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 103.82 ms | 3 - 49 MB | FP16 | NPU | [LaMa-Dilated.tflite](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.tflite) |
60
- | LaMa-Dilated | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 99.637 ms | 4 - 50 MB | FP16 | NPU | Use Export Script |
61
- | LaMa-Dilated | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 69.465 ms | 4 - 4 MB | FP16 | NPU | Use Export Script |
62
- | LaMa-Dilated | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 78.565 ms | 90 - 90 MB | FP16 | NPU | [LaMa-Dilated.onnx](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.onnx) |
63
 
64
 
65
 
66
 
67
  ## Installation
68
 
69
- This model can be installed as a Python package via pip.
70
 
 
71
  ```bash
72
- pip install "qai-hub-models[lama_dilated]"
73
  ```
74
 
75
 
76
-
77
  ## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
78
 
79
  Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
@@ -124,8 +123,8 @@ Profiling Results
124
  LaMa-Dilated
125
  Device : Samsung Galaxy S23 (13)
126
  Runtime : TFLITE
127
- Estimated inference time (ms) : 75.0
128
- Estimated peak memory usage (MB): [3, 318]
129
  Total # Ops : 343
130
  Compute Unit(s) : NPU (343 ops)
131
  ```
@@ -152,7 +151,7 @@ from qai_hub_models.models.lama_dilated import Model
152
  torch_model = Model.from_pretrained()
153
 
154
  # Device
155
- device = hub.Device("Samsung Galaxy S23")
156
 
157
  # Trace model
158
  input_shape = torch_model.get_input_spec()
@@ -244,7 +243,8 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
244
 
245
 
246
  ## License
247
- * The license for the original implementation of LaMa-Dilated can be found [here](https://github.com/advimman/lama/blob/main/LICENSE).
 
248
  * 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)
249
 
250
 
 
35
 
36
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
+ | LaMa-Dilated | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 74.644 ms | 3 - 320 MB | FP16 | NPU | [LaMa-Dilated.tflite](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.tflite) |
39
+ | LaMa-Dilated | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 70.594 ms | 3 - 35 MB | FP16 | NPU | [LaMa-Dilated.so](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.so) |
40
+ | LaMa-Dilated | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 74.551 ms | 6 - 222 MB | FP16 | NPU | [LaMa-Dilated.onnx](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.onnx) |
41
+ | LaMa-Dilated | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 51.489 ms | 2 - 94 MB | FP16 | NPU | [LaMa-Dilated.tflite](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.tflite) |
42
+ | LaMa-Dilated | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 48.532 ms | 4 - 90 MB | FP16 | NPU | [LaMa-Dilated.so](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.so) |
43
+ | LaMa-Dilated | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 50.604 ms | 10 - 102 MB | FP16 | NPU | [LaMa-Dilated.onnx](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.onnx) |
44
+ | LaMa-Dilated | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 49.135 ms | 3 - 93 MB | FP16 | NPU | [LaMa-Dilated.tflite](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.tflite) |
45
+ | LaMa-Dilated | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 38.257 ms | 4 - 93 MB | FP16 | NPU | Use Export Script |
46
+ | LaMa-Dilated | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 48.317 ms | 5 - 98 MB | FP16 | NPU | [LaMa-Dilated.onnx](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.onnx) |
47
+ | LaMa-Dilated | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 74.423 ms | 3 - 319 MB | FP16 | NPU | [LaMa-Dilated.tflite](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.tflite) |
48
+ | LaMa-Dilated | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 67.652 ms | 4 - 7 MB | FP16 | NPU | Use Export Script |
49
+ | LaMa-Dilated | SA7255P ADP | SA7255P | TFLITE | 3020.428 ms | 0 - 88 MB | FP16 | NPU | [LaMa-Dilated.tflite](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.tflite) |
50
+ | LaMa-Dilated | SA7255P ADP | SA7255P | QNN | 3006.43 ms | 1 - 10 MB | FP16 | NPU | Use Export Script |
51
+ | LaMa-Dilated | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 75.099 ms | 1 - 312 MB | FP16 | NPU | [LaMa-Dilated.tflite](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.tflite) |
52
+ | LaMa-Dilated | SA8255 (Proxy) | SA8255P Proxy | QNN | 66.841 ms | 6 - 9 MB | FP16 | NPU | Use Export Script |
53
+ | LaMa-Dilated | SA8295P ADP | SA8295P | TFLITE | 115.806 ms | 3 - 46 MB | FP16 | NPU | [LaMa-Dilated.tflite](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.tflite) |
54
+ | LaMa-Dilated | SA8295P ADP | SA8295P | QNN | 103.885 ms | 1 - 16 MB | FP16 | NPU | Use Export Script |
55
+ | LaMa-Dilated | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 75.632 ms | 3 - 163 MB | FP16 | NPU | [LaMa-Dilated.tflite](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.tflite) |
56
+ | LaMa-Dilated | SA8650 (Proxy) | SA8650P Proxy | QNN | 66.932 ms | 4 - 6 MB | FP16 | NPU | Use Export Script |
57
+ | LaMa-Dilated | SA8775P ADP | SA8775P | TFLITE | 129.828 ms | 3 - 91 MB | FP16 | NPU | [LaMa-Dilated.tflite](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.tflite) |
58
+ | LaMa-Dilated | SA8775P ADP | SA8775P | QNN | 119.036 ms | 2 - 12 MB | FP16 | NPU | Use Export Script |
59
+ | LaMa-Dilated | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 107.296 ms | 3 - 50 MB | FP16 | NPU | [LaMa-Dilated.tflite](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.tflite) |
60
+ | LaMa-Dilated | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 104.543 ms | 4 - 50 MB | FP16 | NPU | Use Export Script |
61
+ | LaMa-Dilated | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 69.497 ms | 4 - 4 MB | FP16 | NPU | Use Export Script |
62
+ | LaMa-Dilated | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 78.573 ms | 90 - 90 MB | FP16 | NPU | [LaMa-Dilated.onnx](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.onnx) |
63
 
64
 
65
 
66
 
67
  ## Installation
68
 
 
69
 
70
+ Install the package via pip:
71
  ```bash
72
+ pip install "qai-hub-models[lama-dilated]"
73
  ```
74
 
75
 
 
76
  ## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
77
 
78
  Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
 
123
  LaMa-Dilated
124
  Device : Samsung Galaxy S23 (13)
125
  Runtime : TFLITE
126
+ Estimated inference time (ms) : 74.6
127
+ Estimated peak memory usage (MB): [3, 320]
128
  Total # Ops : 343
129
  Compute Unit(s) : NPU (343 ops)
130
  ```
 
151
  torch_model = Model.from_pretrained()
152
 
153
  # Device
154
+ device = hub.Device("Samsung Galaxy S24")
155
 
156
  # Trace model
157
  input_shape = torch_model.get_input_spec()
 
243
 
244
 
245
  ## License
246
+ * The license for the original implementation of LaMa-Dilated can be found
247
+ [here](https://github.com/advimman/lama/blob/main/LICENSE).
248
  * 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)
249
 
250