Hugging Face's logo

qualcomm
/
DDColor

Image-to-Image
PyTorch
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
36ace28
·
verified ·
1 Parent(s): d4d48fd

v0.48.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.48.0 for changelog.

Files changed (1) hide show
  1. README.md +32 -33
README.md CHANGED
@@ -14,7 +14,7 @@ pipeline_tag: image-to-image
14
  DDColor is a coloring algorithm that produces natural, vivid color results from incoming black and white images.
15
 
16
  This is based on the implementation of DDColor found [here](https://github.com/piddnad/DDColor/).
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/ddcolor) 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
 
@@ -27,28 +27,27 @@ Below are pre-exported model assets ready for deployment.
27
 
28
  | Runtime | Precision | Chipset | SDK Versions | Download |
29
  |---|---|---|---|---|
30
- | ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddcolor/releases/v0.47.0/ddcolor-onnx-float.zip)
31
- | ONNX | w8a8 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddcolor/releases/v0.47.0/ddcolor-onnx-w8a8.zip)
32
- | ONNX | w8a8_mixed_int16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddcolor/releases/v0.47.0/ddcolor-onnx-w8a8_mixed_int16.zip)
33
- | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddcolor/releases/v0.47.0/ddcolor-qnn_dlc-float.zip)
34
- | QNN_DLC | w8a8 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddcolor/releases/v0.47.0/ddcolor-qnn_dlc-w8a8.zip)
35
- | QNN_DLC | w8a8_mixed_int16 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddcolor/releases/v0.47.0/ddcolor-qnn_dlc-w8a8_mixed_int16.zip)
36
- | TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddcolor/releases/v0.47.0/ddcolor-tflite-float.zip)
37
- | TFLITE | w8a8 | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddcolor/releases/v0.47.0/ddcolor-tflite-w8a8.zip)
38
 
39
  For more device-specific assets and performance metrics, visit **[DDColor on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/ddcolor)**.
40
 
41
 
42
  ### Option 2: Export with Custom Configurations
43
 
44
- Use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/ddcolor) Python library to compile and export the model with your own:
45
  - Custom weights (e.g., fine-tuned checkpoints)
46
  - Custom input shapes
47
  - Target device and runtime configurations
48
 
49
  This option is ideal if you need to customize the model beyond the default configuration provided here.
50
 
51
- See our repository for [DDColor on GitHub](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/ddcolor) for usage instructions.
52
 
53
  ## Model Details
54
 
@@ -64,28 +63,28 @@ See our repository for [DDColor on GitHub](https://github.com/quic/ai-hub-models
64
  ## Performance Summary
65
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
66
  |---|---|---|---|---|---|---
67
- | DDColor | QNN_DLC | float | Snapdragon® X Elite | 1147.868 ms | 1 - 1 MB | NPU
68
- | DDColor | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 827.609 ms | 0 - 1372 MB | NPU
69
- | DDColor | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 1999.063 ms | 1 - 782 MB | NPU
70
- | DDColor | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 1099.417 ms | 1 - 460 MB | NPU
71
- | DDColor | QNN_DLC | float | Qualcomm® SA8775P | 1108.575 ms | 1 - 754 MB | NPU
72
- | DDColor | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 1202.858 ms | 0 - 484 MB | NPU
73
- | DDColor | QNN_DLC | float | Qualcomm® SA7255P | 1999.063 ms | 1 - 782 MB | NPU
74
- | DDColor | QNN_DLC | float | Qualcomm® SA8295P | 1260.185 ms | 1 - 409 MB | NPU
75
- | DDColor | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 832.825 ms | 0 - 782 MB | NPU
76
- | DDColor | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 681.166 ms | 0 - 728 MB | NPU
77
- | DDColor | QNN_DLC | float | Snapdragon® X2 Elite | 712.925 ms | 1 - 1 MB | NPU
78
- | DDColor | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1203.972 ms | 0 - 570 MB | NPU
79
- | DDColor | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 3033.483 ms | 0 - 332 MB | NPU
80
- | DDColor | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 1731.536 ms | 0 - 3 MB | NPU
81
- | DDColor | TFLITE | w8a8 | Qualcomm® SA8775P | 1729.814 ms | 0 - 332 MB | NPU
82
- | DDColor | TFLITE | w8a8 | Qualcomm® QCM6690 | 1749.173 ms | 10 - 411 MB | CPU
83
- | DDColor | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 2116.214 ms | 0 - 557 MB | NPU
84
- | DDColor | TFLITE | w8a8 | Qualcomm® SA7255P | 3033.483 ms | 0 - 332 MB | NPU
85
- | DDColor | TFLITE | w8a8 | Qualcomm® SA8295P | 2042.093 ms | 0 - 333 MB | NPU
86
- | DDColor | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 967.05 ms | 58 - 474 MB | NPU
87
- | DDColor | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 491.275 ms | 93 - 463 MB | CPU
88
- | DDColor | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 935.414 ms | 0 - 499 MB | NPU
89
 
90
  ## License
91
  * The license for the original implementation of DDColor can be found
 
14
  DDColor is a coloring algorithm that produces natural, vivid color results from incoming black and white images.
15
 
16
  This is based on the implementation of DDColor found [here](https://github.com/piddnad/DDColor/).
17
+ This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/ddcolor) 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
 
 
27
 
28
  | Runtime | Precision | Chipset | SDK Versions | Download |
29
  |---|---|---|---|---|
30
+ | ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddcolor/releases/v0.48.0/ddcolor-onnx-float.zip)
31
+ | ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddcolor/releases/v0.48.0/ddcolor-onnx-w8a16.zip)
32
+ | ONNX | w8a8 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddcolor/releases/v0.48.0/ddcolor-onnx-w8a8.zip)
33
+ | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddcolor/releases/v0.48.0/ddcolor-qnn_dlc-float.zip)
34
+ | QNN_DLC | w8a8 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddcolor/releases/v0.48.0/ddcolor-qnn_dlc-w8a8.zip)
35
+ | TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddcolor/releases/v0.48.0/ddcolor-tflite-float.zip)
36
+ | TFLITE | w8a8 | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddcolor/releases/v0.48.0/ddcolor-tflite-w8a8.zip)
 
37
 
38
  For more device-specific assets and performance metrics, visit **[DDColor on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/ddcolor)**.
39
 
40
 
41
  ### Option 2: Export with Custom Configurations
42
 
43
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/ddcolor) Python library to compile and export the model with your own:
44
  - Custom weights (e.g., fine-tuned checkpoints)
45
  - Custom input shapes
46
  - Target device and runtime configurations
47
 
48
  This option is ideal if you need to customize the model beyond the default configuration provided here.
49
 
50
+ See our repository for [DDColor on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/ddcolor) for usage instructions.
51
 
52
  ## Model Details
53
 
 
63
  ## Performance Summary
64
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
65
  |---|---|---|---|---|---|---
66
+ | DDColor | QNN_DLC | float | Snapdragon® X2 Elite | 710.859 ms | 1 - 1 MB | NPU
67
+ | DDColor | QNN_DLC | float | Snapdragon® X Elite | 1146.932 ms | 1 - 1 MB | NPU
68
+ | DDColor | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 827.209 ms | 0 - 1370 MB | NPU
69
+ | DDColor | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 2000.592 ms | 1 - 783 MB | NPU
70
+ | DDColor | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 1101.226 ms | 1 - 3 MB | NPU
71
+ | DDColor | QNN_DLC | float | Qualcomm® SA8775P | 1107.49 ms | 1 - 753 MB | NPU
72
+ | DDColor | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 1201.386 ms | 0 - 484 MB | NPU
73
+ | DDColor | QNN_DLC | float | Qualcomm® SA7255P | 2000.592 ms | 1 - 783 MB | NPU
74
+ | DDColor | QNN_DLC | float | Qualcomm® SA8295P | 1259.569 ms | 1 - 409 MB | NPU
75
+ | DDColor | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 836.361 ms | 1 - 785 MB | NPU
76
+ | DDColor | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 684.462 ms | 0 - 729 MB | NPU
77
+ | DDColor | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1204.165 ms | 0 - 563 MB | NPU
78
+ | DDColor | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 3031.363 ms | 1 - 332 MB | NPU
79
+ | DDColor | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 1734.301 ms | 0 - 3 MB | NPU
80
+ | DDColor | TFLITE | w8a8 | Qualcomm® SA8775P | 8243.529 ms | 2 - 333 MB | NPU
81
+ | DDColor | TFLITE | w8a8 | Qualcomm® QCM6690 | 1740.778 ms | 95 - 496 MB | CPU
82
+ | DDColor | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 2115.804 ms | 1 - 566 MB | NPU
83
+ | DDColor | TFLITE | w8a8 | Qualcomm® SA7255P | 3031.363 ms | 1 - 332 MB | NPU
84
+ | DDColor | TFLITE | w8a8 | Qualcomm® SA8295P | 2043.112 ms | 0 - 334 MB | NPU
85
+ | DDColor | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 967.968 ms | 0 - 414 MB | NPU
86
+ | DDColor | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 492.636 ms | 94 - 464 MB | CPU
87
+ | DDColor | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 939.886 ms | 0 - 498 MB | NPU
88
 
89
  ## License
90
  * The license for the original implementation of DDColor can be found