Hugging Face's logo

qualcomm
/
DDColor

Image-to-Image
PyTorch
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
22d0c5e
·
verified ·
1 Parent(s): 4ee1af3

v0.60.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.60.0 for changelog.

Files changed (2) hide show
  1. README.md +52 -50
  2. release_assets.json +4 -4
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/qualcomm/ai-hub-models/blob/v0.59.0/src/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
 
@@ -27,80 +27,82 @@ Below are pre-exported model assets ready for deployment.
27
 
28
  | Runtime | Precision | Chipset | SDK Versions | Download |
29
  |---|---|---|---|---|
30
- | ONNX | float | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddcolor/releases/v0.59.0/ddcolor-onnx-float.zip)
31
- | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddcolor/releases/v0.59.0/ddcolor-qnn_dlc-float.zip)
32
- | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddcolor/releases/v0.59.0/ddcolor-tflite-float.zip)
33
 
34
  For more device-specific assets and performance metrics, visit **[DDColor on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/ddcolor)**.
35
 
36
 
37
  ### Option 2: Export with Custom Configurations
38
 
39
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.59.0/src/qai_hub_models/models/ddcolor) 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 [DDColor on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.59.0/src/qai_hub_models/models/ddcolor) for usage instructions.
47
 
48
  ## Model Details
49
 
50
  **Model Type:** Model_use_case.image_editing
51
 
52
  **Model Stats:**
53
- - Model checkpoint: ddcolor_paper_tiny.pth
54
  - Input resolution: 224x224
55
- - Number of parameters: 56.3M
56
  - Model size (float): 215 MB
57
  - Model size (w8a8): 54.8 MB
 
58
 
59
  ## Performance Summary
60
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
61
  |---|---|---|---|---|---|---
62
- | DDColor | ONNX | float | Snapdragon® X2 Elite | 28.048 ms | 2 - 2 MB | NPU
63
- | DDColor | ONNX | float | Snapdragon® X Elite | 72.597 ms | 112 - 112 MB | NPU
64
- | DDColor | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 44.686 ms | 2 - 1476 MB | NPU
65
- | DDColor | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 104.091 ms | 3 - 538 MB | NPU
66
- | DDColor | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 74.362 ms | 0 - 540 MB | NPU
67
- | DDColor | ONNX | float | Qualcomm® QCS8450 | 104.091 ms | 3 - 538 MB | NPU
68
- | DDColor | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 80.439 ms | 1 - 4 MB | NPU
69
- | DDColor | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 72.597 ms | 112 - 112 MB | NPU
70
- | DDColor | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 35.203 ms | 2 - 801 MB | NPU
71
- | DDColor | ONNX | float | Snapdragon® 8 Elite Mobile | 35.203 ms | 2 - 801 MB | NPU
72
- | DDColor | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 27.458 ms | 2 - 740 MB | NPU
73
- | DDColor | QNN_DLC | float | Snapdragon® X2 Elite | 27.744 ms | 1 - 1 MB | NPU
74
- | DDColor | QNN_DLC | float | Snapdragon® X Elite | 62.37 ms | 1 - 1 MB | NPU
75
- | DDColor | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 41.678 ms | 0 - 559 MB | NPU
76
- | DDColor | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 73.513 ms | 0 - 462 MB | NPU
77
- | DDColor | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8275 | 129.721 ms | 1 - 453 MB | NPU
78
- | DDColor | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 61.812 ms | 1 - 456 MB | NPU
79
- | DDColor | QNN_DLC | float | Qualcomm® SA8775P | 65.654 ms | 1 - 453 MB | NPU
80
- | DDColor | QNN_DLC | float | Qualcomm® SA8650P | 65.654 ms | 1 - 453 MB | NPU
81
- | DDColor | QNN_DLC | float | Qualcomm® SA8255P | 65.654 ms | 1 - 453 MB | NPU
82
- | DDColor | QNN_DLC | float | Qualcomm® QCS8450 | 73.513 ms | 0 - 462 MB | NPU
83
- | DDColor | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 66.151 ms | 1 - 4 MB | NPU
84
- | DDColor | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 62.37 ms | 1 - 1 MB | NPU
85
- | DDColor | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 31.297 ms | 1 - 620 MB | NPU
86
- | DDColor | QNN_DLC | float | Qualcomm® SA7255P | 129.721 ms | 1 - 453 MB | NPU
87
- | DDColor | QNN_DLC | float | Qualcomm® SA8295P | 69.55 ms | 0 - 330 MB | NPU
88
- | DDColor | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 31.297 ms | 1 - 620 MB | NPU
89
- | DDColor | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 27.368 ms | 0 - 642 MB | NPU
90
- | DDColor | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 42.944 ms | 1 - 1426 MB | NPU
91
- | DDColor | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 81.11 ms | 1 - 554 MB | NPU
92
- | DDColor | TFLITE | float | Qualcomm® Dragonwing™ QCS8275 | 124.433 ms | 1 - 802 MB | NPU
93
- | DDColor | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 67.966 ms | 1 - 4 MB | NPU
94
- | DDColor | TFLITE | float | Qualcomm® SA8775P | 72.388 ms | 1 - 851 MB | NPU
95
- | DDColor | TFLITE | float | Qualcomm® SA8650P | 72.388 ms | 1 - 851 MB | NPU
96
- | DDColor | TFLITE | float | Qualcomm® SA8255P | 72.388 ms | 1 - 851 MB | NPU
97
- | DDColor | TFLITE | float | Qualcomm® QCS8450 | 81.11 ms | 1 - 554 MB | NPU
98
- | DDColor | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 72.594 ms | 1 - 116 MB | NPU
99
- | DDColor | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 33.701 ms | 1 - 978 MB | NPU
100
- | DDColor | TFLITE | float | Qualcomm® SA7255P | 124.433 ms | 1 - 802 MB | NPU
101
- | DDColor | TFLITE | float | Qualcomm® SA8295P | 73.625 ms | 1 - 378 MB | NPU
102
- | DDColor | TFLITE | float | Snapdragon® 8 Elite Mobile | 33.701 ms | 1 - 978 MB | NPU
103
- | DDColor | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 27.498 ms | 1 - 1042 MB | NPU
 
 
104
 
105
  ## License
106
  * 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/v0.60.0/src/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 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddcolor/releases/v0.60.0/ddcolor-onnx-float.zip)
31
+ | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddcolor/releases/v0.60.0/ddcolor-qnn_dlc-float.zip)
32
+ | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddcolor/releases/v0.60.0/ddcolor-tflite-float.zip)
33
 
34
  For more device-specific assets and performance metrics, visit **[DDColor on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/ddcolor)**.
35
 
36
 
37
  ### Option 2: Export with Custom Configurations
38
 
39
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/ddcolor) 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 [DDColor on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/ddcolor) for usage instructions.
47
 
48
  ## Model Details
49
 
50
  **Model Type:** Model_use_case.image_editing
51
 
52
  **Model Stats:**
 
53
  - Input resolution: 224x224
54
+ - Model checkpoint: ddcolor_paper_tiny.pth
55
  - Model size (float): 215 MB
56
  - Model size (w8a8): 54.8 MB
57
+ - Number of parameters: 56.3M
58
 
59
  ## Performance Summary
60
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
61
  |---|---|---|---|---|---|---
62
+ | DDColor | ONNX | float | Snapdragon® X2 Elite | 28.234 ms | 2 - 2 MB | NPU
63
+ | DDColor | ONNX | float | Snapdragon® X Elite | 72.657 ms | 112 - 112 MB | NPU
64
+ | DDColor | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 46.486 ms | 2 - 1478 MB | NPU
65
+ | DDColor | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 84.249 ms | 0 - 635 MB | NPU
66
+ | DDColor | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 63.709 ms | 1 - 5 MB | NPU
67
+ | DDColor | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 73.662 ms | 0 - 131 MB | NPU
68
+ | DDColor | ONNX | float | Qualcomm® QCS8450 | 84.249 ms | 0 - 635 MB | NPU
69
+ | DDColor | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 82.17 ms | 1 - 4 MB | NPU
70
+ | DDColor | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 72.657 ms | 112 - 112 MB | NPU
71
+ | DDColor | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 35.3 ms | 2 - 804 MB | NPU
72
+ | DDColor | ONNX | float | Snapdragon® 8 Elite Mobile | 35.3 ms | 2 - 804 MB | NPU
73
+ | DDColor | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 27.433 ms | 2 - 740 MB | NPU
74
+ | DDColor | QNN_DLC | float | Snapdragon® X2 Elite | 27.781 ms | 1 - 1 MB | NPU
75
+ | DDColor | QNN_DLC | float | Snapdragon® X Elite | 62.334 ms | 1 - 1 MB | NPU
76
+ | DDColor | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 41.403 ms | 0 - 560 MB | NPU
77
+ | DDColor | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 73.083 ms | 0 - 461 MB | NPU
78
+ | DDColor | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 129.685 ms | 1 - 453 MB | NPU
79
+ | DDColor | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 62.053 ms | 1 - 3 MB | NPU
80
+ | DDColor | QNN_DLC | float | Qualcomm® SA8775P | 65.774 ms | 1 - 453 MB | NPU
81
+ | DDColor | QNN_DLC | float | Qualcomm® SA8650P | 65.774 ms | 1 - 453 MB | NPU
82
+ | DDColor | QNN_DLC | float | Qualcomm® SA8255P | 65.774 ms | 1 - 453 MB | NPU
83
+ | DDColor | QNN_DLC | float | Qualcomm® QCS8450 | 73.083 ms | 0 - 461 MB | NPU
84
+ | DDColor | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 66.715 ms | 1 - 4 MB | NPU
85
+ | DDColor | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 62.334 ms | 1 - 1 MB | NPU
86
+ | DDColor | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 32.09 ms | 0 - 616 MB | NPU
87
+ | DDColor | QNN_DLC | float | Qualcomm® SA7255P | 129.685 ms | 1 - 453 MB | NPU
88
+ | DDColor | QNN_DLC | float | Qualcomm® SA8295P | 69.458 ms | 0 - 330 MB | NPU
89
+ | DDColor | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 32.09 ms | 0 - 616 MB | NPU
90
+ | DDColor | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 27.381 ms | 0 - 642 MB | NPU
91
+ | DDColor | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 42.837 ms | 1 - 1422 MB | NPU
92
+ | DDColor | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 82.056 ms | 1 - 551 MB | NPU
93
+ | DDColor | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 57.889 ms | 1 - 117 MB | NPU
94
+ | DDColor | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 124.63 ms | 1 - 801 MB | NPU
95
+ | DDColor | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 68.464 ms | 0 - 162 MB | NPU
96
+ | DDColor | TFLITE | float | Qualcomm® SA8775P | 72.373 ms | 1 - 852 MB | NPU
97
+ | DDColor | TFLITE | float | Qualcomm® SA8650P | 72.373 ms | 1 - 852 MB | NPU
98
+ | DDColor | TFLITE | float | Qualcomm® SA8255P | 72.373 ms | 1 - 852 MB | NPU
99
+ | DDColor | TFLITE | float | Qualcomm® QCS8450 | 82.056 ms | 1 - 551 MB | NPU
100
+ | DDColor | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 71.974 ms | 1 - 116 MB | NPU
101
+ | DDColor | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 33.693 ms | 1 - 979 MB | NPU
102
+ | DDColor | TFLITE | float | Qualcomm® SA7255P | 124.63 ms | 1 - 801 MB | NPU
103
+ | DDColor | TFLITE | float | Qualcomm® SA8295P | 73.565 ms | 1 - 380 MB | NPU
104
+ | DDColor | TFLITE | float | Snapdragon® 8 Elite Mobile | 33.693 ms | 1 - 979 MB | NPU
105
+ | DDColor | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 27.539 ms | 1 - 1035 MB | NPU
106
 
107
  ## License
108
  * The license for the original implementation of DDColor can be found
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.59.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
@@ -8,19 +8,19 @@
8
  "qairt": "2.45.0.260326154327",
9
  "onnx_runtime": "1.27.1"
10
  },
11
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddcolor/releases/v0.59.0/ddcolor-onnx-float.zip"
12
  },
13
  "qnn_dlc": {
14
  "tool_versions": {
15
  "qairt": "2.45.0.260326154327"
16
  },
17
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddcolor/releases/v0.59.0/ddcolor-qnn_dlc-float.zip"
18
  },
19
  "tflite": {
20
  "tool_versions": {
21
  "qairt": "2.45.0.260326154327"
22
  },
23
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddcolor/releases/v0.59.0/ddcolor-tflite-float.zip"
24
  }
25
  }
26
  }
 
1
  {
2
+ "version": "0.60.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
 
8
  "qairt": "2.45.0.260326154327",
9
  "onnx_runtime": "1.27.1"
10
  },
11
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddcolor/releases/v0.60.0/ddcolor-onnx-float.zip"
12
  },
13
  "qnn_dlc": {
14
  "tool_versions": {
15
  "qairt": "2.45.0.260326154327"
16
  },
17
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddcolor/releases/v0.60.0/ddcolor-qnn_dlc-float.zip"
18
  },
19
  "tflite": {
20
  "tool_versions": {
21
  "qairt": "2.45.0.260326154327"
22
  },
23
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddcolor/releases/v0.60.0/ddcolor-tflite-float.zip"
24
  }
25
  }
26
  }