Other
PyTorch
android
qaihm-bot commited on
Commit
5c0edac
·
verified ·
1 Parent(s): 0ff2117

See https://github.com/qualcomm/ai-hub-models/releases/v0.51.0 for changelog.

Files changed (2) hide show
  1. README.md +46 -38
  2. release_assets.json +46 -1
README.md CHANGED
@@ -27,10 +27,11 @@ 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 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.50.2/cvt-onnx-float.zip)
31
- | ONNX | w8a16_mixed_fp16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.50.2/cvt-onnx-w8a16_mixed_fp16.zip)
32
- | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.50.2/cvt-qnn_dlc-float.zip)
33
- | TFLITE | float | Universal | QAIRT 2.43, TFLite 2.19.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.50.2/cvt-tflite-float.zip)
 
34
 
35
  For more device-specific assets and performance metrics, visit **[CVT on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/cvt)**.
36
 
@@ -60,40 +61,47 @@ See our repository for [CVT on GitHub](https://github.com/qualcomm/ai-hub-models
60
  ## Performance Summary
61
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
62
  |---|---|---|---|---|---|---
63
- | CVT | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 183.261 ms | 8 - 2259 MB | NPU
64
- | CVT | ONNX | float | Snapdragon® X2 Elite | 181.596 ms | 20 - 20 MB | NPU
65
- | CVT | ONNX | float | Snapdragon® X Elite | 284.158 ms | 18 - 18 MB | NPU
66
- | CVT | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 249.776 ms | 8 - 2579 MB | NPU
67
- | CVT | ONNX | float | Qualcomm® QCS8550 (Proxy) | 336.501 ms | 0 - 25 MB | NPU
68
- | CVT | ONNX | float | Qualcomm® QCS9075 | 326.612 ms | 7 - 10 MB | NPU
69
- | CVT | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 190.129 ms | 5 - 2223 MB | NPU
70
- | CVT | ONNX | w8a16_mixed_fp16 | Snapdragon® 8 Elite Gen 5 Mobile | 260.79 ms | 62 - 1220 MB | NPU
71
- | CVT | ONNX | w8a16_mixed_fp16 | Snapdragon® X2 Elite | 255.715 ms | 69 - 69 MB | NPU
72
- | CVT | ONNX | w8a16_mixed_fp16 | Snapdragon® X Elite | 424.841 ms | 70 - 70 MB | NPU
73
- | CVT | ONNX | w8a16_mixed_fp16 | Snapdragon® 8 Gen 3 Mobile | 365.931 ms | 58 - 2557 MB | NPU
74
- | CVT | ONNX | w8a16_mixed_fp16 | Snapdragon® 8 Elite For Galaxy Mobile | 277.338 ms | 57 - 1050 MB | NPU
75
- | CVT | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 167.529 ms | 7 - 2257 MB | NPU
76
- | CVT | QNN_DLC | float | Snapdragon® X2 Elite | 180.883 ms | 7 - 7 MB | NPU
77
- | CVT | QNN_DLC | float | Snapdragon® X Elite | 279.839 ms | 7 - 7 MB | NPU
78
- | CVT | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 222.043 ms | 6 - 2553 MB | NPU
79
- | CVT | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 420.185 ms | 1 - 2187 MB | NPU
80
- | CVT | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 333.586 ms | 7 - 10 MB | NPU
81
- | CVT | QNN_DLC | float | Qualcomm® SA8775P | 291.639 ms | 2 - 2187 MB | NPU
82
- | CVT | QNN_DLC | float | Qualcomm® QCS9075 | 323.621 ms | 7 - 16 MB | NPU
83
- | CVT | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 442.643 ms | 6 - 2647 MB | NPU
84
- | CVT | QNN_DLC | float | Qualcomm® SA7255P | 420.185 ms | 1 - 2187 MB | NPU
85
- | CVT | QNN_DLC | float | Qualcomm® SA8295P | 333.101 ms | 1 - 2241 MB | NPU
86
- | CVT | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 184.94 ms | 7 - 2170 MB | NPU
87
- | CVT | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 181.707 ms | 0 - 2244 MB | NPU
88
- | CVT | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 226.435 ms | 0 - 2561 MB | NPU
89
- | CVT | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 425.499 ms | 0 - 2194 MB | NPU
90
- | CVT | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 311.817 ms | 0 - 4 MB | NPU
91
- | CVT | TFLITE | float | Qualcomm® SA8775P | 296.258 ms | 0 - 2193 MB | NPU
92
- | CVT | TFLITE | float | Qualcomm® QCS9075 | 326.991 ms | 0 - 35 MB | NPU
93
- | CVT | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 461.625 ms | 1 - 2670 MB | NPU
94
- | CVT | TFLITE | float | Qualcomm® SA7255P | 425.499 ms | 0 - 2194 MB | NPU
95
- | CVT | TFLITE | float | Qualcomm® SA8295P | 337.147 ms | 0 - 2230 MB | NPU
96
- | CVT | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 187.619 ms | 0 - 2258 MB | NPU
 
 
 
 
 
 
 
97
 
98
  ## License
99
  * The license for the original implementation of CVT can be found
 
27
 
28
  | Runtime | Precision | Chipset | SDK Versions | Download |
29
  |---|---|---|---|---|
30
+ | ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.51.0/cvt-onnx-float.zip)
31
+ | ONNX | w8a16_mixed_fp16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.51.0/cvt-onnx-w8a16_mixed_fp16.zip)
32
+ | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.51.0/cvt-qnn_dlc-float.zip)
33
+ | QNN_DLC | w8a16_mixed_fp16 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.51.0/cvt-qnn_dlc-w8a16_mixed_fp16.zip)
34
+ | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.51.0/cvt-tflite-float.zip)
35
 
36
  For more device-specific assets and performance metrics, visit **[CVT on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/cvt)**.
37
 
 
61
  ## Performance Summary
62
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
63
  |---|---|---|---|---|---|---
64
+ | CVT | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 183.433 ms | 8 - 2258 MB | NPU
65
+ | CVT | ONNX | float | Snapdragon® X2 Elite | 183.052 ms | 20 - 20 MB | NPU
66
+ | CVT | ONNX | float | Snapdragon® X Elite | 282.825 ms | 18 - 18 MB | NPU
67
+ | CVT | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 224.699 ms | 8 - 2578 MB | NPU
68
+ | CVT | ONNX | float | Qualcomm® QCS8550 (Proxy) | 318.335 ms | 0 - 24 MB | NPU
69
+ | CVT | ONNX | float | Qualcomm® QCS9075 | 326.55 ms | 7 - 10 MB | NPU
70
+ | CVT | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 188.812 ms | 3 - 2222 MB | NPU
71
+ | CVT | ONNX | w8a16_mixed_fp16 | Snapdragon® 8 Elite Gen 5 Mobile | 216.427 ms | 6 - 1317 MB | NPU
72
+ | CVT | ONNX | w8a16_mixed_fp16 | Snapdragon® X2 Elite | 221.839 ms | 18 - 18 MB | NPU
73
+ | CVT | ONNX | w8a16_mixed_fp16 | Snapdragon® X Elite | 355.386 ms | 15 - 15 MB | NPU
74
+ | CVT | ONNX | w8a16_mixed_fp16 | Snapdragon® 8 Gen 3 Mobile | 303.476 ms | 6 - 1626 MB | NPU
75
+ | CVT | ONNX | w8a16_mixed_fp16 | Snapdragon® 8 Elite For Galaxy Mobile | 253.463 ms | 4 - 1117 MB | NPU
76
+ | CVT | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 179.073 ms | 7 - 2308 MB | NPU
77
+ | CVT | QNN_DLC | float | Snapdragon® X2 Elite | 181.432 ms | 7 - 7 MB | NPU
78
+ | CVT | QNN_DLC | float | Snapdragon® X Elite | 270.434 ms | 7 - 7 MB | NPU
79
+ | CVT | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 227.639 ms | 7 - 2588 MB | NPU
80
+ | CVT | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 328.998 ms | 0 - 1092 MB | NPU
81
+ | CVT | QNN_DLC | float | Qualcomm® QCS9075 | 324.86 ms | 7 - 17 MB | NPU
82
+ | CVT | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 439.412 ms | 6 - 2717 MB | NPU
83
+ | CVT | QNN_DLC | float | Qualcomm® SA8295P | 336.32 ms | 0 - 2330 MB | NPU
84
+ | CVT | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 185.53 ms | 7 - 2383 MB | NPU
85
+ | CVT | QNN_DLC | w8a16_mixed_fp16 | Snapdragon® 8 Elite Gen 5 Mobile | 203.486 ms | 4 - 2395 MB | NPU
86
+ | CVT | QNN_DLC | w8a16_mixed_fp16 | Snapdragon® X2 Elite | 206.333 ms | 4 - 4 MB | NPU
87
+ | CVT | QNN_DLC | w8a16_mixed_fp16 | Snapdragon® X Elite | 320.411 ms | 4 - 4 MB | NPU
88
+ | CVT | QNN_DLC | w8a16_mixed_fp16 | Snapdragon® 8 Gen 3 Mobile | 245.379 ms | 4 - 2556 MB | NPU
89
+ | CVT | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® QCS8275 (Proxy) | 472.502 ms | 2 - 2284 MB | NPU
90
+ | CVT | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® QCS8550 (Proxy) | 357.202 ms | 4 - 1500 MB | NPU
91
+ | CVT | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® SA8775P | 323.593 ms | 0 - 2282 MB | NPU
92
+ | CVT | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® QCS9075 | 395.971 ms | 5 - 11 MB | NPU
93
+ | CVT | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® SA7255P | 472.502 ms | 2 - 2284 MB | NPU
94
+ | CVT | QNN_DLC | w8a16_mixed_fp16 | Snapdragon® 8 Elite For Galaxy Mobile | 211.53 ms | 4 - 2347 MB | NPU
95
+ | CVT | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 174.276 ms | 0 - 2332 MB | NPU
96
+ | CVT | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 233.495 ms | 0 - 2667 MB | NPU
97
+ | CVT | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 434.684 ms | 0 - 2303 MB | NPU
98
+ | CVT | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 324.164 ms | 0 - 4 MB | NPU
99
+ | CVT | TFLITE | float | Qualcomm® SA8775P | 302.238 ms | 0 - 2303 MB | NPU
100
+ | CVT | TFLITE | float | Qualcomm® QCS9075 | 331.09 ms | 0 - 36 MB | NPU
101
+ | CVT | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 443.407 ms | 0 - 2740 MB | NPU
102
+ | CVT | TFLITE | float | Qualcomm® SA7255P | 434.684 ms | 0 - 2303 MB | NPU
103
+ | CVT | TFLITE | float | Qualcomm® SA8295P | 346.35 ms | 0 - 2304 MB | NPU
104
+ | CVT | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 193.625 ms | 0 - 2398 MB | NPU
105
 
106
  ## License
107
  * The license for the original implementation of CVT can be found
release_assets.json CHANGED
@@ -1 +1,46 @@
1
- {"version":"0.50.2","precisions":{"float":{"universal_assets":{"onnx":{"tool_versions":{"qairt":"2.42.0.251225135753_193295","onnx_runtime":"1.24.3"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.50.2/cvt-onnx-float.zip"},"qnn_dlc":{"tool_versions":{"qairt":"2.43.0.260127150333_193827"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.50.2/cvt-qnn_dlc-float.zip"},"tflite":{"tool_versions":{"qairt":"2.43.0.260127150333_193827","tflite":"2.19.1"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.50.2/cvt-tflite-float.zip"}}},"w8a16_mixed_fp16":{"universal_assets":{"onnx":{"tool_versions":{"qairt":"2.42.0.251225135753_193295","onnx_runtime":"1.24.3"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.50.2/cvt-onnx-w8a16_mixed_fp16.zip"}}}}}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "0.51.0",
3
+ "precisions": {
4
+ "float": {
5
+ "universal_assets": {
6
+ "tflite": {
7
+ "tool_versions": {
8
+ "qairt": "2.45.0.260326154327",
9
+ "litert": "1.4.2"
10
+ },
11
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.51.0/cvt-tflite-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/cvt/releases/v0.51.0/cvt-qnn_dlc-float.zip"
18
+ },
19
+ "onnx": {
20
+ "tool_versions": {
21
+ "qairt": "2.42.0.251225135753_193295",
22
+ "onnx_runtime": "1.24.3"
23
+ },
24
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.51.0/cvt-onnx-float.zip"
25
+ }
26
+ }
27
+ },
28
+ "w8a16_mixed_fp16": {
29
+ "universal_assets": {
30
+ "qnn_dlc": {
31
+ "tool_versions": {
32
+ "qairt": "2.45.0.260326154327"
33
+ },
34
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.51.0/cvt-qnn_dlc-w8a16_mixed_fp16.zip"
35
+ },
36
+ "onnx": {
37
+ "tool_versions": {
38
+ "qairt": "2.42.0.251225135753_193295",
39
+ "onnx_runtime": "1.24.3"
40
+ },
41
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.51.0/cvt-onnx-w8a16_mixed_fp16.zip"
42
+ }
43
+ }
44
+ }
45
+ }
46
+ }