Hugging Face's logo

qualcomm
/
HRNet-W48-OCR

Image Segmentation
PyTorch
bu_auto
real_time
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
5fcef0f
·
verified ·
1 Parent(s): f1c627c

v0.47.0

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.47.0 for changelog.

Files changed (1) hide show
  1. README.md +11 -9
README.md CHANGED
@@ -29,9 +29,10 @@ Below are pre-exported model assets ready for deployment.
29
 
30
  | Runtime | Precision | Chipset | SDK Versions | Download |
31
  |---|---|---|---|---|
32
- | 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/hrnet_w48_ocr/releases/v0.46.0/hrnet_w48_ocr-onnx-float.zip)
33
- | QNN_DLC | w8a16 | Universal | QAIRT 2.42 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_w48_ocr/releases/v0.46.0/hrnet_w48_ocr-qnn_dlc-w8a16.zip)
34
- | TFLITE | float | Universal | TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_w48_ocr/releases/v0.46.0/hrnet_w48_ocr-tflite-float.zip)
 
35
 
36
  For more device-specific assets and performance metrics, visit **[HRNet-W48-OCR on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/hrnet_w48_ocr)**.
37
 
@@ -62,12 +63,13 @@ See our repository for [HRNet-W48-OCR on GitHub](https://github.com/quic/ai-hub-
62
  ## Performance Summary
63
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
64
  |---|---|---|---|---|---|---
65
- | HRNet-W48-OCR | ONNX | float | Snapdragon® X Elite | 990.193 ms | 150 - 150 MB | NPU
66
- | HRNet-W48-OCR | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 868.977 ms | 36 - 3980 MB | NPU
67
- | HRNet-W48-OCR | ONNX | float | Qualcomm® QCS8550 (Proxy) | 1168.136 ms | 24 - 28 MB | NPU
68
- | HRNet-W48-OCR | ONNX | float | Qualcomm® QCS9075 | 1384.373 ms | 24 - 51 MB | NPU
69
- | HRNet-W48-OCR | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 736.445 ms | 11 - 2506 MB | NPU
70
- | HRNet-W48-OCR | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 651.912 ms | 37 - 2597 MB | NPU
 
71
 
72
  ## License
73
  * The license for the original implementation of HRNet-W48-OCR can be found
 
29
 
30
  | Runtime | Precision | Chipset | SDK Versions | Download |
31
  |---|---|---|---|---|
32
+ | 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/hrnet_w48_ocr/releases/v0.47.0/hrnet_w48_ocr-onnx-float.zip)
33
+ | 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/hrnet_w48_ocr/releases/v0.47.0/hrnet_w48_ocr-onnx-w8a16.zip)
34
+ | QNN_DLC | w8a16 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_w48_ocr/releases/v0.47.0/hrnet_w48_ocr-qnn_dlc-w8a16.zip)
35
+ | TFLITE | float | Universal | TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_w48_ocr/releases/v0.47.0/hrnet_w48_ocr-tflite-float.zip)
36
 
37
  For more device-specific assets and performance metrics, visit **[HRNet-W48-OCR on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/hrnet_w48_ocr)**.
38
 
 
63
  ## Performance Summary
64
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
65
  |---|---|---|---|---|---|---
66
+ | HRNet-W48-OCR | ONNX | float | Snapdragon® X Elite | 1089.986 ms | 146 - 146 MB | NPU
67
+ | HRNet-W48-OCR | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 972.202 ms | 1 - 3922 MB | NPU
68
+ | HRNet-W48-OCR | ONNX | float | Qualcomm® QCS8550 (Proxy) | 1204.67 ms | 0 - 168 MB | NPU
69
+ | HRNet-W48-OCR | ONNX | float | Qualcomm® QCS9075 | 1389.278 ms | 24 - 51 MB | NPU
70
+ | HRNet-W48-OCR | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 784.286 ms | 13 - 2553 MB | NPU
71
+ | HRNet-W48-OCR | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 687.218 ms | 35 - 2714 MB | NPU
72
+ | HRNet-W48-OCR | ONNX | float | Snapdragon® X2 Elite | 636.212 ms | 148 - 148 MB | NPU
73
 
74
  ## License
75
  * The license for the original implementation of HRNet-W48-OCR can be found