Hugging Face's logo

opencv
/
opencv_zoo

ONNX
Model card Files
xet
Community
Wanli commited on
Commit
b3310b1
·
1 Parent(s): 70423c2

update benchmarking results on arm platform (#80)

Browse files
Files changed (1) hide show
  1. README.md +15 -15
README.md CHANGED
@@ -16,21 +16,21 @@ Guidelines:
16
 
17
  | Model | Task | Input Size | INTEL-CPU (ms) | RPI-CPU (ms) | JETSON-GPU (ms) | KV3-NPU (ms) | D1-CPU (ms) |
18
  |-------|------|----------|----------------|--------------|-----------------|----------|-------------|
19
- | [YuNet](./models/face_detection_yunet) | Face Detection | 160x120 | 1.45 | 6.22 | 12.18 | 4.04 | 86.69 |
20
- | [SFace](./models/face_recognition_sface) | Face Recognition | 112x112 | 8.65 | 99.20 | 24.88 | 46.25 | --- |
21
- | [LPD-YuNet](./models/license_plate_detection_yunet/) | License Plate Detection | 320x240 | --- | 168.03 | 56.12 | 154.20\* | |
22
- | [DB-IC15](./models/text_detection_db) | Text Detection | 640x480 | 142.91 | 2835.91 | 208.41 | --- | --- |
23
- | [DB-TD500](./models/text_detection_db) | Text Detection | 640x480 | 142.91 | 2841.71 | 210.51 | --- | --- |
24
- | [CRNN-EN](./models/text_recognition_crnn) | Text Recognition | 100x32 | 50.21 | 234.32 | 196.15 | 125.30 | --- |
25
- | [CRNN-CN](./models/text_recognition_crnn) | Text Recognition | 100x32 | 73.52 | 322.16 | 239.76 | 166.79 | --- |
26
- | [PP-ResNet](./models/image_classification_ppresnet) | Image Classification | 224x224 | 56.05 | 602.58 | 98.64 | 75.45 | --- |
27
- | [MobileNet-V1](./models/image_classification_mobilenet) | Image Classification | 224x224 | 9.04 | 92.25 | 33.18 | 145.66\* | --- |
28
- | [MobileNet-V2](./models/image_classification_mobilenet) | Image Classification | 224x224 | 8.86 | 74.03 | 31.92 | 146.31\* | --- |
29
- | [PP-HumanSeg](./models/human_segmentation_pphumanseg) | Human Segmentation | 192x192 | 19.92 | 105.32 | 67.97 | 74.77 | --- |
30
- | [WeChatQRCode](./models/qrcode_wechatqrcode) | QR Code Detection and Parsing | 100x100 | 7.04 | 37.68 | --- | --- | --- |
31
- | [DaSiamRPN](./models/object_tracking_dasiamrpn) | Object Tracking | 1280x720 | 36.15 | 705.48 | 76.82 | --- | --- |
32
- | [YoutuReID](./models/person_reid_youtureid) | Person Re-Identification | 128x256 | 35.81 | 521.98 | 90.07 | 44.61 | --- |
33
- | [MPPalmDet](./models/palm_detection_mediapipe) | Palm Detection | 256x256 | 15.57 | 89.41 | 50.64 | 145.56\* | --- |
34
 
35
  \*: Models are quantized in per-channel mode, which run slower than per-tensor quantized models on NPU.
36
 
 
16
 
17
  | Model | Task | Input Size | INTEL-CPU (ms) | RPI-CPU (ms) | JETSON-GPU (ms) | KV3-NPU (ms) | D1-CPU (ms) |
18
  |-------|------|----------|----------------|--------------|-----------------|----------|-------------|
19
+ | [YuNet](./models/face_detection_yunet) | Face Detection | 160x120 | 1.45 | 5.21 | 12.18 | 4.04 | 86.69 |
20
+ | [SFace](./models/face_recognition_sface) | Face Recognition | 112x112 | 8.65 | 76.95 | 24.88 | 46.25 | --- |
21
+ | [LPD-YuNet](./models/license_plate_detection_yunet/) | License Plate Detection | 320x240 | --- | 134.02 | 56.12 | 154.20\* | |
22
+ | [DB-IC15](./models/text_detection_db) | Text Detection | 640x480 | 142.91 | 2456.49 | 208.41 | --- | --- |
23
+ | [DB-TD500](./models/text_detection_db) | Text Detection | 640x480 | 142.91 | 2572.10 | 210.51 | --- | --- |
24
+ | [CRNN-EN](./models/text_recognition_crnn) | Text Recognition | 100x32 | 50.21 | 230.50 | 196.15 | 125.30 | --- |
25
+ | [CRNN-CN](./models/text_recognition_crnn) | Text Recognition | 100x32 | 73.52 | 309.60 | 239.76 | 166.79 | --- |
26
+ | [PP-ResNet](./models/image_classification_ppresnet) | Image Classification | 224x224 | 56.05 | 440.90 | 98.64 | 75.45 | --- |
27
+ | [MobileNet-V1](./models/image_classification_mobilenet) | Image Classification | 224x224 | 9.04 | 67.97 | 33.18 | 145.66\* | --- |
28
+ | [MobileNet-V2](./models/image_classification_mobilenet) | Image Classification | 224x224 | 8.86 | 51.64 | 31.92 | 146.31\* | --- |
29
+ | [PP-HumanSeg](./models/human_segmentation_pphumanseg) | Human Segmentation | 192x192 | 19.92 | 94.40 | 67.97 | 74.77 | --- |
30
+ | [WeChatQRCode](./models/qrcode_wechatqrcode) | QR Code Detection and Parsing | 100x100 | 7.04 | 36.20 | --- | --- | --- |
31
+ | [DaSiamRPN](./models/object_tracking_dasiamrpn) | Object Tracking | 1280x720 | 36.15 | 683.90 | 76.82 | --- | --- |
32
+ | [YoutuReID](./models/person_reid_youtureid) | Person Re-Identification | 128x256 | 35.81 | 481.54 | 90.07 | 44.61 | --- |
33
+ | [MPPalmDet](./models/palm_detection_mediapipe) | Palm Detection | 256x256 | 15.57 | 168.37 | 50.64 | 145.56\* | --- |
34
 
35
  \*: Models are quantized in per-channel mode, which run slower than per-tensor quantized models on NPU.
36