Yuantao Feng
commited on
Commit
·
411de07
1
Parent(s):
5097b68
fix readme (#30)
Browse files- README.md +1 -1
- models/text_recognition_crnn/README.md +3 -3
README.md
CHANGED
@@ -17,11 +17,11 @@ Guidelines:
|
|
17 |
| Model | Input Size | INTEL-CPU | RPI-CPU | JETSON-GPU | D1-CPU |
|
18 |
|-------|------------|-----------|---------|------------|--------|
|
19 |
| [YuNet](./models/face_detection_yunet) | 160x120 | 1.45 | 6.22 | 12.18 | 86.69 |
|
|
|
20 |
| [DB-IC15](./models/text_detection_db) | 640x480 | 142.91 | 2835.91 | 208.41 | --- |
|
21 |
| [DB-TD500](./models/text_detection_db) | 640x480 | 142.91 | 2841.71 | 210.51 | --- |
|
22 |
| [CRNN-EN](./models/text_recognition_crnn) | 100x32 | 50.21 | 234.32 | 196.15 | --- |
|
23 |
| [CRNN-CN](./models/text_recognition_crnn) | 100x32 | 73.52 | 322.16 | 239.76 | --- |
|
24 |
-
| [SFace](./models/face_recognition_sface) | 112x112 | 8.65 | 99.20 | 24.88 | --- |
|
25 |
| [PP-ResNet](./models/image_classification_ppresnet) | 224x224 | 56.05 | 602.58 | 98.64 | --- |
|
26 |
| [PP-HumanSeg](./models/human_segmentation_pphumanseg) | 192x192 | 19.92 | 105.32 | 67.97 | --- |
|
27 |
| [WeChatQRCode](./models/qrcode_wechatqrcode) | 100x100 | 7.04 | 37.68 | --- | --- |
|
|
|
17 |
| Model | Input Size | INTEL-CPU | RPI-CPU | JETSON-GPU | D1-CPU |
|
18 |
|-------|------------|-----------|---------|------------|--------|
|
19 |
| [YuNet](./models/face_detection_yunet) | 160x120 | 1.45 | 6.22 | 12.18 | 86.69 |
|
20 |
+
| [SFace](./models/face_recognition_sface) | 112x112 | 8.65 | 99.20 | 24.88 | --- |
|
21 |
| [DB-IC15](./models/text_detection_db) | 640x480 | 142.91 | 2835.91 | 208.41 | --- |
|
22 |
| [DB-TD500](./models/text_detection_db) | 640x480 | 142.91 | 2841.71 | 210.51 | --- |
|
23 |
| [CRNN-EN](./models/text_recognition_crnn) | 100x32 | 50.21 | 234.32 | 196.15 | --- |
|
24 |
| [CRNN-CN](./models/text_recognition_crnn) | 100x32 | 73.52 | 322.16 | 239.76 | --- |
|
|
|
25 |
| [PP-ResNet](./models/image_classification_ppresnet) | 224x224 | 56.05 | 602.58 | 98.64 | --- |
|
26 |
| [PP-HumanSeg](./models/human_segmentation_pphumanseg) | 192x192 | 19.92 | 105.32 | 67.97 | --- |
|
27 |
| [WeChatQRCode](./models/qrcode_wechatqrcode) | 100x100 | 7.04 | 37.68 | --- | --- |
|
models/text_recognition_crnn/README.md
CHANGED
@@ -6,8 +6,8 @@ Note:
|
|
6 |
- Model source:
|
7 |
- `text_recognition_CRNN_EN_2021sep.onnx`: https://docs.opencv.org/4.5.2/d9/d1e/tutorial_dnn_OCR.html (CRNN_VGG_BiLSTM_CTC.onnx)
|
8 |
- `text_recognition_CRNN_CN_2021nov.onnx`: https://docs.opencv.org/4.5.2/d4/d43/tutorial_dnn_text_spotting.html (crnn_cs_CN.onnx)
|
9 |
-
- `text_recognition_CRNN_EN_2021sep.onnx` can detect digits (0
|
10 |
-
- `text_recognition_CRNN_CN_2021nov.onnx` can detect digits (0
|
11 |
- For details on training this model series, please visit https://github.com/zihaomu/deep-text-recognition-benchmark.
|
12 |
|
13 |
## Demo
|
@@ -44,4 +44,4 @@ All files in this directory are licensed under [Apache 2.0 License](./LICENSE).
|
|
44 |
- https://github.com/bgshih/crnn
|
45 |
- https://github.com/meijieru/crnn.pytorch
|
46 |
- https://github.com/zihaomu/deep-text-recognition-benchmark
|
47 |
-
- https://docs.opencv.org/4.5.2/d9/d1e/tutorial_dnn_OCR.html
|
|
|
6 |
- Model source:
|
7 |
- `text_recognition_CRNN_EN_2021sep.onnx`: https://docs.opencv.org/4.5.2/d9/d1e/tutorial_dnn_OCR.html (CRNN_VGG_BiLSTM_CTC.onnx)
|
8 |
- `text_recognition_CRNN_CN_2021nov.onnx`: https://docs.opencv.org/4.5.2/d4/d43/tutorial_dnn_text_spotting.html (crnn_cs_CN.onnx)
|
9 |
+
- `text_recognition_CRNN_EN_2021sep.onnx` can detect digits (0\~9) and letters (return lowercase letters a\~z) (view `charset_36_EN.txt` for details).
|
10 |
+
- `text_recognition_CRNN_CN_2021nov.onnx` can detect digits (0\~9), upper/lower-case letters (a\~z and A\~Z), some Chinese characters and some special characters (view `charset_3944_CN.txt` for details).
|
11 |
- For details on training this model series, please visit https://github.com/zihaomu/deep-text-recognition-benchmark.
|
12 |
|
13 |
## Demo
|
|
|
44 |
- https://github.com/bgshih/crnn
|
45 |
- https://github.com/meijieru/crnn.pytorch
|
46 |
- https://github.com/zihaomu/deep-text-recognition-benchmark
|
47 |
+
- https://docs.opencv.org/4.5.2/d9/d1e/tutorial_dnn_OCR.html
|