add crnn int8(EN) (#98)

* add crnn int8 EN

* add crnn int8 (ch)

* revise models

* rename models

Author: Charles-258

models/text_recognition_crnn/README.md

@@ -8,10 +8,12 @@ Results of accuracy evaluation with [tools/eval](../../tools/eval) at different
 |--------------|------------|-----------|-----------|
 | CRNN_EN      | 81.66      | 74.33     | 52.78     |
 | CRNN_EN_FP16 | 82.01      | 74.93     | 52.34     |
+| CRNN_EN_INT8 | 81.75      | 75.33     | 52.43     |
 | CRNN_CH      | 71.28      | 80.90     | 67.36     |
 | CRNN_CH_FP16 | 78.63      | 80.93     | 67.01     |
+| CRNN_CH_INT8 | 78.03      | 80.93     | 66.67     |
 
-\*: 'FP16' stands for 'model quantized into FP16'.
+\*: 'FP16' or 'INT8' stands for 'model quantized into FP16' or 'model quantized into int8'
 
 Note:
 - Model source:

models/text_recognition_crnn/text_recognition_CRNN_CH_2021sep.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dc566fd01ac2118b25c6960508ebd758b64c421a2bfa78dc05401ada6737e0b
+size 64906971

models/text_recognition_crnn/text_recognition_CRNN_CH_FP16.onnx renamed to models/text_recognition_crnn/text_recognition_CRNN_CH_2022oct_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2bc75af1998c0b608f86ab875cbdcd109d18b27ff0d9872e7b7429fd1945f3a
+size 25783320

models/text_recognition_crnn/text_recognition_CRNN_CH_2022oct_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94117b4c2652337b3f1aef81b2ec15a74e97973b1c58f743e86380b95b95ffa2
+size 16378030