add two quantized models(FP16)

Charles-258 · Charles-258 · commit 5e89b2a598e0 · 2022-08-02T14:07:18.000+08:00
diff --git a/models/text_recognition_crnn/README.md b/models/text_recognition_crnn/README.md
@@ -7,7 +7,10 @@ Results of accuracy evaluation with [tools/eval](../../tools/eval).
 | Models | Accuracy(%) |
 | ------ | -------------- |
 | CRNN_EN | 81.66 |
+| CRNN_EN_FP16 | 82.01 |
 | CRNN_CH | 71.28 |
+| CRNN_CH_FP16 | 78.63 |
+\*: 'FP16' stands for 'model quantized into FP16'.
 
 Note:
 - Model source:
diff --git a/models/text_recognition_crnn/text_recognition_CRNN_CH_FP16.onnx b/models/text_recognition_crnn/text_recognition_CRNN_CH_FP16.onnx
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bd15eb1fee92dfef94d79ec10d3985997a876101b9721b19ee23ea327f48d4f
+size 32469497
diff --git a/models/text_recognition_crnn/text_recognition_CRNN_EN_FP16.onnx b/models/text_recognition_crnn/text_recognition_CRNN_EN_FP16.onnx
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd4805b4a4a20ce4dd6948d9209694911c15906e7f7d0da7af5f161c3e3cc301
+size 16915979

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,3 @@`
	`1`	`+version https://git-lfs.github.com/spec/v1`
	`2`	`+oid sha256:3bd15eb1fee92dfef94d79ec10d3985997a876101b9721b19ee23ea327f48d4f`
	`3`	`+size 32469497`
Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,3 @@`
	`1`	`+version https://git-lfs.github.com/spec/v1`
	`2`	`+oid sha256:fd4805b4a4a20ce4dd6948d9209694911c15906e7f7d0da7af5f161c3e3cc301`
	`3`	`+size 16915979`