update

README.md

@@ -28,6 +28,7 @@ pulsar2 build --config ./quant/bird-l.json
 
 For those who are interested in model conversion, you can try to export axmodel through 
 
+- [The original repo, Could get more details](https://github.com/wzf19947/Bird-Species-Classification)
 - [Pulsar2 Link, How to Convert ONNX to axmodel](https://pulsar2-docs.readthedocs.io/en/latest/pulsar2/introduction.html) 
 
 
@@ -193,6 +194,15 @@ Top5正确数: 16325 | Top5准确率: 91.24%
 
 # Bird Detect & Classify End2End Demo
 I've added a demo to do end2end inference with detection axmodel and recognition axmodel in 'model/bird-end2end'.
+
+| Models       | Platforms    | mAP@0.5       | latency      | CMM size(MB)  |
+| -------------| -------------| --------------| -------------| --------------|
+| bird_det     | AX630C       | 0.955         | 3.1ms        | 3.71          |
+
+| Models       | Platforms    | latency      | Top1 Accuracy | Top5 Accuracy | CMM size(MB)  |
+| -------------| -------------| -------------| --------------| --------------| --------------|
+| bird_rec     | AX630C       | 16.3ms       | 81.3%           | 91.2%       | 31.8          |
+
 Try to do bird object detect--->expand & crop--->classify with:
 ```
 python3 onnx_infer_end2end.py