!21559 Add faq in modelzoo

Merge pull request !21559 from chenhaozhe/code_docs_add_modelzoo_fqa

model_zoo/README.md

@@ -113,3 +113,9 @@ MindSpore is Apache 2.0 licensed. Please see the LICENSE file.
 ## License
 
 [Apache License 2.0](https://gitee.com/mindspore/mindspore/blob/master/LICENSE)
+
+## FAQ
+
+- **Q: How to resolve the lack of memory while using `PYNATIVE_MODE` with errors such as *Failed to alloc memory pool memory*?**
+
+  **A**: `PYNATIVE_MODE` usually requires more memory than `GRAPH_MODE`, especially in training process which have to deal with back propagation. You could try using smaller batch size.

model_zoo/README_CN.md

@@ -113,3 +113,9 @@ MindSpore已获得Apache 2.0许可，请参见LICENSE文件。
 ## 许可证
 
 [Apache 2.0许可证](https://gitee.com/mindspore/mindspore/blob/master/LICENSE)
+
+## FAQ
+
+- **Q: 使用`PYNATIVE_MODE`运行模型出现错误内存不足，例如*Failed to alloc memory pool memory*, 该怎么处理?**
+
+  **A**: `PYNATIVE_MODE`通常比`GRAPH_MODE`使用更多内存，尤其是在需要进行反向传播计算的训练图中，你可以尝试使用一些更小的batch size.

model_zoo/official/nlp/bert/README.md

@@ -789,6 +789,8 @@ Please check the official [homepage](https://gitee.com/mindspore/mindspore/tree/
 
 # FAQ
 
+Refer to the [ModelZoo FAQ](https://gitee.com/mindspore/mindspore/tree/master/model_zoo#FAQ) for some common question.
+
 - **Q: How to resolve the continually overflow?**
 
   **A**: Continually overflow is usually caused by using too high learning rate.

model_zoo/official/nlp/bert/README_CN.md

@@ -747,6 +747,8 @@ run_pretrain.py中设置了随机种子，确保分布式训练中每个节点
 
 # FAQ
 
+优先参考[ModelZoo FAQ](https://gitee.com/mindspore/mindspore/tree/master/model_zoo#FAQ)来查找一些常见的公共问题。
+
 - **Q: 运行过程中发生持续溢出怎么办？**
   **A**： 持续溢出通常是因为使用了较高的学习率导致训练不收敛。可以考虑修改yaml配置文件中的参数，调低`learning_rate`来降低初始学习率或提高`power`加速学习率衰减。