update file description and reference

README.md

@@ -1,3 +1,31 @@
-# test_mlflow
+# Abstract
 
-測試使用MLflow紀錄Pytorch模型訓練，以及從Model registry中拉取Production model進行推論。
+Try to use [MLflow](https://mlflow.org) platform to log PyTorch model training, and pull production model from model registry to run inference⛩
+
+# Requirements
+
+* MacOS 12.5
+* Docker 20.10
+
+# Dir
+
+* **service**
+  * House MLflow service data, including MLflow artifacts, backend store and model registry
+
+# Files
+
+* **conda.yaml**
+  * conda env yaml to run this repo
+* **start_mlflow_server.sh**
+  * a script to start MLflow server with basic configuration
+* **test_pytorch_m1.py**
+  * a script to test PyTorch on Apple M1 platform with GPU acceleration
+* **train.py**
+  * a sample code to apply PyTorch to train a small neural network to predict fortune with MLflow logging
+* **predict.py**
+  * a sample code to call registered model to predict testing data and save model to local file system
+* **get_registered_model_via_rest_api.py**
+  * a script to test MLflow REST api
+
+
+###### tags: `MLOps`