Darknet encryption

python/examples/pipeline/PaddleClas/DarkNet53-encryption/README.md

@@ -0,0 +1,23 @@
+# Imagenet Pipeline WebService
+
+This document will takes Imagenet service as an example to introduce how to use Pipeline WebService.
+
+## Get model
+```
+sh get_model.sh
+python encrypt.py
+```
+
+## Start server
+
+```
+python -m paddle_serving_server.serve --model encrypt_server/ --port 9400  --encryption_rpc_port 9401  --use_encryption_model &
+python web_service.py &>log.txt &
+```
+
+## client test
+```
+python http_client.py
+```
+
+if you configure the api gateway, you can use `https_client.py`

python/examples/pipeline/PaddleClas/DarkNet53-encryption/README_CN.md

@@ -0,0 +1,24 @@
+# Imagenet Pipeline WebService
+
+这里以 Imagenet 服务为例来介绍 Pipeline WebService 的使用。
+
+## 获取模型
+```
+sh get_model.sh
+python encrypt.py
+```
+
+## 启动服务
+
+```
+python -m paddle_serving_server.serve --model encrypt_server/ --port 9400  --encryption_rpc_port 9401  --use_encryption_model &
+python web_service.py &>log.txt &
+```
+
+## 测试
+```
+python http_client.py
+```
+如果您已经配置好了api gateway， 您可以使用 `https_client.py`
+
+~

python/examples/pipeline/PaddleClas/DarkNet53-encryption/config.yml

@@ -0,0 +1,25 @@
+#worker_num, 最大并发数。当build_dag_each_worker=True时, 框架会创建worker_num个进程，每个进程内构建grpcSever和DAG
+##当build_dag_each_worker=False时，框架会设置主线程grpc线程池的max_workers=worker_num
+worker_num: 1
+
+#http端口, rpc_port和http_port不允许同时为空。当rpc_port可用且http_port为空时，不自动生成http_port
+http_port: 18080
+rpc_port: 9993
+
+dag:
+    #op资源类型, True, 为线程模型；False，为进程模型
+    is_thread_op: False
+op:
+    imagenet:
+        #并发数，is_thread_op=True时，为线程并发；否则为进程并发
+        concurrency: 1
+        client_type: brpc
+        retry: 1
+        timeout: 3000
+        server_endpoints: ["127.0.0.1:9400"]
+        client_config: "encrypt_client"
+        fetch_list: ["save_infer_model/scale_0.tmp_0"]
+        batch_size: 1
+        auto_batching_timeout: 2000
+        use_encryption_model: True
+        encryption_key: "./key" 

python/examples/pipeline/PaddleClas/DarkNet53-encryption/encrypt.py

@@ -0,0 +1,15 @@
+from paddle_serving_client.io import inference_model_to_serving
+
+
+def serving_encryption():
+    inference_model_to_serving(
+        dirname="./DarkNet53/ppcls_model/",
+        model_filename="__model__",
+        params_filename="./__params__",
+        serving_server="encrypt_server",
+        serving_client="encrypt_client",
+        encryption=True)
+
+
+if __name__ == "__main__":
+    serving_encryption()

python/examples/pipeline/PaddleClas/DarkNet53-encryption/get_model.sh

@@ -0,0 +1,5 @@
+wget --no-check-certificate https://paddle-serving.bj.bcebos.com/model/DarkNet53.tar
+tar -xf DarkNet53.tar
+
+wget --no-check-certificate https://paddle-serving.bj.bcebos.com/imagenet-example/image_data.tar.gz
+tar -xzvf image_data.tar.gz

python/examples/pipeline/PaddleClas/DarkNet53-encryption/http_client.py

@@ -0,0 +1,20 @@
+import numpy as np
+import requests
+import json
+import cv2
+import base64
+import os
+
+def cv2_to_base64(image):
+    return base64.b64encode(image).decode('utf8')
+
+if __name__ == "__main__":
+    url = "http://127.0.0.1:18080/imagenet/prediction"
+    with open(os.path.join(".", "daisy.jpg"), 'rb') as file:
+        image_data1 = file.read()
+    image = cv2_to_base64(image_data1)
+    header = {"Content-Type":"application/json", "apikey":"WeJn7tVjuujtGxBgl6cWRGpmL2VMEBdb", "X-INSTANCE-ID" : "kong_ins10"}
+    data = {"key": ["image"], "value": [image]}
+    for i in range(1):
+        r = requests.post(url=url, data=json.dumps(data))
+        print(r.json())

python/examples/pipeline/PaddleClas/DarkNet53-encryption/https_client.py

@@ -0,0 +1,20 @@
+import numpy as np
+import requests
+import json
+import cv2
+import base64
+import os
+
+def cv2_to_base64(image):
+    return base64.b64encode(image).decode('utf8')
+
+if __name__ == "__main__":
+    url = "https://10.21.8.132:8443/image-clas/imagenet/prediction"
+    with open(os.path.join(".", "daisy.jpg"), 'rb') as file:
+        image_data1 = file.read()
+    image = cv2_to_base64(image_data1)
+    headers = {"Content-Type":"application/json", "apikey":"BlfvO08Z9mQpFjcMagl2dxOIA8h2UVdp", "X-INSTANCE-ID" : "kong_ins10"}
+    data = {"key": ["image"], "value": [image]}
+    for i in range(1):
+        r = requests.post(url=url, headers=headers, data=json.dumps(data),verify=False)
+        print(r.json())