Merge branch 'develop' into encryption

doc/DOCKER_IMAGES.md

@@ -24,7 +24,6 @@ You can get images in two ways:
    ```
 
 
-   
 
 ## Image description
 
@@ -40,3 +39,13 @@ Runtime images cannot be used for compilation.
 |              GPU (cuda10.0-cudnn7) development               | CentOS7 | latest-cuda10.0-cudnn7-devel | [Dockerfile.cuda10.0-cudnn7.devel](../tools/Dockerfile.cuda10.0-cudnn7.devel) |
 |     CPU development (Used to compile packages on Ubuntu)     | CentOS6 |            <None>            | [Dockerfile.centos6.devel](../tools/Dockerfile.centos6.devel) |
 | GPU (cuda9.0-cudnn7) development (Used to compile packages on Ubuntu) | CentOS6 |            <None>            | [Dockerfile.centos6.cuda9.0-cudnn7.devel](../tools/Dockerfile.centos6.cuda9.0-cudnn7.devel) |
+
+
+
+## Requirements for running CUDA containers
+
+Running a CUDA container requires a machine with at least one CUDA-capable GPU and a driver compatible with the CUDA toolkit version you are using. 
+
+The machine running the CUDA container **only requires the NVIDIA driver**, the CUDA toolkit doesn't have to be installed.
+
+For the relationship between CUDA toolkit version, Driver version and GPU architecture, please refer to [nvidia-docker wiki](https://github.com/NVIDIA/nvidia-docker/wiki/CUDA).

doc/DOCKER_IMAGES_CN.md

@@ -22,7 +22,6 @@
    ```shell
    docker build -t <image-name>:<images-tag> .
    ```
-
    
 
 
@@ -40,3 +39,13 @@
 | GPU (cuda10.0-cudnn7) 开发镜像                     | CentOS7  | latest-cuda10.0-cudnn7-devel | [Dockerfile.cuda10.0-cudnn7.devel](../tools/Dockerfile.cuda10.0-cudnn7.devel) |
 | CPU 开发镜像 (用于编译 Ubuntu 包)                  | CentOS6  | <无>                         | [Dockerfile.centos6.devel](../tools/Dockerfile.centos6.devel) |
 | GPU (cuda9.0-cudnn7) 开发镜像 (用于编译 Ubuntu 包) | CentOS6  | <无>                         | [Dockerfile.centos6.cuda9.0-cudnn7.devel](../tools/Dockerfile.centos6.cuda9.0-cudnn7.devel) |
+
+
+
+## 运行CUDA容器的要求
+
+运行CUDA容器需要至少具有一个支持CUDA的GPU以及与您所使用的CUDA工具包版本兼容的驱动程序。
+
+运行CUDA容器的机器**只需要相应的NVIDIA驱动程序**，而CUDA工具包不是必要的。
+
+相关CUDA工具包版本、驱动版本和GPU架构的关系请参阅 [nvidia-docker wiki](https://github.com/NVIDIA/nvidia-docker/wiki/CUDA)。

python/examples/cascade_rcnn/test_client.py

+# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from paddle_serving_client import Client
+from paddle_serving_app.reader import *
+import numpy as np
+
+preprocess = Sequential([
+    File2Image(), BGR2RGB(), Div(255.0),
+    Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225], False),
+    Resize(800, 1333), Transpose((2, 0, 1)), PadStride(32)
+])
+postprocess = RCNNPostprocess("label_list.txt", "output")
+client = Client()
+client.load_client_config("serving_client/serving_client_conf.prototxt")
+client.connect(['127.0.0.1:9292'])
+im = preprocess('000000570688.jpg')
+fetch_map = client.predict(
+    feed={
+        "image": im,
+        "im_info": np.array(list(im.shape[1:]) + [1.0]),
+        "im_shape": np.array(list(im.shape[1:]) + [1.0])
+    },
+    fetch=["multiclass_nms_0.tmp_0"],
+    batch=True)
+fetch_map["image"] = '000000570688.jpg'
+print(fetch_map)
+postprocess(fetch_map)
+print(fetch_map)

python/examples/faster_rcnn_model/benchmark.py → python/examples/faster_rcnn/benchmark.py

@@ -29,13 +29,11 @@ from paddle_serving_app.reader import ChineseBertReader
 from paddle_serving_app.reader import *
 import numpy as np
 
-
-
 args = benchmark_args()
 
 
 def single_func(idx, resource):
-    img="./000000570688.jpg"
+    img = "./000000570688.jpg"
     profile_flags = False
     latency_flags = False
     if os.getenv("FLAGS_profile_client"):
@@ -67,10 +65,12 @@ def single_func(idx, resource):
                 for bi in range(args.batch_size):
                     print("1111batch")
                     print(bi)
-                    feed_batch.append({"image": im,
+                    feed_batch.append({
+                        "image": im,
                         "im_info": np.array(list(im.shape[1:]) + [1.0]),
-                        "im_shape": np.array(list(im.shape[1:]) + [1.0])})
-               # im = preprocess(img)
+                        "im_shape": np.array(list(im.shape[1:]) + [1.0])
+                    })
+            # im = preprocess(img)
                 b_end = time.time()
 
                 if profile_flags:
@@ -81,8 +81,7 @@ def single_func(idx, resource):
                             int(round(b_end * 1000000))))
                 #result = client.predict(feed=feed_batch, fetch=fetch)
                 fetch_map = client.predict(
-                    feed=feed_batch,
-                    fetch=["multiclass_nms"])
+                    feed=feed_batch, fetch=["multiclass_nms"])
                 fetch_map["image"] = img
                 postprocess(fetch_map)
 
@@ -102,13 +101,12 @@ def single_func(idx, resource):
 
 if __name__ == '__main__':
     multi_thread_runner = MultiThreadRunner()
-    endpoint_list = [
-        "127.0.0.1:7777"
-    ]
+    endpoint_list = ["127.0.0.1:7777"]
     turns = 10
     start = time.time()
     result = multi_thread_runner.run(
-        single_func, args.thread, {"endpoint": endpoint_list,"turns": turns})
+        single_func, args.thread, {"endpoint": endpoint_list,
+                                   "turns": turns})
     end = time.time()
     total_cost = end - start
 

python/examples/faster_rcnn/label_list.txt

+background
+person
+bicycle
+car
+motorcycle
+airplane
+bus
+train
+truck
+boat
+traffic light
+fire hydrant
+stop sign
+parking meter
+bench
+bird
+cat
+dog
+horse
+sheep
+cow
+elephant
+bear
+zebra
+giraffe
+backpack
+umbrella
+handbag
+tie
+suitcase
+frisbee
+skis
+snowboard
+sports ball
+kite
+baseball bat
+baseball glove
+skateboard
+surfboard
+tennis racket
+bottle
+wine glass
+cup
+fork
+knife
+spoon
+bowl
+banana
+apple
+sandwich
+orange
+broccoli
+carrot
+hot dog
+pizza
+donut
+cake
+chair
+couch
+potted plant
+bed
+dining table
+toilet
+tv
+laptop
+mouse
+remote
+keyboard
+cell phone
+microwave
+oven
+toaster
+sink
+refrigerator
+book
+clock
+vase
+scissors
+teddy bear
+hair drier
+toothbrush

python/examples/ocr/det_debugger_server.py

@@ -53,7 +53,9 @@ class OCRService(WebService):
         self.ori_h, self.ori_w, _ = im.shape
         det_img = self.det_preprocess(im)
         _, self.new_h, self.new_w = det_img.shape
-        return {"image": det_img[np.newaxis, :].copy()}, ["concat_1.tmp_0"]
+        return {
+            "image": det_img[np.newaxis, :].copy()
+        }, ["concat_1.tmp_0"], True
 
     def postprocess(self, feed={}, fetch=[], fetch_map=None):
         det_out = fetch_map["concat_1.tmp_0"]

python/examples/ocr/det_web_server.py

@@ -54,7 +54,7 @@ class OCRService(WebService):
         det_img = self.det_preprocess(im)
         _, self.new_h, self.new_w = det_img.shape
         print(det_img)
-        return {"image": det_img}, ["concat_1.tmp_0"]
+        return {"image": det_img}, ["concat_1.tmp_0"], False
 
     def postprocess(self, feed={}, fetch=[], fetch_map=None):
         det_out = fetch_map["concat_1.tmp_0"]

python/examples/ocr/ocr_debugger_server.py

@@ -42,10 +42,9 @@ class OCRService(WebService):
         self.det_client = LocalPredictor()
         if sys.argv[1] == 'gpu':
             self.det_client.load_model_config(
-                det_model_config, gpu=True, profile=False)
+                det_model_config, use_gpu=True, gpu_id=1)
         elif sys.argv[1] == 'cpu':
-            self.det_client.load_model_config(
-                det_model_config, gpu=False, profile=False)
+            self.det_client.load_model_config(det_model_config)
         self.ocr_reader = OCRReader()
 
     def preprocess(self, feed=[], fetch=[]):
@@ -58,7 +57,7 @@ class OCRService(WebService):
         det_img = det_img[np.newaxis, :]
         det_img = det_img.copy()
         det_out = self.det_client.predict(
-            feed={"image": det_img}, fetch=["concat_1.tmp_0"])
+            feed={"image": det_img}, fetch=["concat_1.tmp_0"], batch=True)
         filter_func = FilterBoxes(10, 10)
         post_func = DBPostProcess({
             "thresh": 0.3,
@@ -91,7 +90,7 @@ class OCRService(WebService):
             imgs[id] = norm_img
         feed = {"image": imgs.copy()}
         fetch = ["ctc_greedy_decoder_0.tmp_0", "softmax_0.tmp_0"]
-        return feed, fetch
+        return feed, fetch, True
 
     def postprocess(self, feed={}, fetch=[], fetch_map=None):
         rec_res = self.ocr_reader.postprocess(fetch_map, with_score=True)
@@ -107,7 +106,8 @@ ocr_service.load_model_config("ocr_rec_model")
 ocr_service.prepare_server(workdir="workdir", port=9292)
 ocr_service.init_det_debugger(det_model_config="ocr_det_model")
 if sys.argv[1] == 'gpu':
-    ocr_service.run_debugger_service(gpu=True)
+    ocr_service.set_gpus("2")
+    ocr_service.run_debugger_service()
 elif sys.argv[1] == 'cpu':
     ocr_service.run_debugger_service()
 ocr_service.run_web_service()

python/examples/ocr/ocr_web_client.py

@@ -36,4 +36,5 @@ for img_file in os.listdir(test_img_dir):
     image = cv2_to_base64(image_data1)
     data = {"feed": [{"image": image}], "fetch": ["res"]}
     r = requests.post(url=url, headers=headers, data=json.dumps(data))
+    print(r)
     print(r.json())

python/examples/ocr/ocr_web_server.py

@@ -50,7 +50,7 @@ class OCRService(WebService):
         ori_h, ori_w, _ = im.shape
         det_img = self.det_preprocess(im)
         det_out = self.det_client.predict(
-            feed={"image": det_img}, fetch=["concat_1.tmp_0"])
+            feed={"image": det_img}, fetch=["concat_1.tmp_0"], batch=False)
         _, new_h, new_w = det_img.shape
         filter_func = FilterBoxes(10, 10)
         post_func = DBPostProcess({
@@ -77,10 +77,10 @@ class OCRService(WebService):
             max_wh_ratio = max(max_wh_ratio, wh_ratio)
         for img in img_list:
             norm_img = self.ocr_reader.resize_norm_img(img, max_wh_ratio)
-            feed = {"image": norm_img}
-            feed_list.append(feed)
+            feed_list.append(norm_img[np.newaxis, :])
+        feed_batch = {"image": np.concatenate(feed_list, axis=0)}
         fetch = ["ctc_greedy_decoder_0.tmp_0", "softmax_0.tmp_0"]
-        return feed_list, fetch
+        return feed_batch, fetch, True
 
     def postprocess(self, feed={}, fetch=[], fetch_map=None):
         rec_res = self.ocr_reader.postprocess(fetch_map, with_score=True)

python/examples/ocr/rec_debugger_server.py

@@ -52,7 +52,7 @@ class OCRService(WebService):
             imgs[i] = norm_img
         feed = {"image": imgs.copy()}
         fetch = ["ctc_greedy_decoder_0.tmp_0", "softmax_0.tmp_0"]
-        return feed, fetch
+        return feed, fetch, True
 
     def postprocess(self, feed={}, fetch=[], fetch_map=None):
         rec_res = self.ocr_reader.postprocess(fetch_map, with_score=True)

python/examples/ocr/rec_web_server.py

@@ -51,10 +51,17 @@ class OCRService(WebService):
             max_wh_ratio = max(max_wh_ratio, wh_ratio)
         for img in img_list:
             norm_img = self.ocr_reader.resize_norm_img(img, max_wh_ratio)
-            feed = {"image": norm_img}
-            feed_list.append(feed)
+            #feed = {"image": norm_img}
+            feed_list.append(norm_img)
+        if len(feed_list) == 1:
+            feed_batch = {
+                "image": np.concatenate(
+                    feed_list, axis=0)[np.newaxis, :]
+            }
+        else:
+            feed_batch = {"image": np.concatenate(feed_list, axis=0)}
         fetch = ["ctc_greedy_decoder_0.tmp_0", "softmax_0.tmp_0"]
-        return feed_list, fetch
+        return feed_batch, fetch, True
 
     def postprocess(self, feed={}, fetch=[], fetch_map=None):
         rec_res = self.ocr_reader.postprocess(fetch_map, with_score=True)

python/paddle_serving_server/web_service.py

@@ -199,7 +199,7 @@ class WebService(object):
         from paddle_serving_app.local_predict import LocalPredictor
         self.client = LocalPredictor()
         self.client.load_model_config(
-            "{}".format(self.model_config), gpu=False, profile=False)
+            "{}".format(self.model_config), use_gpu=False)
 
     def run_web_service(self):
         print("This API will be deprecated later. Please do not use it")

python/paddle_serving_server_gpu/web_service.py

@@ -260,7 +260,7 @@ class WebService(object):
         from paddle_serving_app.local_predict import LocalPredictor
         self.client = LocalPredictor()
         self.client.load_model_config(
-            "{}".format(self.model_config), gpu=gpu, profile=False)
+            "{}".format(self.model_config), use_gpu=True, gpu_id=self.gpus[0])
 
     def run_web_service(self):
         print("This API will be deprecated later. Please do not use it")

python/setup.py.client.in

@@ -43,8 +43,8 @@ if '${PACK}' == 'ON':
     copy_lib()
 
 REQUIRED_PACKAGES = [
-    'six >= 1.10.0', 'protobuf >= 3.11.0', 'numpy >= 1.12', 'grpcio >= 1.28.1',
-    'grpcio-tools >= 1.28.1', 'requests'
+    'six >= 1.10.0', 'protobuf >= 3.11.0', 'numpy >= 1.12', 'grpcio <= 1.33.2',
+    'grpcio-tools <= 1.33.2'
 ]
 
 

python/setup.py.server.in

@@ -28,7 +28,7 @@ max_version, mid_version, min_version = util.python_version()
 util.gen_pipeline_code("paddle_serving_server")
 
 REQUIRED_PACKAGES = [
-    'six >= 1.10.0', 'protobuf >= 3.11.0', 'grpcio >= 1.28.1', 'grpcio-tools >= 1.28.1',
+    'six >= 1.10.0', 'protobuf >= 3.11.0', 'grpcio <= 1.33.2', 'grpcio-tools <= 1.33.2',
     'paddle_serving_client', 'flask >= 1.1.1', 'paddle_serving_app', 'func_timeout', 'pyyaml'
 ]
 

python/setup.py.server_gpu.in

@@ -30,7 +30,7 @@ max_version, mid_version, min_version = util.python_version()
 util.gen_pipeline_code("paddle_serving_server_gpu")
 
 REQUIRED_PACKAGES = [
-    'six >= 1.10.0', 'protobuf >= 3.11.0', 'grpcio >= 1.28.1', 'grpcio-tools >= 1.28.1',
+    'six >= 1.10.0', 'protobuf >= 3.11.0', 'grpcio <= 1.33.2', 'grpcio-tools <= 1.33.2',
     'paddle_serving_client', 'flask >= 1.1.1', 'paddle_serving_app', 'func_timeout', 'pyyaml'
 ]