ocr_gpu

python/examples/pipeline/ocr_gpu/README.md

+# OCR Pipeline WebService 
+
+(English|[简体中文](./README_CN.md))
+
+This document will take OCR as an example to show how to use Pipeline WebService to start multi-model tandem services.
+
+## Get Model
+```
+python -m paddle_serving_app.package --get_model ocr_rec
+tar -xzvf ocr_rec.tar.gz
+python -m paddle_serving_app.package --get_model ocr_det
+tar -xzvf ocr_det.tar.gz
+```
+
+## Get Dataset (Optional)
+```
+wget --no-check-certificate https://paddle-serving.bj.bcebos.com/ocr/test_imgs.tar
+tar xf test_imgs.tar
+```
+
+## Start Service
+```
+python web_service.py &>log.txt &
+```
+
+## Test
+```
+python pipeline_http_client.py
+```
+
+
+
+<!--
+## More (PipelineServing)
+
+You can choose one of the following versions to start Service.
+
+### Remote Service Version
+```
+python -m paddle_serving_server_gpu.serve --model ocr_det_model --port 12000 --gpu_id 0 &> det.log &
+python -m paddle_serving_server_gpu.serve --model ocr_rec_model --port 12001 --gpu_id 0 &> rec.log &
+python remote_service_pipeline_server.py &>pipeline.log &
+```
+
+### Local Service Version
+```
+python local_service_pipeline_server.py &>pipeline.log &
+```
+
+### Hybrid Service Version
+```
+python -m paddle_serving_server_gpu.serve --model ocr_rec_model --port 12001 --gpu_id 0 &> rec.log &
+python hybrid_service_pipeline_server.py &>pipeline.log &
+```
+
+## Client Prediction
+
+### RPC
+```
+python pipeline_rpc_client.py
+```
+
+### HTTP
+```
+python pipeline_http_client.py
+```
+-->

python/examples/pipeline/ocr_gpu/local_service.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.
+try:
+    from paddle_serving_server_gpu.web_service import WebService, Op
+except ImportError:
+    from paddle_serving_server_gpu.web_service import WebService, Op
+import logging
+import numpy as np
+import cv2
+import base64
+from paddle_serving_app.reader import OCRReader
+from paddle_serving_app.reader import Sequential, ResizeByFactor
+from paddle_serving_app.reader import Div, Normalize, Transpose
+from paddle_serving_app.reader import DBPostProcess, FilterBoxes, GetRotateCropImage, SortedBoxes
+
+_LOGGER = logging.getLogger()
+
+
+class DetOp(Op):
+    def init_op(self):
+        self.det_preprocess = Sequential([
+            ResizeByFactor(32, 960), Div(255),
+            Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]), Transpose(
+                (2, 0, 1))
+        ])
+        self.filter_func = FilterBoxes(10, 10)
+        self.post_func = DBPostProcess({
+            "thresh": 0.3,
+            "box_thresh": 0.5,
+            "max_candidates": 1000,
+            "unclip_ratio": 1.5,
+            "min_size": 3
+        })
+
+    def preprocess(self, input_dicts):
+        (_, input_dict), = input_dicts.items()
+        data = base64.b64decode(input_dict["image"].encode('utf8'))
+        data = np.fromstring(data, np.uint8)
+        # Note: class variables(self.var) can only be used in process op mode
+        self.im = cv2.imdecode(data, cv2.IMREAD_COLOR)
+        self.ori_h, self.ori_w, _ = self.im.shape
+        det_img = self.det_preprocess(self.im)
+        _, self.new_h, self.new_w = det_img.shape
+        with open("in.npy", 'wb') as f:
+            np.save(f, det_img[np.newaxis,:])
+        return {"image": det_img[np.newaxis,:].copy()}
+
+    def postprocess(self, input_dicts, fetch_dict):
+        det_out = fetch_dict["concat_1.tmp_0"]
+        ratio_list = [
+            float(self.new_h) / self.ori_h, float(self.new_w) / self.ori_w
+        ]
+        dt_boxes_list = self.post_func(det_out, [ratio_list])
+        dt_boxes = self.filter_func(dt_boxes_list[0], [self.ori_h, self.ori_w])
+        out_dict = {"dt_boxes": dt_boxes, "image": self.im}
+        return out_dict
+
+
+class RecOp(Op):
+    def init_op(self):
+        self.ocr_reader = OCRReader()
+        self.get_rotate_crop_image = GetRotateCropImage()
+        self.sorted_boxes = SortedBoxes()
+
+    def preprocess(self, input_dicts):
+        (_, input_dict), = input_dicts.items()
+        im = input_dict["image"]
+        dt_boxes = input_dict["dt_boxes"]
+        dt_boxes = self.sorted_boxes(dt_boxes)
+        feed_list = []
+        img_list = []
+        max_wh_ratio = 0
+        for i, dtbox in enumerate(dt_boxes):
+            boximg = self.get_rotate_crop_image(im, dt_boxes[i])
+            img_list.append(boximg)
+            h, w = boximg.shape[0:2]
+            wh_ratio = w * 1.0 / h
+            max_wh_ratio = max(max_wh_ratio, wh_ratio)
+        _, w, h = self.ocr_reader.resize_norm_img(img_list[0],
+                                                  max_wh_ratio).shape
+        imgs = np.zeros((len(img_list), 3, w, h)).astype('float32')
+        for id, img in enumerate(img_list):
+            norm_img = self.ocr_reader.resize_norm_img(img, max_wh_ratio)
+            imgs[id] = norm_img
+        feed = {"image": imgs.copy()}
+        return feed
+
+    def postprocess(self, input_dicts, fetch_dict):
+        rec_res = self.ocr_reader.postprocess(fetch_dict, with_score=True)
+        res_lst = []
+        for res in rec_res:
+            res_lst.append(res[0])
+        res = {"res": str(res_lst)}
+        return res
+
+
+class OcrService(WebService):
+    def get_pipeline_response(self, read_op):
+        det_op = DetOp(name="det", input_ops=[read_op])
+        rec_op = RecOp(name="rec", input_ops=[det_op])
+        return rec_op
+
+
+uci_service = OcrService(name="ocr")
+uci_service.prepare_pipeline_config("config.yml")
+uci_service.run_service()

python/examples/pipeline/ocr_gpu/pipeline_http_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_server_gpu.pipeline import PipelineClient
+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')
+
+
+url = "http://127.0.0.1:9999/ocr/prediction"
+test_img_dir = "test_imgs/rctw_samples/"
+for img_file in os.listdir(test_img_dir):
+    with open(os.path.join(test_img_dir, img_file), 'rb') as file:
+        image_data1 = file.read()
+    image = cv2_to_base64(image_data1)
+    data = {"key": ["image"], "value": [image]}
+    r = requests.post(url=url, data=json.dumps(data))
+    js = r.json()
+    print(js)
+    break
+    if "error_info" in js:
+        print("receive error exit")