Merge remote-tracking branch 'PaddlePaddle/dygraph' into dygraph

tools/infer/predict_system.py

@@ -13,6 +13,7 @@
 # limitations under the License.
 import os
 import sys
+import subprocess
 
 __dir__ = os.path.dirname(os.path.abspath(__file__))
 sys.path.append(__dir__)
@@ -141,6 +142,7 @@ def sorted_boxes(dt_boxes):
 
 def main(args):
     image_file_list = get_image_file_list(args.image_dir)
+    image_file_list = image_file_list[args.process_id::args.total_process_num]
     text_sys = TextSystem(args)
     is_visualize = True
     font_path = args.vis_font_path
@@ -184,4 +186,18 @@ def main(args):
 
 
 if __name__ == "__main__":
-    main(utility.parse_args())
+    args = utility.parse_args()
+    if args.use_mp:
+        p_list = []
+        total_process_num = args.total_process_num
+        for process_id in range(total_process_num):
+            cmd = [sys.executable, "-u"] + sys.argv + [
+                "--process_id={}".format(process_id),
+                "--use_mp={}".format(False)
+            ]
+            p = subprocess.Popen(cmd, stdout=sys.stdout, stderr=sys.stdout)
+            p_list.append(p)
+        for p in p_list:
+            p.wait()
+    else:
+        main(args)

tools/infer/utility.py

@@ -74,6 +74,20 @@ def parse_args():
         "--vis_font_path", type=str, default="./doc/fonts/simfang.ttf")
     parser.add_argument("--drop_score", type=float, default=0.5)
 
+    # params for e2e
+    parser.add_argument("--e2e_algorithm", type=str, default='PGNet')
+    parser.add_argument("--e2e_model_dir", type=str)
+    parser.add_argument("--e2e_limit_side_len", type=float, default=768)
+    parser.add_argument("--e2e_limit_type", type=str, default='max')
+
+    # PGNet parmas
+    parser.add_argument("--e2e_pgnet_score_thresh", type=float, default=0.5)
+    parser.add_argument(
+        "--e2e_char_dict_path", type=str, default="./ppocr/utils/ic15_dict.txt")
+    parser.add_argument("--e2e_pgnet_valid_set", type=str, default='totaltext')
+    parser.add_argument("--e2e_pgnet_polygon", type=bool, default=True)
+    parser.add_argument("--e2e_pgnet_mode", type=str, default='fast')
+
     # params for text classifier
     parser.add_argument("--use_angle_cls", type=str2bool, default=False)
     parser.add_argument("--cls_model_dir", type=str)
@@ -85,6 +99,10 @@ def parse_args():
     parser.add_argument("--enable_mkldnn", type=str2bool, default=False)
     parser.add_argument("--use_pdserving", type=str2bool, default=False)
 
+    parser.add_argument("--use_mp", type=str2bool, default=False)
+    parser.add_argument("--total_process_num", type=int, default=1)
+    parser.add_argument("--process_id", type=int, default=0)
+
     return parser.parse_args()
 
 
@@ -93,8 +111,10 @@ def create_predictor(args, mode, logger):
         model_dir = args.det_model_dir
     elif mode == 'cls':
         model_dir = args.cls_model_dir
-    else:
+    elif mode == 'rec':
         model_dir = args.rec_model_dir
+    else:
+        model_dir = args.e2e_model_dir
 
     if model_dir is None:
         logger.info("not find {} model file path {}".format(mode, model_dir))
@@ -148,6 +168,22 @@ def create_predictor(args, mode, logger):
     return predictor, input_tensor, output_tensors
 
 
+def draw_e2e_res(dt_boxes, strs, img_path):
+    src_im = cv2.imread(img_path)
+    for box, str in zip(dt_boxes, strs):
+        box = box.astype(np.int32).reshape((-1, 1, 2))
+        cv2.polylines(src_im, [box], True, color=(255, 255, 0), thickness=2)
+        cv2.putText(
+            src_im,
+            str,
+            org=(int(box[0, 0, 0]), int(box[0, 0, 1])),
+            fontFace=cv2.FONT_HERSHEY_COMPLEX,
+            fontScale=0.7,
+            color=(0, 255, 0),
+            thickness=1)
+    return src_im
+
+
 def draw_text_det_res(dt_boxes, img_path):
     src_im = cv2.imread(img_path)
     for box in dt_boxes:

tools/infer_e2e.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 __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import numpy as np
+
+import os
+import sys
+
+__dir__ = os.path.dirname(os.path.abspath(__file__))
+sys.path.append(__dir__)
+sys.path.append(os.path.abspath(os.path.join(__dir__, '..')))
+
+os.environ["FLAGS_allocator_strategy"] = 'auto_growth'
+
+import cv2
+import json
+import paddle
+
+from ppocr.data import create_operators, transform
+from ppocr.modeling.architectures import build_model
+from ppocr.postprocess import build_post_process
+from ppocr.utils.save_load import init_model
+from ppocr.utils.utility import get_image_file_list
+import tools.program as program
+
+
+def draw_e2e_res(dt_boxes, strs, config, img, img_name):
+    if len(dt_boxes) > 0:
+        src_im = img
+        for box, str in zip(dt_boxes, strs):
+            box = box.astype(np.int32).reshape((-1, 1, 2))
+            cv2.polylines(src_im, [box], True, color=(255, 255, 0), thickness=2)
+            cv2.putText(
+                src_im,
+                str,
+                org=(int(box[0, 0, 0]), int(box[0, 0, 1])),
+                fontFace=cv2.FONT_HERSHEY_COMPLEX,
+                fontScale=0.7,
+                color=(0, 255, 0),
+                thickness=1)
+        save_det_path = os.path.dirname(config['Global'][
+            'save_res_path']) + "/e2e_results/"
+        if not os.path.exists(save_det_path):
+            os.makedirs(save_det_path)
+        save_path = os.path.join(save_det_path, os.path.basename(img_name))
+        cv2.imwrite(save_path, src_im)
+        logger.info("The e2e Image saved in {}".format(save_path))
+
+
+def main():
+    global_config = config['Global']
+
+    # build model
+    model = build_model(config['Architecture'])
+
+    init_model(config, model, logger)
+
+    # build post process
+    post_process_class = build_post_process(config['PostProcess'],
+                                            global_config)
+
+    # create data ops
+    transforms = []
+    for op in config['Eval']['dataset']['transforms']:
+        op_name = list(op)[0]
+        if 'Label' in op_name:
+            continue
+        elif op_name == 'KeepKeys':
+            op[op_name]['keep_keys'] = ['image', 'shape']
+        transforms.append(op)
+
+    ops = create_operators(transforms, global_config)
+
+    save_res_path = config['Global']['save_res_path']
+    if not os.path.exists(os.path.dirname(save_res_path)):
+        os.makedirs(os.path.dirname(save_res_path))
+
+    model.eval()
+    with open(save_res_path, "wb") as fout:
+        for file in get_image_file_list(config['Global']['infer_img']):
+            logger.info("infer_img: {}".format(file))
+            with open(file, 'rb') as f:
+                img = f.read()
+                data = {'image': img}
+            batch = transform(data, ops)
+            images = np.expand_dims(batch[0], axis=0)
+            shape_list = np.expand_dims(batch[1], axis=0)
+            images = paddle.to_tensor(images)
+            preds = model(images)
+            post_result = post_process_class(preds, shape_list)
+            points, strs = post_result['points'], post_result['strs']
+            # write resule
+            dt_boxes_json = []
+            for poly, str in zip(points, strs):
+                tmp_json = {"transcription": str}
+                tmp_json['points'] = poly.tolist()
+                dt_boxes_json.append(tmp_json)
+            otstr = file + "\t" + json.dumps(dt_boxes_json) + "\n"
+            fout.write(otstr.encode())
+            src_img = cv2.imread(file)
+            draw_e2e_res(points, strs, config, src_img, file)
+    logger.info("success!")
+
+
+if __name__ == '__main__':
+    config, device, logger, vdl_writer = program.preprocess()
+    main()

tools/program.py

@@ -237,8 +237,9 @@ def train(config,
                     vdl_writer.add_scalar('TRAIN/{}'.format(k), v, global_step)
                 vdl_writer.add_scalar('TRAIN/lr', lr, global_step)
 
-            if dist.get_rank(
-            ) == 0 and global_step > 0 and global_step % print_batch_step == 0:
+            if dist.get_rank() == 0 and (
+                (global_step > 0 and global_step % print_batch_step == 0) or
+                (idx >= len(train_dataloader) - 1)):
                 logs = train_stats.log()
                 strs = 'epoch: [{}/{}], iter: {}, {}, reader_cost: {:.5f} s, batch_cost: {:.5f} s, samples: {}, ips: {:.5f}'.format(
                     epoch, epoch_num, global_step, logs, train_reader_cost /
@@ -374,7 +375,8 @@ def preprocess(is_train=False):
 
     alg = config['Architecture']['algorithm']
     assert alg in [
-        'EAST', 'DB', 'SAST', 'Rosetta', 'CRNN', 'STARNet', 'RARE', 'SRN', 'CLS'
+        'EAST', 'DB', 'SAST', 'Rosetta', 'CRNN', 'STARNet', 'RARE', 'SRN',
+        'CLS', 'PGNet'
     ]
 
     device = 'gpu:{}'.format(dist.ParallelEnv().dev_id) if use_gpu else 'cpu'

tools/train.py

@@ -52,7 +52,10 @@ def main(config, device, logger, vdl_writer):
     train_dataloader = build_dataloader(config, 'Train', device, logger)
     if len(train_dataloader) == 0:
         logger.error(
-            'No Images in train dataset, please check annotation file and path in the configuration file'
+            "No Images in train dataset, please ensure\n" +
+            "\t1. The images num in the train label_file_list should be larger than or equal with batch size.\n"
+            +
+            "\t2. The annotation file and path in the configuration file are provided normally."
         )
         return