Merge branch 'develop' into update_docs

README.md

@@ -4,7 +4,7 @@
     <img src="./docs/images/logo.png" align="middle" width = "500" />
   </p>
 
-  **基于飞桨框架开发的高性能遥感影像处理开发套件，帮助您端到端地完成从数据预处理到模型部署的全流程遥感深度学习应用。**
+  **飞桨高性能遥感影像开发套件，端到端完成从数据到部署的全流程遥感应用。**
 
   <!-- [![version](https://img.shields.io/github/release/PaddlePaddle/PaddleRS.svg)](https://github.com/PaddlePaddle/PaddleRS/releases) -->
   [![license](https://img.shields.io/badge/license-Apache%202-blue.svg)](LICENSE)

paddlers/deploy/predictor.py

@@ -146,7 +146,7 @@ class Predictor(object):
         return predictor
 
     def preprocess(self, images, transforms):
-        preprocessed_samples = self._model._preprocess(
+        preprocessed_samples = self._model.preprocess(
             images, transforms, to_tensor=False)
         if self._model.model_type == 'classifier':
             preprocessed_samples = {'image': preprocessed_samples[0]}
@@ -172,12 +172,12 @@ class Predictor(object):
     def postprocess(self, net_outputs, topk=1, ori_shape=None, transforms=None):
         if self._model.model_type == 'classifier':
             true_topk = min(self._model.num_classes, topk)
-            if self._model._postprocess is None:
+            if self._model.postprocess is None:
                 self._model.build_postprocess_from_labels(topk)
-            # XXX: Convert ndarray to tensor as self._model._postprocess requires
+            # XXX: Convert ndarray to tensor as self._model.postprocess requires
             assert len(net_outputs) == 1
             net_outputs = paddle.to_tensor(net_outputs[0])
-            outputs = self._model._postprocess(net_outputs)
+            outputs = self._model.postprocess(net_outputs)
             class_ids = map(itemgetter('class_ids'), outputs)
             scores = map(itemgetter('scores'), outputs)
             label_names = map(itemgetter('label_names'), outputs)
@@ -187,7 +187,7 @@ class Predictor(object):
                 'label_names_map': n,
             } for l, s, n in zip(class_ids, scores, label_names)]
         elif self._model.model_type in ('segmenter', 'change_detector'):
-            label_map, score_map = self._model._postprocess(
+            label_map, score_map = self._model.postprocess(
                 net_outputs,
                 batch_origin_shape=ori_shape,
                 transforms=transforms.transforms)
@@ -200,7 +200,7 @@ class Predictor(object):
                 k: v
                 for k, v in zip(['bbox', 'bbox_num', 'mask'], net_outputs)
             }
-            preds = self._model._postprocess(net_outputs)
+            preds = self._model.postprocess(net_outputs)
         else:
             logging.error(
                 "Invalid model type {}.".format(self._model.model_type),

paddlers/tasks/change_detector.py

@@ -113,10 +113,10 @@ class BaseChangeDetector(BaseModel):
         if mode == 'test':
             origin_shape = inputs[2]
             if self.status == 'Infer':
-                label_map_list, score_map_list = self._postprocess(
+                label_map_list, score_map_list = self.postprocess(
                     net_out, origin_shape, transforms=inputs[3])
             else:
-                logit_list = self._postprocess(
+                logit_list = self.postprocess(
                     logit, origin_shape, transforms=inputs[3])
                 label_map_list = []
                 score_map_list = []
@@ -144,7 +144,7 @@ class BaseChangeDetector(BaseModel):
                 raise ValueError("Expected label.ndim == 4 but got {}".format(
                     label.ndim))
             origin_shape = [label.shape[-2:]]
-            pred = self._postprocess(
+            pred = self.postprocess(
                 pred, origin_shape, transforms=inputs[3])[0]  # NCHW
             intersect_area, pred_area, label_area = ppseg.utils.metrics.calculate_area(
                 pred, label, self.num_classes)
@@ -549,7 +549,7 @@ class BaseChangeDetector(BaseModel):
             images = [img_file]
         else:
             images = img_file
-        batch_im1, batch_im2, batch_origin_shape = self._preprocess(
+        batch_im1, batch_im2, batch_origin_shape = self.preprocess(
             images, transforms, self.model_type)
         self.net.eval()
         data = (batch_im1, batch_im2, batch_origin_shape, transforms.transforms)
@@ -660,7 +660,7 @@ class BaseChangeDetector(BaseModel):
         dst_data = None
         print("GeoTiff saved in {}.".format(save_file))
 
-    def _preprocess(self, images, transforms, to_tensor=True):
+    def preprocess(self, images, transforms, to_tensor=True):
         self._check_transforms(transforms, 'test')
         batch_im1, batch_im2 = list(), list()
         batch_ori_shape = list()
@@ -732,7 +732,7 @@ class BaseChangeDetector(BaseModel):
             batch_restore_list.append(restore_list)
         return batch_restore_list
 
-    def _postprocess(self, batch_pred, batch_origin_shape, transforms):
+    def postprocess(self, batch_pred, batch_origin_shape, transforms):
         batch_restore_list = BaseChangeDetector.get_transforms_shape_info(
             batch_origin_shape, transforms)
         if isinstance(batch_pred, (tuple, list)) and self.status == 'Infer':

paddlers/tasks/classifier.py

@@ -62,7 +62,7 @@ class BaseClassifier(BaseModel):
         self.metrics = None
         self.losses = losses
         self.labels = None
-        self._postprocess = None
+        self.postprocess = None
         if params.get('with_net', True):
             params.pop('with_net', None)
             self.net = self.build_net(**params)
@@ -122,13 +122,12 @@ class BaseClassifier(BaseModel):
         net_out = net(inputs[0])
 
         if mode == 'test':
-            return self._postprocess(net_out)
+            return self.postprocess(net_out)
 
         outputs = OrderedDict()
         label = paddle.to_tensor(inputs[1], dtype="int64")
 
         if mode == 'eval':
-            # print(self._postprocess(net_out)[0])  # for test
             label = paddle.unsqueeze(label, axis=-1)
             metric_dict = self.metrics(net_out, label)
             outputs['top1'] = metric_dict["top1"]
@@ -177,13 +176,13 @@ class BaseClassifier(BaseModel):
         label_dict = dict()
         for i, label in enumerate(self.labels):
             label_dict[i] = label
-        self._postprocess = build_postprocess({
+        self.postprocess = build_postprocess({
             "name": "Topk",
             "topk": topk,
             "class_id_map_file": None
         })
         # Add class_id_map from model.yml
-        self._postprocess.class_id_map = label_dict
+        self.postprocess.class_id_map = label_dict
 
     def train(self,
               num_epochs,
@@ -248,8 +247,7 @@ class BaseClassifier(BaseModel):
         if self.losses is None:
             self.losses = self.default_loss()
         self.metrics = self.default_metric()
-        self._postprocess = self.default_postprocess(train_dataset.label_list)
-        # print(self._postprocess.class_id_map)
+        self.postprocess = self.default_postprocess(train_dataset.label_list)
 
         if optimizer is None:
             num_steps_each_epoch = train_dataset.num_samples // train_batch_size
@@ -457,12 +455,12 @@ class BaseClassifier(BaseModel):
             images = [img_file]
         else:
             images = img_file
-        batch_im, batch_origin_shape = self._preprocess(images, transforms,
-                                                        self.model_type)
+        batch_im, batch_origin_shape = self.preprocess(images, transforms,
+                                                       self.model_type)
         self.net.eval()
         data = (batch_im, batch_origin_shape, transforms.transforms)
 
-        if self._postprocess is None:
+        if self.postprocess is None:
             self.build_postprocess_from_labels()
 
         outputs = self.run(self.net, data, 'test')
@@ -483,7 +481,7 @@ class BaseClassifier(BaseModel):
             }
         return prediction
 
-    def _preprocess(self, images, transforms, to_tensor=True):
+    def preprocess(self, images, transforms, to_tensor=True):
         self._check_transforms(transforms, 'test')
         batch_im = list()
         batch_ori_shape = list()

paddlers/tasks/object_detector.py

@@ -249,6 +249,34 @@ class BaseDetector(BaseModel):
                 Defaults to None.
         """
 
+        args = self._pre_train(locals())
+        return self._real_train(**args)
+
+    def _pre_train(self, in_args):
+        return in_args
+
+    def _real_train(self,
+                    num_epochs,
+                    train_dataset,
+                    train_batch_size=64,
+                    eval_dataset=None,
+                    optimizer=None,
+                    save_interval_epochs=1,
+                    log_interval_steps=10,
+                    save_dir='output',
+                    pretrain_weights='IMAGENET',
+                    learning_rate=.001,
+                    warmup_steps=0,
+                    warmup_start_lr=0.0,
+                    lr_decay_epochs=(216, 243),
+                    lr_decay_gamma=0.1,
+                    metric=None,
+                    use_ema=False,
+                    early_stop=False,
+                    early_stop_patience=5,
+                    use_vdl=True,
+                    resume_checkpoint=None):
+
         if self.status == 'Infer':
             logging.error(
                 "Exported inference model does not support training.",
@@ -582,16 +610,16 @@ class BaseDetector(BaseModel):
         else:
             images = img_file
 
-        batch_samples = self._preprocess(images, transforms)
+        batch_samples = self.preprocess(images, transforms)
         self.net.eval()
         outputs = self.run(self.net, batch_samples, 'test')
-        prediction = self._postprocess(outputs)
+        prediction = self.postprocess(outputs)
 
         if isinstance(img_file, (str, np.ndarray)):
             prediction = prediction[0]
         return prediction
 
-    def _preprocess(self, images, transforms, to_tensor=True):
+    def preprocess(self, images, transforms, to_tensor=True):
         self._check_transforms(transforms, 'test')
         batch_samples = list()
         for im in images:
@@ -608,7 +636,7 @@ class BaseDetector(BaseModel):
 
         return batch_samples
 
-    def _postprocess(self, batch_pred):
+    def postprocess(self, batch_pred):
         infer_result = {}
         if 'bbox' in batch_pred:
             bboxes = batch_pred['bbox']
@@ -879,108 +907,24 @@ class PicoDet(BaseDetector):
         self.fixed_input_shape = image_shape
         return self._define_input_spec(image_shape)
 
-    def train(self,
-              num_epochs,
-              train_dataset,
-              train_batch_size=64,
-              eval_dataset=None,
-              optimizer=None,
-              save_interval_epochs=1,
-              log_interval_steps=10,
-              save_dir='output',
-              pretrain_weights='IMAGENET',
-              learning_rate=.001,
-              warmup_steps=0,
-              warmup_start_lr=0.0,
-              lr_decay_epochs=(216, 243),
-              lr_decay_gamma=0.1,
-              metric=None,
-              use_ema=False,
-              early_stop=False,
-              early_stop_patience=5,
-              use_vdl=True,
-              resume_checkpoint=None):
-        """
-        Train the model.
-
-        Args:
-            num_epochs (int): Number of epochs.
-            train_dataset (paddlers.datasets.COCODetDataset|paddlers.datasets.VOCDetDataset): 
-                Training dataset.
-            train_batch_size (int, optional): Total batch size among all cards used in 
-                training. Defaults to 64.
-            eval_dataset (paddlers.datasets.COCODetDataset|paddlers.datasets.VOCDetDataset|None, optional): 
-                Evaluation dataset. If None, the model will not be evaluated during training 
-                process. Defaults to None.
-            optimizer (paddle.optimizer.Optimizer|None, optional): Optimizer used for 
-                training. If None, a default optimizer will be used. Defaults to None.
-            save_interval_epochs (int, optional): Epoch interval for saving the model. 
-                Defaults to 1.
-            log_interval_steps (int, optional): Step interval for printing training 
-                information. Defaults to 10.
-            save_dir (str, optional): Directory to save the model. Defaults to 'output'.
-            pretrain_weights (str|None, optional): None or name/path of pretrained 
-                weights. If None, no pretrained weights will be loaded. 
-                Defaults to 'IMAGENET'.
-            learning_rate (float, optional): Learning rate for training. Defaults to .001.
-            warmup_steps (int, optional): Number of steps of warm-up training. 
-                Defaults to 0.
-            warmup_start_lr (float, optional): Start learning rate of warm-up training. 
-                Defaults to 0..
-            lr_decay_epochs (list|tuple, optional): Epoch milestones for learning 
-                rate decay. Defaults to (216, 243).
-            lr_decay_gamma (float, optional): Gamma coefficient of learning rate decay. 
-                Defaults to .1.
-            metric (str|None, optional): Evaluation metric. Choices are {'VOC', 'COCO', None}. 
-                If None, determine the metric according to the  dataset format. 
-                Defaults to None.
-            use_ema (bool, optional): Whether to use exponential moving average 
-                strategy. Defaults to False.
-            early_stop (bool, optional): Whether to adopt early stop strategy. 
-                Defaults to False.
-            early_stop_patience (int, optional): Early stop patience. Defaults to 5.
-            use_vdl(bool, optional): Whether to use VisualDL to monitor the training 
-                process. Defaults to True.
-            resume_checkpoint (str|None, optional): Path of the checkpoint to resume
-                training from. If None, no training checkpoint will be resumed. At most
-                Aone of `resume_checkpoint` and `pretrain_weights` can be set simultaneously.
-                Defaults to None.
-        """
-
+    def _pre_train(self, in_args):
+        optimizer = in_args['optimizer']
         if optimizer is None:
-            num_steps_each_epoch = len(train_dataset) // train_batch_size
+            num_steps_each_epoch = len(in_args['train_dataset']) // in_args[
+                'train_batch_size']
             optimizer = self.default_optimizer(
                 parameters=self.net.parameters(),
-                learning_rate=learning_rate,
-                warmup_steps=warmup_steps,
-                warmup_start_lr=warmup_start_lr,
-                lr_decay_epochs=lr_decay_epochs,
-                lr_decay_gamma=lr_decay_gamma,
-                num_steps_each_epoch=num_steps_each_epoch,
+                learning_rate=in_args['learning_rate'],
+                warmup_steps=in_args['warmup_steps'],
+                warmup_start_lr=in_args['warmup_start_lr'],
+                lr_decay_epochs=in_args['lr_decay_epochs'],
+                lr_decay_gamma=in_args['lr_decay_gamma'],
+                num_steps_each_epoch=in_args['num_steps_each_epoch'],
                 reg_coeff=4e-05,
                 scheduler='Cosine',
-                num_epochs=num_epochs)
-        super(PicoDet, self).train(
-            num_epochs=num_epochs,
-            train_dataset=train_dataset,
-            train_batch_size=train_batch_size,
-            eval_dataset=eval_dataset,
-            optimizer=optimizer,
-            save_interval_epochs=save_interval_epochs,
-            log_interval_steps=log_interval_steps,
-            save_dir=save_dir,
-            pretrain_weights=pretrain_weights,
-            learning_rate=learning_rate,
-            warmup_steps=warmup_steps,
-            warmup_start_lr=warmup_start_lr,
-            lr_decay_epochs=lr_decay_epochs,
-            lr_decay_gamma=lr_decay_gamma,
-            metric=metric,
-            use_ema=use_ema,
-            early_stop=early_stop,
-            early_stop_patience=early_stop_patience,
-            use_vdl=use_vdl,
-            resume_checkpoint=resume_checkpoint)
+                num_epochs=in_args['num_epochs'])
+            in_args['optimizer'] = optimizer
+        return in_args
 
 
 class YOLOv3(BaseDetector):
@@ -1372,82 +1316,12 @@ class FasterRCNN(BaseDetector):
         super(FasterRCNN, self).__init__(
             model_name='FasterRCNN', num_classes=num_classes, **params)
 
-    def train(self,
-              num_epochs,
-              train_dataset,
-              train_batch_size=64,
-              eval_dataset=None,
-              optimizer=None,
-              save_interval_epochs=1,
-              log_interval_steps=10,
-              save_dir='output',
-              pretrain_weights='IMAGENET',
-              learning_rate=.001,
-              warmup_steps=0,
-              warmup_start_lr=0.0,
-              lr_decay_epochs=(216, 243),
-              lr_decay_gamma=0.1,
-              metric=None,
-              use_ema=False,
-              early_stop=False,
-              early_stop_patience=5,
-              use_vdl=True,
-              resume_checkpoint=None):
-        """
-        Train the model.
-
-        Args:
-            num_epochs (int): Number of epochs.
-            train_dataset (paddlers.datasets.COCODetDataset|paddlers.datasets.VOCDetDataset): 
-                Training dataset.
-            train_batch_size (int, optional): Total batch size among all cards used in 
-                training. Defaults to 64.
-            eval_dataset (paddlers.datasets.COCODetDataset|paddlers.datasets.VOCDetDataset|None, optional): 
-                Evaluation dataset. If None, the model will not be evaluated during training 
-                process. Defaults to None.
-            optimizer (paddle.optimizer.Optimizer|None, optional): Optimizer used for 
-                training. If None, a default optimizer will be used. Defaults to None.
-            save_interval_epochs (int, optional): Epoch interval for saving the model. 
-                Defaults to 1.
-            log_interval_steps (int, optional): Step interval for printing training 
-                information. Defaults to 10.
-            save_dir (str, optional): Directory to save the model. Defaults to 'output'.
-            pretrain_weights (str|None, optional): None or name/path of pretrained 
-                weights. If None, no pretrained weights will be loaded. 
-                Defaults to 'IMAGENET'.
-            learning_rate (float, optional): Learning rate for training. Defaults to .001.
-            warmup_steps (int, optional): Number of steps of warm-up training. 
-                Defaults to 0.
-            warmup_start_lr (float, optional): Start learning rate of warm-up training. 
-                Defaults to 0..
-            lr_decay_epochs (list|tuple, optional): Epoch milestones for learning 
-                rate decay. Defaults to (216, 243).
-            lr_decay_gamma (float, optional): Gamma coefficient of learning rate decay. 
-                Defaults to .1.
-            metric (str|None, optional): Evaluation metric. Choices are {'VOC', 'COCO', None}. 
-                If None, determine the metric according to the  dataset format. 
-                Defaults to None.
-            use_ema (bool, optional): Whether to use exponential moving average 
-                strategy. Defaults to False.
-            early_stop (bool, optional): Whether to adopt early stop strategy. 
-                Defaults to False.
-            early_stop_patience (int, optional): Early stop patience. Defaults to 5.
-            use_vdl(bool, optional): Whether to use VisualDL to monitor the training 
-                process. Defaults to True.
-            resume_checkpoint (str|None, optional): Path of the checkpoint to resume
-                training from. If None, no training checkpoint will be resumed. At most
-                Aone of `resume_checkpoint` and `pretrain_weights` can be set simultaneously.
-                Defaults to None.
-        """
-
+    def _pre_train(self, in_args):
+        train_dataset = in_args['train_dataset']
         if train_dataset.pos_num < len(train_dataset.file_list):
+            # In-place modification
             train_dataset.num_workers = 0
-        super(FasterRCNN, self).train(
-            num_epochs, train_dataset, train_batch_size, eval_dataset,
-            optimizer, save_interval_epochs, log_interval_steps, save_dir,
-            pretrain_weights, learning_rate, warmup_steps, warmup_start_lr,
-            lr_decay_epochs, lr_decay_gamma, metric, use_ema, early_stop,
-            early_stop_patience, use_vdl, resume_checkpoint)
+        return in_args
 
     def _compose_batch_transform(self, transforms, mode='train'):
         if mode == 'train':
@@ -2214,82 +2088,12 @@ class MaskRCNN(BaseDetector):
         super(MaskRCNN, self).__init__(
             model_name='MaskRCNN', num_classes=num_classes, **params)
 
-    def train(self,
-              num_epochs,
-              train_dataset,
-              train_batch_size=64,
-              eval_dataset=None,
-              optimizer=None,
-              save_interval_epochs=1,
-              log_interval_steps=10,
-              save_dir='output',
-              pretrain_weights='IMAGENET',
-              learning_rate=.001,
-              warmup_steps=0,
-              warmup_start_lr=0.0,
-              lr_decay_epochs=(216, 243),
-              lr_decay_gamma=0.1,
-              metric=None,
-              use_ema=False,
-              early_stop=False,
-              early_stop_patience=5,
-              use_vdl=True,
-              resume_checkpoint=None):
-        """
-        Train the model.
-
-        Args:
-            num_epochs (int): Number of epochs.
-            train_dataset (paddlers.datasets.COCODetDataset|paddlers.datasets.VOCDetDataset): 
-                Training dataset.
-            train_batch_size (int, optional): Total batch size among all cards used in 
-                training. Defaults to 64.
-            eval_dataset (paddlers.datasets.COCODetDataset|paddlers.datasets.VOCDetDataset|None, optional): 
-                Evaluation dataset. If None, the model will not be evaluated during training 
-                process. Defaults to None.
-            optimizer (paddle.optimizer.Optimizer|None, optional): Optimizer used for 
-                training. If None, a default optimizer will be used. Defaults to None.
-            save_interval_epochs (int, optional): Epoch interval for saving the model. 
-                Defaults to 1.
-            log_interval_steps (int, optional): Step interval for printing training 
-                information. Defaults to 10.
-            save_dir (str, optional): Directory to save the model. Defaults to 'output'.
-            pretrain_weights (str|None, optional): None or name/path of pretrained 
-                weights. If None, no pretrained weights will be loaded. 
-                Defaults to 'IMAGENET'.
-            learning_rate (float, optional): Learning rate for training. Defaults to .001.
-            warmup_steps (int, optional): Number of steps of warm-up training. 
-                Defaults to 0.
-            warmup_start_lr (float, optional): Start learning rate of warm-up training. 
-                Defaults to 0..
-            lr_decay_epochs (list|tuple, optional): Epoch milestones for learning 
-                rate decay. Defaults to (216, 243).
-            lr_decay_gamma (float, optional): Gamma coefficient of learning rate decay. 
-                Defaults to .1.
-            metric (str|None, optional): Evaluation metric. Choices are {'VOC', 'COCO', None}. 
-                If None, determine the metric according to the  dataset format. 
-                Defaults to None.
-            use_ema (bool, optional): Whether to use exponential moving average 
-                strategy. Defaults to False.
-            early_stop (bool, optional): Whether to adopt early stop strategy. 
-                Defaults to False.
-            early_stop_patience (int, optional): Early stop patience. Defaults to 5.
-            use_vdl(bool, optional): Whether to use VisualDL to monitor the training 
-                process. Defaults to True.
-            resume_checkpoint (str|None, optional): Path of the checkpoint to resume
-                training from. If None, no training checkpoint will be resumed. At most
-                Aone of `resume_checkpoint` and `pretrain_weights` can be set simultaneously.
-                Defaults to None.
-        """
-
+    def _pre_train(self, in_args):
+        train_dataset = in_args['train_dataset']
         if train_dataset.pos_num < len(train_dataset.file_list):
+            # In-place modification
             train_dataset.num_workers = 0
-        super(MaskRCNN, self).train(
-            num_epochs, train_dataset, train_batch_size, eval_dataset,
-            optimizer, save_interval_epochs, log_interval_steps, save_dir,
-            pretrain_weights, learning_rate, warmup_steps, warmup_start_lr,
-            lr_decay_epochs, lr_decay_gamma, metric, use_ema, early_stop,
-            early_stop_patience, use_vdl, resume_checkpoint)
+        return in_args
 
     def _compose_batch_transform(self, transforms, mode='train'):
         if mode == 'train':

paddlers/tasks/segmenter.py

@@ -111,10 +111,10 @@ class BaseSegmenter(BaseModel):
         if mode == 'test':
             origin_shape = inputs[1]
             if self.status == 'Infer':
-                label_map_list, score_map_list = self._postprocess(
+                label_map_list, score_map_list = self.postprocess(
                     net_out, origin_shape, transforms=inputs[2])
             else:
-                logit_list = self._postprocess(
+                logit_list = self.postprocess(
                     logit, origin_shape, transforms=inputs[2])
                 label_map_list = []
                 score_map_list = []
@@ -142,7 +142,7 @@ class BaseSegmenter(BaseModel):
                 raise ValueError("Expected label.ndim == 4 but got {}".format(
                     label.ndim))
             origin_shape = [label.shape[-2:]]
-            pred = self._postprocess(
+            pred = self.postprocess(
                 pred, origin_shape, transforms=inputs[2])[0]  # NCHW
             intersect_area, pred_area, label_area = ppseg.utils.metrics.calculate_area(
                 pred, label, self.num_classes)
@@ -521,8 +521,8 @@ class BaseSegmenter(BaseModel):
             images = [img_file]
         else:
             images = img_file
-        batch_im, batch_origin_shape = self._preprocess(images, transforms,
-                                                        self.model_type)
+        batch_im, batch_origin_shape = self.preprocess(images, transforms,
+                                                       self.model_type)
         self.net.eval()
         data = (batch_im, batch_origin_shape, transforms.transforms)
         outputs = self.run(self.net, data, 'test')
@@ -626,7 +626,7 @@ class BaseSegmenter(BaseModel):
         dst_data = None
         print("GeoTiff saved in {}.".format(save_file))
 
-    def _preprocess(self, images, transforms, to_tensor=True):
+    def preprocess(self, images, transforms, to_tensor=True):
         self._check_transforms(transforms, 'test')
         batch_im = list()
         batch_ori_shape = list()
@@ -693,7 +693,7 @@ class BaseSegmenter(BaseModel):
             batch_restore_list.append(restore_list)
         return batch_restore_list
 
-    def _postprocess(self, batch_pred, batch_origin_shape, transforms):
+    def postprocess(self, batch_pred, batch_origin_shape, transforms):
         batch_restore_list = BaseSegmenter.get_transforms_shape_info(
             batch_origin_shape, transforms)
         if isinstance(batch_pred, (tuple, list)) and self.status == 'Infer':
@@ -781,7 +781,7 @@ class BaseSegmenter(BaseModel):
 
 class UNet(BaseSegmenter):
     def __init__(self,
-                 input_channel=3,
+                 in_channels=3,
                  num_classes=2,
                  use_mixed_loss=False,
                  losses=None,
@@ -794,7 +794,7 @@ class UNet(BaseSegmenter):
         })
         super(UNet, self).__init__(
             model_name='UNet',
-            input_channel=input_channel,
+            input_channel=in_channels,
             num_classes=num_classes,
             use_mixed_loss=use_mixed_loss,
             losses=losses,
@@ -803,7 +803,7 @@ class UNet(BaseSegmenter):
 
 class DeepLabV3P(BaseSegmenter):
     def __init__(self,
-                 input_channel=3,
+                 in_channels=3,
                  num_classes=2,
                  backbone='ResNet50_vd',
                  use_mixed_loss=False,

test_tipc/infer.py

@@ -141,7 +141,7 @@ class TIPCPredictor(object):
         return config
 
     def preprocess(self, images, transforms):
-        preprocessed_samples = self._model._preprocess(
+        preprocessed_samples = self._model.preprocess(
             images, transforms, to_tensor=False)
         if self._model.model_type == 'classifier':
             preprocessed_samples = {'image': preprocessed_samples[0]}
@@ -167,12 +167,12 @@ class TIPCPredictor(object):
     def postprocess(self, net_outputs, topk=1, ori_shape=None, transforms=None):
         if self._model.model_type == 'classifier':
             true_topk = min(self._model.num_classes, topk)
-            if self._model._postprocess is None:
+            if self._model.postprocess is None:
                 self._model.build_postprocess_from_labels(topk)
-            # XXX: Convert ndarray to tensor as self._model._postprocess requires
+            # XXX: Convert ndarray to tensor as self._model.postprocess requires
             assert len(net_outputs) == 1
             net_outputs = paddle.to_tensor(net_outputs[0])
-            outputs = self._model._postprocess(net_outputs)
+            outputs = self._model.postprocess(net_outputs)
             class_ids = map(itemgetter('class_ids'), outputs)
             scores = map(itemgetter('scores'), outputs)
             label_names = map(itemgetter('label_names'), outputs)
@@ -182,7 +182,7 @@ class TIPCPredictor(object):
                 'label_names_map': n,
             } for l, s, n in zip(class_ids, scores, label_names)]
         elif self._model.model_type in ('segmenter', 'change_detector'):
-            label_map, score_map = self._model._postprocess(
+            label_map, score_map = self._model.postprocess(
                 net_outputs,
                 batch_origin_shape=ori_shape,
                 transforms=transforms.transforms)
@@ -195,7 +195,7 @@ class TIPCPredictor(object):
                 k: v
                 for k, v in zip(['bbox', 'bbox_num', 'mask'], net_outputs)
             }
-            preds = self._model._postprocess(net_outputs)
+            preds = self._model.postprocess(net_outputs)
         else:
             logging.error(
                 "Invalid model type {}.".format(self._model.model_type),