Merge branch 'develop' into refactor_res

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]}
@@ -182,12 +182,12 @@ class Predictor(object):
                     transforms=None):
         if self._model.model_type == 'classifier':
             true_topk = min(self._model.num_classes, topk)
-            if self._model._postprocess is None:
-                self._model.build_postprocess_from_labels(true_topk)
-            # XXX: Convert ndarray to tensor as self._model._postprocess requires
+            if self._model.postprocess is None:
+                self._model.build_postprocess_from_labels(topk)
+            # 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)
@@ -197,7 +197,7 @@ 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)
@@ -210,9 +210,9 @@ 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)
         elif self._model.model_type == 'restorer':
-            res_maps = self._model._postprocess(
+            res_maps = self._model.postprocess(
                 net_outputs[0],
                 batch_tar_shape=tar_shape,
                 transforms=transforms.transforms)

paddlers/tasks/change_detector.py

@@ -119,10 +119,10 @@ 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 = []
@@ -150,7 +150,7 @@ 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)
@@ -556,7 +556,7 @@ 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)
@@ -667,7 +667,7 @@ 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()
@@ -739,7 +739,7 @@ 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)
@@ -127,13 +127,12 @@ 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"]
@@ -182,13 +181,13 @@ 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,
@@ -253,8 +252,7 @@ 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
@@ -460,12 +458,12 @@ 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')
@@ -486,7 +484,7 @@ 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

@@ -254,6 +254,34 @@ 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.",
@@ -583,16 +611,16 @@ 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:
@@ -609,7 +637,7 @@ 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']
@@ -880,108 +908,24 @@ 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
 
     def build_data_loader(self, dataset, batch_size, mode='train'):
         if dataset.num_samples < batch_size:
@@ -1393,82 +1337,12 @@ 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':
@@ -2235,82 +2109,12 @@ 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

@@ -117,10 +117,10 @@ 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 = []
@@ -148,7 +148,7 @@ 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)
@@ -526,8 +526,8 @@ 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')
@@ -631,7 +631,7 @@ 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()
@@ -698,7 +698,7 @@ 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':
@@ -786,7 +786,7 @@ class BaseSegmenter(BaseModel):
 
 class UNet(BaseSegmenter):
     def __init__(self,
-                 input_channel=3,
+                 in_channels=3,
                  num_classes=2,
                  use_mixed_loss=False,
                  losses=None,
@@ -799,7 +799,7 @@ 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,
@@ -808,7 +808,7 @@ 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),