refine metric related code

dygraph/paddlex/cv/models/detector.py

@@ -334,12 +334,24 @@ class BaseDetector(BaseModel):
             collections.OrderedDict with key-value pairs: {"mAP(0.50, 11point)":`mean average precision`}.
 
         """
-        if eval_dataset.__class__.__name__ == 'VOCDetection':
+
+        if metric is None:
+            if not hasattr(self, metric):
+                if eval_dataset.__class__.__name__ == 'VOCDetection':
+                    self.metric = 'voc'
+                elif eval_dataset.__class__.__name__ == 'CocoDetection':
+                    self.metric = 'coco'
+        else:
+            assert metric.lower() in ['coco', 'voc'], \
+                "Evaluation metric {} is not supported, please choose form 'COCO' and 'VOC'"
+            self.metric = metric.lower()
+
+        if self.metric == 'voc':
             eval_dataset.data_fields = {
                 'im_id', 'image_shape', 'image', 'gt_bbox', 'gt_class',
                 'difficult'
             }
-        elif eval_dataset.__class__.__name__ == 'CocoDetection':
+        elif self.metric == 'coco':
             if self.__class__.__name__ == 'MaskRCNN':
                 eval_dataset.data_fields = {
                     'im_id', 'image_shape', 'image', 'gt_bbox', 'gt_class',
@@ -380,41 +392,16 @@ class BaseDetector(BaseModel):
                 is_bbox_normalized = any(
                     isinstance(t, _NormalizeBox)
                     for t in eval_dataset.batch_transforms.batch_transforms)
-            if metric is None:
-                if getattr(self, 'metric', None) is not None:
-                    if self.metric == 'voc':
-                        eval_metric = VOCMetric(
-                            labels=eval_dataset.labels,
-                            coco_gt=copy.deepcopy(eval_dataset.coco_gt),
-                            is_bbox_normalized=is_bbox_normalized,
-                            classwise=False)
-                    else:
-                        eval_metric = COCOMetric(
-                            coco_gt=copy.deepcopy(eval_dataset.coco_gt),
-                            classwise=False)
-                else:
-                    if eval_dataset.__class__.__name__ == 'VOCDetection':
-                        eval_metric = VOCMetric(
-                            labels=eval_dataset.labels,
-                            coco_gt=copy.deepcopy(eval_dataset.coco_gt),
-                            is_bbox_normalized=is_bbox_normalized,
-                            classwise=False)
-                    elif eval_dataset.__class__.__name__ == 'CocoDetection':
-                        eval_metric = COCOMetric(
-                            coco_gt=copy.deepcopy(eval_dataset.coco_gt),
-                            classwise=False)
+            if self.metric == 'voc':
+                eval_metric = VOCMetric(
+                    labels=eval_dataset.labels,
+                    coco_gt=copy.deepcopy(eval_dataset.coco_gt),
+                    is_bbox_normalized=is_bbox_normalized,
+                    classwise=False)
             else:
-                assert metric.lower() in ['coco', 'voc'], \
-                    "Evaluation metric {} is not supported, please choose form 'COCO' and 'VOC'"
-                if metric.lower() == 'coco':
-                    eval_metric = COCOMetric(
-                        coco_gt=copy.deepcopy(eval_dataset.coco_gt),
-                        classwise=False)
-                else:
-                    eval_metric = VOCMetric(
-                        labels=eval_dataset.labels,
-                        is_bbox_normalized=is_bbox_normalized,
-                        classwise=False)
+                eval_metric = COCOMetric(
+                    coco_gt=copy.deepcopy(eval_dataset.coco_gt),
+                    classwise=False)
             scores = collections.OrderedDict()
             logging.info(
                 "Start to evaluate(total_samples={}, total_steps={})...".

dygraph/tutorials/train/object_detection/faster_rcnn_r34_fpn.py

@@ -1,58 +0,0 @@
-import paddlex as pdx
-from paddlex import transforms as T
-
-# 下载和解压昆虫检测数据集
-dataset = 'https://bj.bcebos.com/paddlex/datasets/insect_det.tar.gz'
-pdx.utils.download_and_decompress(dataset, path='./')
-
-# 定义训练和验证时的transforms
-# API说明：https://github.com/PaddlePaddle/PaddleX/blob/release/2.0-rc/paddlex/cv/transforms/operators.py
-train_transforms = T.Compose([
-    T.RandomResizeByShort(
-        short_sizes=[640, 672, 704, 736, 768, 800],
-        max_size=1333,
-        interp='CUBIC'), T.RandomHorizontalFlip(), T.Normalize(
-            mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
-])
-
-eval_transforms = T.Compose([
-    T.ResizeByShort(
-        short_size=800, max_size=1333, interp='CUBIC'), T.Normalize(
-            mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
-])
-
-# 定义训练和验证所用的数据集
-# API说明：https://github.com/PaddlePaddle/PaddleX/blob/release/2.0-rc/paddlex/cv/datasets/voc.py#L29
-train_dataset = pdx.datasets.VOCDetection(
-    data_dir='insect_det',
-    file_list='insect_det/train_list.txt',
-    label_list='insect_det/labels.txt',
-    transforms=train_transforms,
-    shuffle=True)
-
-eval_dataset = pdx.datasets.VOCDetection(
-    data_dir='insect_det',
-    file_list='insect_det/val_list.txt',
-    label_list='insect_det/labels.txt',
-    transforms=eval_transforms,
-    shuffle=False)
-
-# 初始化模型，并进行训练
-# 可使用VisualDL查看训练指标，参考https://github.com/PaddlePaddle/PaddleX/tree/release/2.0-rc/tutorials/train#visualdl可视化训练指标
-num_classes = len(train_dataset.labels)
-model = pdx.models.FasterRCNN(
-    num_classes=num_classes, backbone='ResNet34', with_fpn=True)
-
-# API说明：https://github.com/PaddlePaddle/PaddleX/blob/release/2.0-rc/paddlex/cv/models/detector.py#L154
-# 各参数介绍与调整说明：https://paddlex.readthedocs.io/zh_CN/develop/appendix/parameters.html
-model.train(
-    num_epochs=12,
-    train_dataset=train_dataset,
-    train_batch_size=2,
-    eval_dataset=eval_dataset,
-    learning_rate=0.0025,
-    lr_decay_epochs=[8, 11],
-    warmup_steps=500,
-    warmup_start_lr=0.00025,
-    save_dir='output/faster_rcnn_r50_fpn',
-    use_vdl=True)