change fluid.layers.data to fluid.data (#34)

* change fluid.layers.data to fluid.data

* fix export_model doc

docs/EXPORT_MODEL.md

@@ -14,14 +14,14 @@
 使用[训练/评估/推断](GETTING_STARTED_cn.md)中训练得到的模型进行试用，脚本如下
 
 ```bash
-# 导出FasterRCNN模型, 模型中data层默认的shape为3x800x1333
+# 导出FasterRCNN模型
 python tools/export_model.py -c configs/faster_rcnn_r50_1x.yml \
         --output_dir=./inference_model \
         -o weights=output/faster_rcnn_r50_1x/model_final \
 
 ```
 
-预测模型会导出到`inference_model/faster_rcnn_r50_1x`目录下，模型名和参数名分别为`__model__`和`__params__`。
+- 预测模型会导出到`inference_model/faster_rcnn_r50_1x`目录下，模型名和参数名分别为`__model__`和`__params__`。
 
 ## 设置导出模型的输入大小
 
@@ -46,3 +46,5 @@ python tools/export_model.py -c configs/ssd/ssd_mobilenet_v1_voc.yml \
         -o weights= https://paddlemodels.bj.bcebos.com/object_detection/ssd_mobilenet_v1_voc.tar \
            SSDTestFeed.image_shape=[3,300,300]
 ```
+
+- 保存FPN系列模型时，需要保证上下采样维度一致，因此image_shape须设置为32的倍数

ppdet/data/data_feed.py

@@ -453,7 +453,7 @@ class FasterRCNNTrainFeed(DataFeed):
                      'image', 'im_info', 'im_id', 'gt_box', 'gt_label',
                      'is_crowd'
                  ],
-                 image_shape=[3, 800, 1333],
+                 image_shape=[None, 3, None, None],
                  sample_transforms=[
                      DecodeImage(to_rgb=True),
                      RandomFlipImage(prob=0.5),
@@ -505,7 +505,7 @@ class FasterRCNNEvalFeed(DataFeed):
                                      COCO_VAL_IMAGE_DIR).__dict__,
                  fields=['image', 'im_info', 'im_id', 'im_shape', 'gt_box',
                          'gt_label', 'is_difficult'],
-                 image_shape=[3, 800, 1333],
+                 image_shape=[None, 3, None, None],
                  sample_transforms=[
                      DecodeImage(to_rgb=True),
                      NormalizeImage(mean=[0.485, 0.456, 0.406],
@@ -552,7 +552,7 @@ class FasterRCNNTestFeed(DataFeed):
                  dataset=SimpleDataSet(COCO_VAL_ANNOTATION,
                                        COCO_VAL_IMAGE_DIR).__dict__,
                  fields=['image', 'im_info', 'im_id', 'im_shape'],
-                 image_shape=[3, 800, 1333],
+                 image_shape=[None, 3, None, None],
                  sample_transforms=[
                      DecodeImage(to_rgb=True),
                      NormalizeImage(mean=[0.485, 0.456, 0.406],
@@ -600,7 +600,7 @@ class MaskRCNNTrainFeed(DataFeed):
                      'image', 'im_info', 'im_id', 'gt_box', 'gt_label',
                      'is_crowd', 'gt_mask'
                  ],
-                 image_shape=[3, 800, 1333],
+                 image_shape=[None, 3, None, None],
                  sample_transforms=[
                      DecodeImage(to_rgb=True),
                      RandomFlipImage(prob=0.5, is_mask_flip=True),
@@ -646,7 +646,7 @@ class MaskRCNNEvalFeed(DataFeed):
                  dataset=CocoDataSet(COCO_VAL_ANNOTATION,
                                      COCO_VAL_IMAGE_DIR).__dict__,
                  fields=['image', 'im_info', 'im_id', 'im_shape'],
-                 image_shape=[3, 800, 1333],
+                 image_shape=[None, 3, None, None],
                  sample_transforms=[
                      DecodeImage(to_rgb=True),
                      NormalizeImage(mean=[0.485, 0.456, 0.406],
@@ -698,7 +698,7 @@ class MaskRCNNTestFeed(DataFeed):
                  dataset=SimpleDataSet(COCO_VAL_ANNOTATION,
                                        COCO_VAL_IMAGE_DIR).__dict__,
                  fields=['image', 'im_info', 'im_id', 'im_shape'],
-                 image_shape=[3, 800, 1333],
+                 image_shape=[None, 3, None, None],
                  sample_transforms=[
                      DecodeImage(to_rgb=True),
                      NormalizeImage(
@@ -743,7 +743,7 @@ class SSDTrainFeed(DataFeed):
     def __init__(self,
                  dataset=VocDataSet().__dict__,
                  fields=['image', 'gt_box', 'gt_label'],
-                 image_shape=[3, 300, 300],
+                 image_shape=[None, 3, 300, 300],
                  sample_transforms=[
                      DecodeImage(to_rgb=True, with_mixup=False),
                      NormalizeBox(),
@@ -802,7 +802,7 @@ class SSDEvalFeed(DataFeed):
             dataset=VocDataSet(VOC_VAL_ANNOTATION).__dict__,
             fields=['image', 'im_shape', 'im_id', 'gt_box',
                          'gt_label', 'is_difficult'],
-            image_shape=[3, 300, 300],
+            image_shape=[None, 3, 300, 300],
             sample_transforms=[
                 DecodeImage(to_rgb=True, with_mixup=False),
                 NormalizeBox(),
@@ -847,7 +847,7 @@ class SSDTestFeed(DataFeed):
     def __init__(self,
                  dataset=SimpleDataSet(VOC_VAL_ANNOTATION).__dict__,
                  fields=['image', 'im_id', 'im_shape'],
-                 image_shape=[3, 300, 300],
+                 image_shape=[None, 3, 300, 300],
                  sample_transforms=[
                      DecodeImage(to_rgb=True),
                      ResizeImage(target_size=300, use_cv2=False, interp=1),
@@ -893,7 +893,7 @@ class YoloTrainFeed(DataFeed):
     def __init__(self,
                  dataset=CocoDataSet().__dict__,
                  fields=['image', 'gt_box', 'gt_label', 'gt_score'],
-                 image_shape=[3, 608, 608],
+                 image_shape=[None, 3, 608, 608],
                  sample_transforms=[
                      DecodeImage(to_rgb=True, with_mixup=True),
                      MixupImage(alpha=1.5, beta=1.5),
@@ -955,7 +955,7 @@ class YoloEvalFeed(DataFeed):
                                      COCO_VAL_IMAGE_DIR).__dict__,
                  fields=['image', 'im_size', 'im_id', 'gt_box',
                          'gt_label', 'is_difficult'],
-                 image_shape=[3, 608, 608],
+                 image_shape=[None, 3, 608, 608],
                  sample_transforms=[
                      DecodeImage(to_rgb=True),
                      ResizeImage(target_size=608, interp=2),
@@ -1013,7 +1013,7 @@ class YoloTestFeed(DataFeed):
                  dataset=SimpleDataSet(COCO_VAL_ANNOTATION,
                                        COCO_VAL_IMAGE_DIR).__dict__,
                  fields=['image', 'im_size', 'im_id'],
-                 image_shape=[3, 608, 608],
+                 image_shape=[None, 3, 608, 608],
                  sample_transforms=[
                      DecodeImage(to_rgb=True),
                      ResizeImage(target_size=608, interp=2),

ppdet/modeling/model_input.py

@@ -25,16 +25,16 @@ __all__ = ['create_feed']
 
 # yapf: disable
 feed_var_def = [
-    {'name': 'im_info',       'shape': [3],  'dtype': 'float32', 'lod_level': 0},
-    {'name': 'im_id',         'shape': [1],  'dtype': 'int32',   'lod_level': 0},
-    {'name': 'gt_box',        'shape': [4],  'dtype': 'float32', 'lod_level': 1},
-    {'name': 'gt_label',      'shape': [1],  'dtype': 'int32',   'lod_level': 1},
-    {'name': 'is_crowd',      'shape': [1],  'dtype': 'int32',   'lod_level': 1},
-    {'name': 'gt_mask',       'shape': [2],  'dtype': 'float32', 'lod_level': 3},
-    {'name': 'is_difficult',  'shape': [1],  'dtype': 'int32',   'lod_level': 1},
-    {'name': 'gt_score',      'shape': [1],  'dtype': 'float32', 'lod_level': 0},
-    {'name': 'im_shape',      'shape': [3],  'dtype': 'float32', 'lod_level': 0},
-    {'name': 'im_size',       'shape': [2],  'dtype': 'int32',   'lod_level': 0},
+    {'name': 'im_info',       'shape': [None, 3],  'dtype': 'float32', 'lod_level': 0},
+    {'name': 'im_id',         'shape': [None, 1],  'dtype': 'int32',   'lod_level': 0},
+    {'name': 'gt_box',        'shape': [None, 4],  'dtype': 'float32', 'lod_level': 1},
+    {'name': 'gt_label',      'shape': [None, 1],  'dtype': 'int32',   'lod_level': 1},
+    {'name': 'is_crowd',      'shape': [None, 1],  'dtype': 'int32',   'lod_level': 1},
+    {'name': 'gt_mask',       'shape': [None, 2],  'dtype': 'float32', 'lod_level': 3},
+    {'name': 'is_difficult',  'shape': [None, 1],  'dtype': 'int32',   'lod_level': 1},
+    {'name': 'gt_score',      'shape': [None, 1],  'dtype': 'float32', 'lod_level': 0},
+    {'name': 'im_shape',      'shape': [None, 3],  'dtype': 'float32', 'lod_level': 0},
+    {'name': 'im_size',       'shape': [None, 2],  'dtype': 'int32',   'lod_level': 0},
 ]
 # yapf: enable
 
@@ -52,10 +52,10 @@ def create_feed(feed, iterable=False, sub_prog_feed=False):
     # tensor padding with 0 is used instead of LoD tensor when 
     # num_max_boxes is set
     if getattr(feed, 'num_max_boxes', None) is not None:
-        feed_var_map['gt_label']['shape'] = [feed.num_max_boxes]
-        feed_var_map['gt_score']['shape'] = [feed.num_max_boxes]
-        feed_var_map['gt_box']['shape'] = [feed.num_max_boxes, 4]
-        feed_var_map['is_difficult']['shape'] = [feed.num_max_boxes]
+        feed_var_map['gt_label']['shape'] = [None, feed.num_max_boxes]
+        feed_var_map['gt_score']['shape'] = [None, feed.num_max_boxes]
+        feed_var_map['gt_box']['shape'] = [None, feed.num_max_boxes, 4]
+        feed_var_map['is_difficult']['shape'] = [None, feed.num_max_boxes]
         feed_var_map['gt_label']['lod_level'] = 0
         feed_var_map['gt_score']['lod_level'] = 0
         feed_var_map['gt_box']['lod_level'] = 0
@@ -113,7 +113,7 @@ def create_feed(feed, iterable=False, sub_prog_feed=False):
             feed.fields = feed.fields + [box_name]
             feed_var_map[box_name] = sub_prog_feed
 
-    feed_vars = OrderedDict([(key, fluid.layers.data(
+    feed_vars = OrderedDict([(key, fluid.data(
         name=feed_var_map[key]['name'],
         shape=feed_var_map[key]['shape'],
         dtype=feed_var_map[key]['dtype'],