fix voc dataset collact_batch (#4966)

ppdet/engine/trainer.py

@@ -111,8 +111,12 @@ class Trainer(object):
         if self.mode == 'eval':
             self._eval_batch_sampler = paddle.io.BatchSampler(
                 self.dataset, batch_size=self.cfg.EvalReader['batch_size'])
-            self.loader = create('{}Reader'.format(self.mode.capitalize()))(
-                self.dataset, cfg.worker_num, self._eval_batch_sampler)
+            reader_name = '{}Reader'.format(self.mode.capitalize())
+            # If metric is VOC, need to be set collate_batch=False.
+            if cfg.metric == 'VOC':
+                cfg[reader_name]['collate_batch'] = False
+            self.loader = create(reader_name)(self.dataset, cfg.worker_num,
+                                              self._eval_batch_sampler)
         # TestDataset build after user set images, skip loader creation here
 
         # build optimizer in train mode
@@ -444,6 +448,9 @@ class Trainer(object):
                         paddle.io.BatchSampler(
                             self._eval_dataset,
                             batch_size=self.cfg.EvalReader['batch_size'])
+                    # If metric is VOC, need to be set collate_batch=False.
+                    if self.cfg.metric == 'VOC':
+                        self.cfg['EvalReader']['collate_batch'] = False
                     self._eval_loader = create('EvalReader')(
                         self._eval_dataset,
                         self.cfg.worker_num,

ppdet/modeling/backbones/lcnet.py

@@ -19,7 +19,7 @@ from __future__ import print_function
 import paddle
 import paddle.nn as nn
 from paddle import ParamAttr
-from paddle.nn import AdaptiveAvgPool2D, BatchNorm, Conv2D, Dropout, Linear
+from paddle.nn import AdaptiveAvgPool2D, Conv2D
 from paddle.regularizer import L2Decay
 from paddle.nn.initializer import KaimingNormal
 
@@ -81,7 +81,7 @@ class ConvBNLayer(nn.Layer):
             weight_attr=ParamAttr(initializer=KaimingNormal()),
             bias_attr=False)
 
-        self.bn = BatchNorm2D(
+        self.bn = nn.BatchNorm2D(
             num_filters,
             weight_attr=ParamAttr(regularizer=L2Decay(0.0)),
             bias_attr=ParamAttr(regularizer=L2Decay(0.0)))

ppdet/modeling/backbones/shufflenet_v2.py

@@ -19,7 +19,8 @@ from __future__ import print_function
 import paddle
 import paddle.nn as nn
 from paddle import ParamAttr
-from paddle.nn import Conv2D, MaxPool2D, AdaptiveAvgPool2D, BatchNorm
+import paddle.nn.functional as F
+from paddle.nn import Conv2D, MaxPool2D, AdaptiveAvgPool2D, BatchNorm2D
 from paddle.nn.initializer import KaimingNormal
 from paddle.regularizer import L2Decay
 
@@ -55,6 +56,8 @@ class ConvBNLayer(nn.Layer):
             out_channels,
             weight_attr=ParamAttr(regularizer=L2Decay(0.0)),
             bias_attr=ParamAttr(regularizer=L2Decay(0.0)))
+        if act == "hard_swish":
+            act = 'hardswish'
         self.act = act
 
     def forward(self, inputs):