batch fix pool2d

ppcls/modeling/architectures/alexnet.py

@@ -2,7 +2,8 @@ import paddle
 from paddle import ParamAttr
 import paddle.nn as nn
 import paddle.nn.functional as F
-from paddle.nn import Conv2d, Pool2D, BatchNorm, Linear, Dropout, ReLU
+from paddle.nn import Conv2d, BatchNorm, Linear, Dropout, ReLU
+from paddle.nn import AdaptiveAvgPool2d, MaxPool2d, AvgPool2d
 from paddle.nn.initializer import Uniform
 import math
 
@@ -35,8 +36,7 @@ class ConvPoolLayer(nn.Layer):
                 name=name + "_weights", initializer=Uniform(-stdv, stdv)),
             bias_attr=ParamAttr(
                 name=name + "_offset", initializer=Uniform(-stdv, stdv)))
-        self._pool = Pool2D(
-            pool_size=3, pool_stride=2, pool_padding=0, pool_type="max")
+        self._pool = MaxPool2d(kernel_size=3, stride=2, padding=0)
 
     def forward(self, inputs):
         x = self._conv(inputs)

ppcls/modeling/architectures/densenet.py

@@ -20,7 +20,8 @@ import numpy as np
 import paddle
 from paddle import ParamAttr
 import paddle.nn as nn
-from paddle.nn import Conv2d, Pool2D, BatchNorm, Linear, Dropout
+from paddle.nn import Conv2d, BatchNorm, Linear, Dropout
+from paddle.nn import AdaptiveAvgPool2d, MaxPool2d, AvgPool2d
 from paddle.nn.initializer import Uniform
 
 import math
@@ -144,7 +145,7 @@ class TransitionLayer(nn.Layer):
             stride=1,
             name=name)
 
-        self.pool2d_avg = Pool2D(pool_size=2, pool_stride=2, pool_type='avg')
+        self.pool2d_avg = AvgPool2d(kernel_size=2, stride=2, padding=0)
 
     def forward(self, input):
         y = self.conv_ac_func(input)
@@ -213,8 +214,7 @@ class DenseNet(nn.Layer):
             act='relu',
             name="conv1")
 
-        self.pool2d_max = Pool2D(
-            pool_size=3, pool_stride=2, pool_padding=1, pool_type='max')
+        self.pool2d_max = MaxPool2d(kernel_size=3, stride=2, padding=1)
 
         self.block_config = block_config
 
@@ -256,7 +256,7 @@ class DenseNet(nn.Layer):
             moving_mean_name='conv5_blk_bn_mean',
             moving_variance_name='conv5_blk_bn_variance')
 
-        self.pool2d_avg = Pool2D(pool_type='avg', global_pooling=True)
+        self.pool2d_avg = AdaptiveAvgPool2d(1)
 
         stdv = 1.0 / math.sqrt(num_features * 1.0)
 

ppcls/modeling/architectures/dpn.py

@@ -21,7 +21,8 @@ import sys
 import paddle
 from paddle import ParamAttr
 import paddle.nn as nn
-from paddle.nn import Conv2d, Pool2D, BatchNorm, Linear
+from paddle.nn import Conv2d, BatchNorm, Linear
+from paddle.nn import AdaptiveAvgPool2d, MaxPool2d, AvgPool2d
 from paddle.nn.initializer import Uniform
 
 import math
@@ -235,8 +236,7 @@ class DPN(nn.Layer):
             act='relu',
             name="conv1")
 
-        self.pool2d_max = Pool2D(
-            pool_size=3, pool_stride=2, pool_padding=1, pool_type='max')
+        self.pool2d_max = MaxPool2d(kernel_size=3, stride=2, padding=1)
 
         num_channel_dpn = init_num_filter
 
@@ -301,7 +301,7 @@ class DPN(nn.Layer):
             moving_mean_name='final_concat_bn_mean',
             moving_variance_name='final_concat_bn_variance')
 
-        self.pool2d_avg = Pool2D(pool_type='avg', global_pooling=True)
+        self.pool2d_avg = AdaptiveAvgPool2d(1)
 
         stdv = 0.01
 

ppcls/modeling/architectures/googlenet.py

@@ -2,7 +2,8 @@ import paddle
 from paddle import ParamAttr
 import paddle.nn as nn
 import paddle.nn.functional as F
-from paddle.nn import Conv2d, Pool2D, BatchNorm, Linear, Dropout
+from paddle.nn import Conv2d, BatchNorm, Linear, Dropout
+from paddle.nn import AdaptiveAvgPool2d, MaxPool2d, AvgPool2d
 from paddle.nn.initializer import Uniform
 
 import math
@@ -72,8 +73,8 @@ class Inception(nn.Layer):
             name="inception_" + name + "_5x5_reduce")
         self._conv5 = ConvLayer(
             filter5R, filter5, 5, name="inception_" + name + "_5x5")
-        self._pool = Pool2D(
-            pool_size=3, pool_type="max", pool_stride=1, pool_padding=1)
+        self._pool = MaxPool2d(kernel_size=3, stride=1, padding=1)
+
         self._convprj = ConvLayer(
             input_channels, proj, 1, name="inception_" + name + "_3x3_proj")
 
@@ -98,7 +99,7 @@ class GoogleNetDY(nn.Layer):
     def __init__(self, class_dim=1000):
         super(GoogleNetDY, self).__init__()
         self._conv = ConvLayer(3, 64, 7, 2, name="conv1")
-        self._pool = Pool2D(pool_size=3, pool_type="max", pool_stride=2)
+        self._pool = MaxPool2d(kernel_size=3, stride=2)
         self._conv_1 = ConvLayer(64, 64, 1, name="conv2_1x1")
         self._conv_2 = ConvLayer(64, 192, 3, name="conv2_3x3")
 
@@ -123,7 +124,7 @@ class GoogleNetDY(nn.Layer):
         self._ince5b = Inception(
             832, 832, 384, 192, 384, 48, 128, 128, name="ince5b")
 
-        self._pool_5 = Pool2D(pool_size=7, pool_type='avg', pool_stride=7)
+        self._pool_5 = AvgPool2d(kernel_size=7, stride=7)
 
         self._drop = Dropout(p=0.4)
         self._fc_out = Linear(
@@ -131,7 +132,7 @@ class GoogleNetDY(nn.Layer):
             class_dim,
             weight_attr=xavier(1024, 1, "out"),
             bias_attr=ParamAttr(name="out_offset"))
-        self._pool_o1 = Pool2D(pool_size=5, pool_stride=3, pool_type="avg")
+        self._pool_o1 = AvgPool2d(kernel_size=5, stride=3)
         self._conv_o1 = ConvLayer(512, 128, 1, name="conv_o1")
         self._fc_o1 = Linear(
             1152,
@@ -144,7 +145,7 @@ class GoogleNetDY(nn.Layer):
             class_dim,
             weight_attr=xavier(1024, 1, "out1"),
             bias_attr=ParamAttr(name="out1_offset"))
-        self._pool_o2 = Pool2D(pool_size=5, pool_stride=3, pool_type='avg')
+        self._pool_o2 = AvgPool2d(kernel_size=5, stride=3)
         self._conv_o2 = ConvLayer(528, 128, 1, name="conv_o2")
         self._fc_o2 = Linear(
             1152,

ppcls/modeling/architectures/hrnet.py

@@ -21,7 +21,8 @@ import paddle
 from paddle import ParamAttr
 import paddle.nn as nn
 import paddle.nn.functional as F
-from paddle.nn import Conv2d, Pool2D, BatchNorm, Linear
+from paddle.nn import Conv2d, BatchNorm, Linear
+from paddle.nn import AdaptiveAvgPool2d, MaxPool2d, AvgPool2d
 from paddle.nn.initializer import Uniform
 
 import math
@@ -310,7 +311,7 @@ class SELayer(nn.Layer):
     def __init__(self, num_channels, num_filters, reduction_ratio, name=None):
         super(SELayer, self).__init__()
 
-        self.pool2d_gap = Pool2D(pool_type='avg', global_pooling=True)
+        self.pool2d_gap = AdaptiveAvgPool2d(1)
 
         self._num_channels = num_channels
 
@@ -622,7 +623,7 @@ class HRNet(nn.Layer):
             stride=1,
             name="cls_head_last_conv")
 
-        self.pool2d_avg = Pool2D(pool_type='avg', global_pooling=True)
+        self.pool2d_avg = AdaptiveAvgPool2d(1)
 
         stdv = 1.0 / math.sqrt(2048 * 1.0)
 

ppcls/modeling/architectures/inception_v4.py

@@ -16,7 +16,8 @@ import paddle
 from paddle import ParamAttr
 import paddle.nn as nn
 import paddle.nn.functional as F
-from paddle.nn import Conv2d, Pool2D, BatchNorm, Linear, Dropout
+from paddle.nn import Conv2d, BatchNorm, Linear, Dropout
+from paddle.nn import AdaptiveAvgPool2d, MaxPool2d, AvgPool2d
 from paddle.nn.initializer import Uniform
 import math
 
@@ -67,7 +68,7 @@ class InceptionStem(nn.Layer):
         self._conv_2 = ConvBNLayer(32, 32, 3, act="relu", name="conv2_3x3_s1")
         self._conv_3 = ConvBNLayer(
             32, 64, 3, padding=1, act="relu", name="conv3_3x3_s1")
-        self._pool = Pool2D(pool_size=3, pool_type="max", pool_stride=2)
+        self._pool = MaxPool2d(kernel_size=3, stride=2, padding=0)
         self._conv2 = ConvBNLayer(
             64, 96, 3, stride=2, act="relu", name="inception_stem1_3x3_s2")
         self._conv1_1 = ConvBNLayer(
@@ -122,7 +123,7 @@ class InceptionStem(nn.Layer):
 class InceptionA(nn.Layer):
     def __init__(self, name):
         super(InceptionA, self).__init__()
-        self._pool = Pool2D(pool_size=3, pool_type="avg", pool_padding=1)
+        self._pool = AvgPool2d(kernel_size=3, stride=1, padding=1)
         self._conv1 = ConvBNLayer(
             384, 96, 1, act="relu", name="inception_a" + name + "_1x1")
         self._conv2 = ConvBNLayer(
@@ -177,7 +178,7 @@ class InceptionA(nn.Layer):
 class ReductionA(nn.Layer):
     def __init__(self):
         super(ReductionA, self).__init__()
-        self._pool = Pool2D(pool_size=3, pool_type="max", pool_stride=2)
+        self._pool = MaxPool2d(kernel_size=3, stride=2, padding=0)
         self._conv2 = ConvBNLayer(
             384, 384, 3, stride=2, act="relu", name="reduction_a_3x3")
         self._conv3_1 = ConvBNLayer(
@@ -200,7 +201,7 @@ class ReductionA(nn.Layer):
 class InceptionB(nn.Layer):
     def __init__(self, name=None):
         super(InceptionB, self).__init__()
-        self._pool = Pool2D(pool_size=3, pool_type="avg", pool_padding=1)
+        self._pool = AvgPool2d(kernel_size=3, stride=1, padding=1)
         self._conv1 = ConvBNLayer(
             1024, 128, 1, act="relu", name="inception_b" + name + "_1x1")
         self._conv2 = ConvBNLayer(
@@ -277,7 +278,7 @@ class InceptionB(nn.Layer):
 class ReductionB(nn.Layer):
     def __init__(self):
         super(ReductionB, self).__init__()
-        self._pool = Pool2D(pool_size=3, pool_type="max", pool_stride=2)
+        self._pool = MaxPool2d(kernel_size=3, stride=2, padding=0)
         self._conv2_1 = ConvBNLayer(
             1024, 192, 1, act="relu", name="reduction_b_3x3_reduce")
         self._conv2_2 = ConvBNLayer(
@@ -318,7 +319,7 @@ class ReductionB(nn.Layer):
 class InceptionC(nn.Layer):
     def __init__(self, name=None):
         super(InceptionC, self).__init__()
-        self._pool = Pool2D(pool_size=3, pool_type="avg", pool_padding=1)
+        self._pool = AvgPool2d(kernel_size=3, stride=1, padding=1)
         self._conv1 = ConvBNLayer(
             1536, 256, 1, act="relu", name="inception_c" + name + "_1x1")
         self._conv2 = ConvBNLayer(
@@ -410,7 +411,7 @@ class InceptionV4DY(nn.Layer):
         self._inceptionC_2 = InceptionC(name="2")
         self._inceptionC_3 = InceptionC(name="3")
 
-        self.avg_pool = Pool2D(pool_type='avg', global_pooling=True)
+        self.avg_pool = AdaptiveAvgPool2d(1)
         self._drop = Dropout(p=0.2)
         stdv = 1.0 / math.sqrt(1536 * 1.0)
         self.out = Linear(

ppcls/modeling/architectures/mobilenet_v1.py

@@ -21,7 +21,8 @@ import paddle
 from paddle import ParamAttr
 import paddle.nn as nn
 import paddle.nn.functional as F
-from paddle.nn import Conv2d, Pool2D, BatchNorm, Linear, Dropout
+from paddle.nn import Conv2d, BatchNorm, Linear, Dropout
+from paddle.nn import AdaptiveAvgPool2d, MaxPool2d, AvgPool2d
 from paddle.nn.initializer import MSRA
 import math
 
@@ -226,7 +227,7 @@ class MobileNet(nn.Layer):
                 name="conv6"))
         self.block_list.append(conv6)
 
-        self.pool2d_avg = Pool2D(pool_type='avg', global_pooling=True)
+        self.pool2d_avg = AdaptiveAvgPool2d(1)
 
         self.out = Linear(
             int(1024 * scale),

ppcls/modeling/architectures/mobilenet_v2.py

@@ -21,7 +21,8 @@ import paddle
 from paddle import ParamAttr
 import paddle.nn as nn
 import paddle.nn.functional as F
-from paddle.nn import Conv2d, Pool2D, BatchNorm, Linear, Dropout
+from paddle.nn import Conv2d, BatchNorm, Linear, Dropout
+from paddle.nn import AdaptiveAvgPool2d, MaxPool2d, AvgPool2d
 
 import math
 
@@ -198,7 +199,7 @@ class MobileNet(nn.Layer):
             padding=0,
             name="conv9")
 
-        self.pool2d_avg = Pool2D(pool_type="avg", global_pooling=True)
+        self.pool2d_avg = AdaptiveAvgPool2d(1)
 
         self.out = Linear(
             self.out_c,

ppcls/modeling/architectures/mobilenet_v3.py

@@ -21,7 +21,8 @@ import paddle
 from paddle import ParamAttr
 import paddle.nn as nn
 import paddle.nn.functional as F
-from paddle.nn import Conv2d, Pool2D, BatchNorm, Linear, Dropout
+from paddle.nn import Conv2d, BatchNorm, Linear, Dropout
+from paddle.nn import AdaptiveAvgPool2d, MaxPool2d, AvgPool2d
 # TODO: need to be removed later!
 from paddle.fluid.regularizer import L2Decay
 
@@ -133,8 +134,7 @@ class MobileNetV3(nn.Layer):
             act="hard_swish",
             name="conv_last")
 
-        self.pool = Pool2D(
-            pool_type="avg", global_pooling=True, use_cudnn=False)
+        self.pool = AdaptiveAvgPool2d(1)
 
         self.last_conv = Conv2d(
             in_channels=make_divisible(scale * self.cls_ch_squeeze),
@@ -275,7 +275,7 @@ class ResidualUnit(nn.Layer):
 class SEModule(nn.Layer):
     def __init__(self, channel, reduction=4, name=""):
         super(SEModule, self).__init__()
-        self.avg_pool = Pool2D(pool_type="avg", global_pooling=True)
+        self.avg_pool = AdaptiveAvgPool2d(1)
         self.conv1 = Conv2d(
             in_channels=channel,
             out_channels=channel // reduction,

ppcls/modeling/architectures/res2net.py

@@ -18,9 +18,12 @@ from __future__ import print_function
 
 import numpy as np
 import paddle
-import paddle.fluid as fluid
-from paddle.fluid.param_attr import ParamAttr
-from paddle.fluid.dygraph.nn import Conv2D, Pool2D, BatchNorm, Linear, Dropout
+from paddle import ParamAttr
+import paddle.nn as nn
+import paddle.nn.functional as F
+from paddle.nn import Conv2d, BatchNorm, Linear, Dropout
+from paddle.nn import AdaptiveAvgPool2d, MaxPool2d, AvgPool2d
+from paddle.nn.initializer import Uniform
 
 import math
 
@@ -31,7 +34,7 @@ __all__ = [
 ]
 
 
-class ConvBNLayer(fluid.dygraph.Layer):
+class ConvBNLayer(nn.Layer):
     def __init__(
             self,
             num_channels,
@@ -43,15 +46,14 @@ class ConvBNLayer(fluid.dygraph.Layer):
             name=None, ):
         super(ConvBNLayer, self).__init__()
 
-        self._conv = Conv2D(
-            num_channels=num_channels,
-            num_filters=num_filters,
-            filter_size=filter_size,
+        self._conv = Conv2d(
+            in_channels=num_channels,
+            out_channels=num_filters,
+            kernel_size=filter_size,
             stride=stride,
             padding=(filter_size - 1) // 2,
             groups=groups,
-            act=None,
-            param_attr=ParamAttr(name=name + "_weights"),
+            weight_attr=ParamAttr(name=name + "_weights"),
             bias_attr=False)
         if name == "conv1":
             bn_name = "bn_" + name
@@ -71,7 +73,7 @@ class ConvBNLayer(fluid.dygraph.Layer):
         return y
 
 
-class BottleneckBlock(fluid.dygraph.Layer):
+class BottleneckBlock(nn.Layer):
     def __init__(self,
                  num_channels1,
                  num_channels2,
@@ -102,8 +104,7 @@ class BottleneckBlock(fluid.dygraph.Layer):
                     act='relu',
                     name=name + '_branch2b_' + str(s + 1)))
             self.conv1_list.append(conv1)
-        self.pool2d_avg = Pool2D(
-            pool_size=3, pool_stride=stride, pool_padding=1, pool_type='avg')
+        self.pool2d_avg = AvgPool2d(kernel_size=3, stride=stride, padding=1)
 
         self.conv2 = ConvBNLayer(
             num_channels=num_filters,
@@ -124,7 +125,7 @@ class BottleneckBlock(fluid.dygraph.Layer):
 
     def forward(self, inputs):
         y = self.conv0(inputs)
-        xs = fluid.layers.split(y, self.scales, 1)
+        xs = paddle.split(y, self.scales, 1)
         ys = []
         for s, conv1 in enumerate(self.conv1_list):
             if s == 0 or self.stride == 2:
@@ -135,18 +136,18 @@ class BottleneckBlock(fluid.dygraph.Layer):
             ys.append(xs[-1])
         else:
             ys.append(self.pool2d_avg(xs[-1]))
-        conv1 = fluid.layers.concat(ys, axis=1)
+        conv1 = paddle.concat(ys, axis=1)
         conv2 = self.conv2(conv1)
 
         if self.shortcut:
             short = inputs
         else:
             short = self.short(inputs)
-        y = fluid.layers.elementwise_add(x=short, y=conv2, act='relu')
+        y = paddle.elementwise_add(x=short, y=conv2, act='relu')
         return y
 
 
-class Res2Net(fluid.dygraph.Layer):
+class Res2Net(nn.Layer):
     def __init__(self, layers=50, scales=4, width=26, class_dim=1000):
         super(Res2Net, self).__init__()
 
@@ -178,8 +179,7 @@ class Res2Net(fluid.dygraph.Layer):
             stride=2,
             act='relu',
             name="conv1")
-        self.pool2d_max = Pool2D(
-            pool_size=3, pool_stride=2, pool_padding=1, pool_type='max')
+        self.pool2d_max = MaxPool2d(kernel_size=3, stride=2, padding=1)
 
         self.block_list = []
         for block in range(len(depth)):
@@ -207,8 +207,7 @@ class Res2Net(fluid.dygraph.Layer):
                 self.block_list.append(bottleneck_block)
                 shortcut = True
 
-        self.pool2d_avg = Pool2D(
-            pool_size=7, pool_type='avg', global_pooling=True)
+        self.pool2d_avg = AdaptiveAvgPool2d(1)
 
         self.pool2d_avg_channels = num_channels[-1] * 2
 
@@ -217,9 +216,8 @@ class Res2Net(fluid.dygraph.Layer):
         self.out = Linear(
             self.pool2d_avg_channels,
             class_dim,
-            param_attr=ParamAttr(
-                initializer=fluid.initializer.Uniform(-stdv, stdv),
-                name="fc_weights"),
+            weight_attr=ParamAttr(
+                initializer=Uniform(-stdv, stdv), name="fc_weights"),
             bias_attr=ParamAttr(name="fc_offset"))
 
     def forward(self, inputs):
@@ -228,7 +226,7 @@ class Res2Net(fluid.dygraph.Layer):
         for block in self.block_list:
             y = block(y)
         y = self.pool2d_avg(y)
-        y = fluid.layers.reshape(y, shape=[-1, self.pool2d_avg_channels])
+        y = paddle.reshape(y, shape=[-1, self.pool2d_avg_channels])
         y = self.out(y)
         return y
 

ppcls/modeling/architectures/xception_deeplab.py

@@ -2,7 +2,8 @@ import paddle
 from paddle import ParamAttr
 import paddle.nn as nn
 import paddle.nn.functional as F
-from paddle.nn import Conv2d, Pool2D, BatchNorm, Linear, Dropout
+from paddle.nn import Conv2d, BatchNorm, Linear, Dropout
+from paddle.nn import AdaptiveAvgPool2d, MaxPool2d, AvgPool2d
 
 __all__ = ["Xception41_deeplab", "Xception65_deeplab", "Xception71_deeplab"]
 
@@ -346,7 +347,7 @@ class XceptionDeeplab(nn.Layer):
         self.stride = s
 
         self._drop = Dropout(p=0.5)
-        self._pool = Pool2D(pool_type="avg", global_pooling=True)
+        self._pool = AdaptiveAvgPool2d(1)
         self._fc = Linear(
             self.chns[1][-1],
             class_dim,