fix resnext_wsl

ppcls/modeling/architectures/__init__.py

@@ -34,5 +34,6 @@ from .shufflenet_v2 import ShuffleNetV2_x0_25, ShuffleNetV2_x0_33, ShuffleNetV2_
 from .alexnet import AlexNet
 from .inception_v4 import InceptionV4
 from .xception_deeplab import Xception41_deeplab, Xception65_deeplab, Xception71_deeplab
+from .resnext101_wsl import ResNeXt101_32x8d_wsl, ResNeXt101_32x16d_wsl, ResNeXt101_32x32d_wsl, ResNeXt101_32x48d_wsl
 
 from .distillation_models import ResNet50_vd_distill_MobileNetV3_large_x1_0

ppcls/modeling/architectures/res2net_vd.py

@@ -202,8 +202,7 @@ class Res2Net_vd(nn.Layer):
             stride=1,
             act='relu',
             name="conv1_3")
-        self.pool2d_max = MaxPool2d(
-            kernel_size=3, stride=2, padding=1, ceil_mode=True)
+        self.pool2d_max = MaxPool2d(kernel_size=3, stride=2, padding=1)
 
         self.block_list = []
         for block in range(len(depth)):

ppcls/modeling/architectures/se_resnet_vd.py

@@ -17,9 +17,12 @@ 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
 
@@ -29,7 +32,7 @@ __all__ = [
 ]
 
 
-class ConvBNLayer(fluid.dygraph.Layer):
+class ConvBNLayer(nn.Layer):
     def __init__(
             self,
             num_channels,
@@ -43,21 +46,17 @@ class ConvBNLayer(fluid.dygraph.Layer):
         super(ConvBNLayer, self).__init__()
 
         self.is_vd_mode = is_vd_mode
-        self._pool2d_avg = Pool2D(
-            pool_size=2,
-            pool_stride=2,
-            pool_padding=0,
-            pool_type='avg',
-            ceil_mode=True)
-        self._conv = Conv2D(
-            num_channels=num_channels,
-            num_filters=num_filters,
-            filter_size=filter_size,
+        self._pool2d_avg = AvgPool2d(
+            kernel_size=2, stride=2, padding=0, ceil_mode=True)
+
+        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
@@ -79,7 +78,7 @@ class ConvBNLayer(fluid.dygraph.Layer):
         return y
 
 
-class BottleneckBlock(fluid.dygraph.Layer):
+class BottleneckBlock(nn.Layer):
     def __init__(self,
                  num_channels,
                  num_filters,
@@ -136,11 +135,11 @@ class BottleneckBlock(fluid.dygraph.Layer):
             short = inputs
         else:
             short = self.short(inputs)
-        y = fluid.layers.elementwise_add(x=short, y=scale, act='relu')
+        y = paddle.elementwise_add(x=short, y=scale, act='relu')
         return y
 
 
-class BasicBlock(fluid.dygraph.Layer):
+class BasicBlock(nn.Layer):
     def __init__(self,
                  num_channels,
                  num_filters,
@@ -191,15 +190,15 @@ class BasicBlock(fluid.dygraph.Layer):
             short = inputs
         else:
             short = self.short(inputs)
-        y = fluid.layers.elementwise_add(x=short, y=scale, act='relu')
+        y = paddle.elementwise_add(x=short, y=scale, act='relu')
         return y
 
 
-class SELayer(fluid.dygraph.Layer):
+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
 
@@ -208,34 +207,32 @@ class SELayer(fluid.dygraph.Layer):
         self.squeeze = Linear(
             num_channels,
             med_ch,
-            act="relu",
-            param_attr=ParamAttr(
-                initializer=fluid.initializer.Uniform(-stdv, stdv),
-                name=name + "_sqz_weights"),
+            weight_attr=ParamAttr(
+                initializer=Uniform(-stdv, stdv), name=name + "_sqz_weights"),
             bias_attr=ParamAttr(name=name + '_sqz_offset'))
 
         stdv = 1.0 / math.sqrt(med_ch * 1.0)
         self.excitation = Linear(
             med_ch,
             num_filters,
-            act="sigmoid",
-            param_attr=ParamAttr(
-                initializer=fluid.initializer.Uniform(-stdv, stdv),
-                name=name + "_exc_weights"),
+            weight_attr=ParamAttr(
+                initializer=Uniform(-stdv, stdv), name=name + "_exc_weights"),
             bias_attr=ParamAttr(name=name + '_exc_offset'))
 
     def forward(self, input):
         pool = self.pool2d_gap(input)
-        pool = fluid.layers.reshape(pool, shape=[-1, self._num_channels])
+        pool = paddle.reshape(pool, shape=[-1, self._num_channels])
         squeeze = self.squeeze(pool)
+        squeeze = F.relu(squeeze)
         excitation = self.excitation(squeeze)
-        excitation = fluid.layers.reshape(
+        excitation = F.sigmoid(excitation)
+        excitation = paddle.reshape(
             excitation, shape=[-1, self._num_channels, 1, 1])
         out = input * excitation
         return out
 
 
-class SE_ResNet_vd(fluid.dygraph.Layer):
+class SE_ResNet_vd(nn.Layer):
     def __init__(self, layers=50, class_dim=1000):
         super(SE_ResNet_vd, self).__init__()
 
@@ -280,8 +277,7 @@ class SE_ResNet_vd(fluid.dygraph.Layer):
             stride=1,
             act='relu',
             name="conv1_3")
-        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 = []
         if layers >= 50:
@@ -325,8 +321,7 @@ class SE_ResNet_vd(fluid.dygraph.Layer):
                     self.block_list.append(basic_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
 
@@ -335,9 +330,8 @@ class SE_ResNet_vd(fluid.dygraph.Layer):
         self.out = Linear(
             self.pool2d_avg_channels,
             class_dim,
-            param_attr=ParamAttr(
-                initializer=fluid.initializer.Uniform(-stdv, stdv),
-                name="fc6_weights"),
+            weight_attr=ParamAttr(
+                initializer=Uniform(-stdv, stdv), name="fc6_weights"),
             bias_attr=ParamAttr(name="fc6_offset"))
 
     def forward(self, inputs):
@@ -348,7 +342,7 @@ class SE_ResNet_vd(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