fix layer helper

ppcls/modeling/architectures/GhostNet_wqz.py

@@ -0,0 +1,334 @@
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import math
+
+import paddle
+import paddle.fluid as fluid
+from paddle.fluid.param_attr import ParamAttr
+from paddle.fluid.initializer import MSRA
+from paddle.fluid.contrib.model_stat import summary
+
+__all__ = ["GhostNet", "GhostNetV1"]
+
+
+class GhostNet():
+    def __init__(self, width_mult):
+        cfgs = [
+            # k, t, c, SE, s
+            [3, 16, 16, 0, 1],
+            [3, 48, 24, 0, 2],
+            [3, 72, 24, 0, 1],
+            [5, 72, 40, 1, 2],
+            [5, 120, 40, 1, 1],
+            [3, 240, 80, 0, 2],
+            [3, 200, 80, 0, 1],
+            [3, 184, 80, 0, 1],
+            [3, 184, 80, 0, 1],
+            [3, 480, 112, 1, 1],
+            [3, 672, 112, 1, 1],
+            [5, 672, 160, 1, 2],
+            [5, 960, 160, 0, 1],
+            [5, 960, 160, 1, 1],
+            [5, 960, 160, 0, 1],
+            [5, 960, 160, 1, 1]
+        ]
+        self.cfgs = cfgs
+        self.width_mult = width_mult
+
+    def _make_divisible(self, v, divisor, min_value=None):
+        """
+        This function is taken from the original tf repo.
+        It ensures that all layers have a channel number that is divisible by 8
+        It can be seen here:
+        https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet.py
+        """
+        if min_value is None:
+            min_value = divisor
+        new_v = max(min_value, int(v + divisor / 2) // divisor * divisor)
+        # Make sure that round down does not go down by more than 10%.
+        if new_v < 0.9 * v:
+            new_v += divisor
+        return new_v
+
+    def conv_bn_layer(self,
+                      input,
+                      num_filters,
+                      filter_size,
+                      stride=1,
+                      groups=1,
+                      act=None,
+                      name=None,
+                      data_format="NCHW"):
+        print("conv bn, num_filters: {}, filter_size: {}, stride: {}".format(
+            num_filters, filter_size, stride))
+        x = fluid.layers.conv2d(
+            input=input,
+            num_filters=num_filters,
+            filter_size=filter_size,
+            stride=stride,
+            padding=(filter_size - 1) // 2,
+            groups=groups,
+            act=None,
+            param_attr=ParamAttr(
+                initializer=fluid.initializer.MSRA(), name=name + "_weights"),
+            bias_attr=False,
+            name=name + "_conv_op",
+            data_format=data_format)
+
+        x = fluid.layers.batch_norm(
+            input=x,
+            act=act,
+            name=name + "_bn",
+            param_attr=ParamAttr(name=name + "_bn_scale"),
+            bias_attr=ParamAttr(name=name + "_bn_offset"),
+            moving_mean_name=name + "_bn_mean",
+            moving_variance_name=name + "_bn_variance",
+            data_layout=data_format)
+        return x
+
+    def SElayer(self, input, num_channels, reduction_ratio=4, name=None):
+        pool = fluid.layers.pool2d(
+            input=input, pool_size=0, pool_type='avg', global_pooling=True)
+        stdv = 1.0 / math.sqrt(pool.shape[1] * 1.0)
+        squeeze = fluid.layers.fc(
+            input=pool,
+            size=num_channels // reduction_ratio,
+            act='relu',
+            param_attr=fluid.param_attr.ParamAttr(
+                initializer=fluid.initializer.Uniform(-stdv, stdv),
+                name=name + '_sqz_weights'),
+            bias_attr=ParamAttr(name=name + '_sqz_offset'))
+        stdv = 1.0 / math.sqrt(squeeze.shape[1] * 1.0)
+        excitation = fluid.layers.fc(
+            input=squeeze,
+            size=num_channels,
+            act=None,
+            param_attr=fluid.param_attr.ParamAttr(
+                initializer=fluid.initializer.Uniform(-stdv, stdv),
+                name=name + '_exc_weights'),
+            bias_attr=ParamAttr(name=name + '_exc_offset'))
+        excitation = fluid.layers.clip(
+            x=excitation, min=0, max=1, name=name + '_clip')
+        scale = fluid.layers.elementwise_mul(x=input, y=excitation, axis=0)
+        return scale
+
+    def depthwise_conv(self,
+                       inp,
+                       oup,
+                       kernel_size,
+                       stride=1,
+                       relu=False,
+                       name=None,
+                       data_format="NCHW"):
+        return self.conv_bn_layer(
+            input=inp,
+            num_filters=oup,
+            filter_size=kernel_size,
+            stride=stride,
+            groups=inp.shape[1] if data_format == "NCHW" else inp.shape[-1],
+            act="relu" if relu else None,
+            name=name + "_dw",
+            data_format=data_format)
+
+    def GhostModule(self,
+                    inp,
+                    oup,
+                    kernel_size=1,
+                    ratio=2,
+                    dw_size=3,
+                    stride=1,
+                    relu=True,
+                    name=None,
+                    data_format="NCHW"):
+        self.oup = oup
+        init_channels = math.ceil(oup / ratio)
+        new_channels = init_channels * (ratio - 1)
+        primary_conv = self.conv_bn_layer(
+            input=inp,
+            num_filters=init_channels,
+            filter_size=kernel_size,
+            stride=stride,
+            groups=1,
+            act="relu" if relu else None,
+            name=name + "_primary_conv",
+            data_format="NCHW")
+        cheap_operation = self.conv_bn_layer(
+            input=primary_conv,
+            num_filters=new_channels,
+            filter_size=dw_size,
+            stride=1,
+            groups=init_channels,
+            act="relu" if relu else None,
+            name=name + "_cheap_operation",
+            data_format=data_format)
+        out = fluid.layers.concat(
+            [primary_conv, cheap_operation], axis=1, name=name + "_concat")
+        return out[:, :self.oup, :, :]
+
+    def GhostBottleneck(self,
+                        inp,
+                        hidden_dim,
+                        oup,
+                        kernel_size,
+                        stride,
+                        use_se,
+                        name=None,
+                        data_format="NCHW"):
+        inp_channels = inp.shape[1]
+        x = self.GhostModule(
+            inp=inp,
+            oup=hidden_dim,
+            kernel_size=1,
+            stride=1,
+            relu=True,
+            name=name + "GhostBottle_1",
+            data_format="NCHW")
+        if stride == 2:
+            x = self.depthwise_conv(
+                inp=x,
+                oup=hidden_dim,
+                kernel_size=kernel_size,
+                stride=stride,
+                relu=False,
+                name=name + "_dw2",
+                data_format="NCHW")
+        if use_se:
+            x = self.SElayer(
+                input=x, num_channels=hidden_dim, name=name + "SElayer")
+        x = self.GhostModule(
+            inp=x,
+            oup=oup,
+            kernel_size=1,
+            relu=False,
+            name=name + "GhostModule_2")
+        if stride == 1 and inp_channels == oup:
+            shortcut = inp
+        else:
+            shortcut = self.depthwise_conv(
+                inp=inp,
+                oup=inp_channels,
+                kernel_size=kernel_size,
+                stride=stride,
+                relu=False,
+                name=name + "shortcut_depthwise_conv",
+                data_format="NCHW")
+            shortcut = self.conv_bn_layer(
+                input=shortcut,
+                num_filters=oup,
+                filter_size=1,
+                stride=1,
+                groups=1,
+                act=None,
+                name=name + "shortcut_conv_bn",
+                data_format="NCHW")
+        return fluid.layers.elementwise_add(
+            x=x, y=shortcut, axis=-1, act=None, name=name + "elementwise_add")
+
+    def net(self, input, class_dim=1000):
+        # build first layer:
+        output_channel = self._make_divisible(16 * self.width_mult, 4)
+        x = self.conv_bn_layer(
+            input=input,
+            num_filters=output_channel,
+            filter_size=3,
+            stride=2,
+            groups=1,
+            act="relu",
+            name="firstlayer",
+            data_format="NCHW")
+        input_channel = output_channel
+        # build inverted residual blocks
+        idx = 0
+        for k, exp_size, c, use_se, s in self.cfgs:
+            output_channel = self._make_divisible(c * self.width_mult, 4)
+            hidden_channel = self._make_divisible(exp_size * self.width_mult,
+                                                  4)
+            x = self.GhostBottleneck(
+                inp=x,
+                hidden_dim=hidden_channel,
+                oup=output_channel,
+                kernel_size=k,
+                stride=s,
+                use_se=use_se,
+                name="GhostBottle_" + str(idx),
+                data_format="NCHW")
+            input_channel = output_channel
+            idx += 1
+        # build last several layers
+        output_channel = self._make_divisible(exp_size * self.width_mult, 4)
+        x = self.conv_bn_layer(
+            input=x,
+            num_filters=output_channel,
+            filter_size=1,
+            stride=1,
+            groups=1,
+            act="relu",
+            name="lastlayer",
+            data_format="NCHW")
+        x = fluid.layers.pool2d(
+            input=x, pool_type='avg', global_pooling=True, data_format="NCHW")
+        input_channel = output_channel
+        output_channel = 1280
+
+        stdv = 1.0 / math.sqrt(x.shape[1] * 1.0)
+        out = fluid.layers.conv2d(
+            input=x,
+            num_filters=output_channel,
+            filter_size=1,
+            groups=1,
+            param_attr=ParamAttr(
+                name="fc_0_w",
+                initializer=fluid.initializer.Uniform(-stdv, stdv)),
+            bias_attr=False,
+            name="fc_0")
+        out = fluid.layers.batch_norm(
+            input=out,
+            act="relu",
+            name="fc_0_bn",
+            param_attr=ParamAttr(name="fc_0_bn_scale"),
+            bias_attr=ParamAttr(name="fc_0_bn_offset"),
+            moving_mean_name="fc_0_bn_mean",
+            moving_variance_name="fc_0_bn_variance",
+            data_layout="NCHW")
+        out = fluid.layers.dropout(x=out, dropout_prob=0.2)
+        stdv = 1.0 / math.sqrt(out.shape[1] * 1.0)
+        out = fluid.layers.fc(
+            input=out,
+            size=class_dim,
+            param_attr=ParamAttr(
+                name="fc_1_w",
+                initializer=fluid.initializer.Uniform(-stdv, stdv)),
+            bias_attr=ParamAttr(name="fc_1_bias"))
+        return out
+
+
+def GhostNet_0_5():
+    model = GhostNet(width_mult=0.5)
+    return model
+
+
+def GhostNet_1_0():
+    model = GhostNet(width_mult=1.0)
+    return model
+
+
+def GhostNet_1_3():
+    model = GhostNet(width_mult=1.3)
+    return model
+
+
+if __name__ == "__main__":
+    # from calc_flops import summary
+
+    image = fluid.data(name='image', shape=[-1, 3, 224, 224], dtype='float32')
+    model = GhostNet_1_3()
+    out = model.net(input=image, class_dim=1000)
+    test_program = fluid.default_main_program().clone(for_test=True)
+
+    place = fluid.CPUPlace()
+    exe = fluid.Executor(place)
+    exe.run(fluid.default_startup_program())
+
+    total_flops_params, is_quantize = summary(test_program)

ppcls/modeling/architectures/__init__.py

@@ -24,9 +24,11 @@ from .se_resnext_vd import SE_ResNeXt50_vd_32x4d, SE_ResNeXt50_vd_32x4d, SENet15
 from .dpn import DPN68
 from .densenet import DenseNet121
 from .hrnet import HRNet_W18_C
+from .efficientnet import EfficientNetB0
+from .googlenet import GoogLeNet
 from .mobilenet_v1 import MobileNetV1_x0_25, MobileNetV1_x0_5, MobileNetV1_x0_75, MobileNetV1
 from .mobilenet_v2 import MobileNetV2_x0_25, MobileNetV2_x0_5, MobileNetV2_x0_75, MobileNetV2, MobileNetV2_x1_5, MobileNetV2_x2_0
 from .mobilenet_v3 import MobileNetV3_small_x0_35, MobileNetV3_small_x0_5, MobileNetV3_small_x0_75, MobileNetV3_small_x1_0, MobileNetV3_small_x1_25, MobileNetV3_large_x0_35, MobileNetV3_large_x0_5, MobileNetV3_large_x0_75, MobileNetV3_large_x1_0, MobileNetV3_large_x1_25
 from .shufflenet_v2 import ShuffleNetV2_x0_25, ShuffleNetV2_x0_33, ShuffleNetV2_x0_5, ShuffleNetV2, ShuffleNetV2_x1_5, ShuffleNetV2_x2_0, ShuffleNetV2_swish
 
-from .distillation_models import ResNet50_vd_distill_MobileNetV3_large_x1_0
+from .distillation_models import ResNet50_vd_distill_MobileNetV3_large_x1_0

ppcls/modeling/architectures/densenet.py

@@ -20,7 +20,6 @@ import numpy as np
 import paddle
 import paddle.fluid as fluid
 from paddle.fluid.param_attr import ParamAttr
-from paddle.fluid.layer_helper import LayerHelper
 from paddle.fluid.dygraph.nn import Conv2D, Pool2D, BatchNorm, Linear, Dropout
 
 import math

ppcls/modeling/architectures/dpn.py

@@ -21,7 +21,6 @@ import sys
 import paddle
 import paddle.fluid as fluid
 from paddle.fluid.param_attr import ParamAttr
-from paddle.fluid.layer_helper import LayerHelper
 from paddle.fluid.dygraph.nn import Conv2D, Pool2D, BatchNorm, Linear
 
 import math

ppcls/modeling/architectures/efficientnet.py

@@ -1,7 +1,6 @@
 import paddle
 import paddle.fluid as fluid
 from paddle.fluid.param_attr import ParamAttr
-from paddle.fluid.layer_helper import LayerHelper
 from paddle.fluid.dygraph.nn import Conv2D, Pool2D, BatchNorm, Linear, Dropout
 import math
 import collections
@@ -491,6 +490,7 @@ class SEBlock(fluid.dygraph.Layer):
             num_squeezed_channels,
             oup,
             1,
+            act="sigmoid",
             use_bias=True,
             padding_type=padding_type,
             name=name + "_se_expand")
@@ -499,8 +499,6 @@ class SEBlock(fluid.dygraph.Layer):
         x = self._pool(inputs)
         x = self._conv1(x)
         x = self._conv2(x)
-        layer_helper = LayerHelper(self.full_name(), act='sigmoid')
-        x = layer_helper.append_activation(x)
         return fluid.layers.elementwise_mul(inputs, x)
 
 
@@ -565,18 +563,17 @@ class MbConvBlock(fluid.dygraph.Layer):
 
     def forward(self, inputs):
         x = inputs
-        layer_helper = LayerHelper(self.full_name(), act='swish')
         if self.expand_ratio != 1:
             x = self._ecn(x)
-            x = layer_helper.append_activation(x)
+            x = fluid.layers.swish(x)
         x = self._dcn(x)
-        x = layer_helper.append_activation(x)
+        x = fluid.layers.swish(x)
         if self.has_se:
             x = self._se(x)
         x = self._pcn(x)
         if self.id_skip and \
-            self.block_args.stride == 1 and \
-            self.block_args.input_filters == self.block_args.output_filters:
+                self.block_args.stride == 1 and \
+                self.block_args.input_filters == self.block_args.output_filters:
             if self.drop_connect_rate:
                 x = _drop_connect(x, self.drop_connect_rate, self.is_test)
             x = fluid.layers.elementwise_add(x, inputs)
@@ -697,8 +694,7 @@ class ExtractFeatures(fluid.dygraph.Layer):
 
     def forward(self, inputs):
         x = self._conv_stem(inputs)
-        layer_helper = LayerHelper(self.full_name(), act='swish')
-        x = layer_helper.append_activation(x)
+        x = fluid.layers.swish(x)
         for _mc_block in self.conv_seq:
             x = _mc_block(x)
         return x
@@ -914,4 +910,4 @@ def EfficientNetB7(is_test=False,
         override_params=override_params,
         use_se=use_se,
         **args)
-    return model
+    return model

ppcls/modeling/architectures/googlenet.py

@@ -1,18 +1,17 @@
 import paddle
 import paddle.fluid as fluid
 from paddle.fluid.param_attr import ParamAttr
-from paddle.fluid.layer_helper import LayerHelper
 from paddle.fluid.dygraph.nn import Conv2D, Pool2D, BatchNorm, Linear
 import math
 
-__all__ = ['GoogLeNet_DY']
+__all__ = ['GoogLeNet']
+
 
 def xavier(channels, filter_size, name):
     stdv = (3.0 / (filter_size**2 * channels))**0.5
     param_attr = ParamAttr(
         initializer=fluid.initializer.Uniform(-stdv, stdv),
         name=name + "_weights")
-
     return param_attr
 
 
@@ -90,8 +89,8 @@ class Inception(fluid.dygraph.Layer):
         convprj = self._convprj(pool)
 
         cat = fluid.layers.concat([conv1, conv3, conv5, convprj], axis=1)
-        layer_helper = LayerHelper(self.full_name(), act="relu")
-        return layer_helper.append_activation(cat)
+        cat = fluid.layers.relu(cat)
+        return cat
 
 
 class GoogleNetDY(fluid.dygraph.Layer):
@@ -205,4 +204,4 @@ class GoogleNetDY(fluid.dygraph.Layer):
 
 def GoogLeNet(**args):
     model = GoogleNetDY(**args)
-    return model
+    return model

ppcls/modeling/architectures/hrnet.py

@@ -20,7 +20,6 @@ import numpy as np
 import paddle
 import paddle.fluid as fluid
 from paddle.fluid.param_attr import ParamAttr
-from paddle.fluid.layer_helper import LayerHelper
 from paddle.fluid.dygraph.nn import Conv2D, Pool2D, BatchNorm, Linear
 
 import math
@@ -495,8 +494,7 @@ class FuseLayers(fluid.dygraph.Layer):
                     residual = fluid.layers.elementwise_add(
                         x=residual, y=y, act=None)
 
-            layer_helper = LayerHelper(self.full_name(), act='relu')
-            residual = layer_helper.append_activation(residual)
+            residual = fluid.layers.relu(residual)
             outs.append(residual)
 
         return outs

ppcls/modeling/architectures/mobilenet_v1.py

@@ -20,7 +20,6 @@ import numpy as np
 import paddle
 import paddle.fluid as fluid
 from paddle.fluid.param_attr import ParamAttr
-from paddle.fluid.layer_helper import LayerHelper
 from paddle.fluid.dygraph.nn import Conv2D, Pool2D, BatchNorm, Linear, Dropout
 from paddle.fluid.initializer import MSRA
 import math

ppcls/modeling/architectures/mobilenet_v2.py

@@ -20,7 +20,6 @@ import numpy as np
 import paddle
 import paddle.fluid as fluid
 from paddle.fluid.param_attr import ParamAttr
-from paddle.fluid.layer_helper import LayerHelper
 from paddle.fluid.dygraph.nn import Conv2D, Pool2D, BatchNorm, Linear, Dropout
 
 import math

ppcls/modeling/architectures/mobilenet_v3.py

@@ -20,7 +20,6 @@ import numpy as np
 import paddle
 import paddle.fluid as fluid
 from paddle.fluid.param_attr import ParamAttr
-from paddle.fluid.layer_helper import LayerHelper
 from paddle.fluid.dygraph.nn import Conv2D, Pool2D, BatchNorm, Linear, Dropout
 
 import math

ppcls/modeling/architectures/res2net.py

@@ -20,7 +20,6 @@ import numpy as np
 import paddle
 import paddle.fluid as fluid
 from paddle.fluid.param_attr import ParamAttr
-from paddle.fluid.layer_helper import LayerHelper
 from paddle.fluid.dygraph.nn import Conv2D, Pool2D, BatchNorm, Linear, Dropout
 
 import math
@@ -143,9 +142,8 @@ class BottleneckBlock(fluid.dygraph.Layer):
             short = inputs
         else:
             short = self.short(inputs)
-        y = fluid.layers.elementwise_add(x=short, y=conv2)
-        layer_helper = LayerHelper(self.full_name(), act='relu')
-        return layer_helper.append_activation(y)
+        y = fluid.layers.elementwise_add(x=short, y=conv2, act='relu')
+        return y
 
 
 class Res2Net(fluid.dygraph.Layer):

ppcls/modeling/architectures/res2net_vd.py

@@ -20,7 +20,6 @@ import numpy as np
 import paddle
 import paddle.fluid as fluid
 from paddle.fluid.param_attr import ParamAttr
-from paddle.fluid.layer_helper import LayerHelper
 from paddle.fluid.dygraph.nn import Conv2D, Pool2D, BatchNorm, Linear, Dropout
 
 import math
@@ -47,7 +46,11 @@ class ConvBNLayer(fluid.dygraph.Layer):
 
         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)
+            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,
@@ -150,9 +153,8 @@ class BottleneckBlock(fluid.dygraph.Layer):
             short = inputs
         else:
             short = self.short(inputs)
-        y = fluid.layers.elementwise_add(x=short, y=conv2)
-        layer_helper = LayerHelper(self.full_name(), act='relu')
-        return layer_helper.append_activation(y)
+        y = fluid.layers.elementwise_add(x=short, y=conv2, act='relu')
+        return y
 
 
 class Res2Net_vd(fluid.dygraph.Layer):

ppcls/modeling/architectures/resnet.py

@@ -20,7 +20,6 @@ import numpy as np
 import paddle
 import paddle.fluid as fluid
 from paddle.fluid.param_attr import ParamAttr
-from paddle.fluid.layer_helper import LayerHelper
 from paddle.fluid.dygraph.nn import Conv2D, Pool2D, BatchNorm, Linear, Dropout
 
 import math
@@ -118,10 +117,8 @@ class BottleneckBlock(fluid.dygraph.Layer):
         else:
             short = self.short(inputs)
 
-        y = fluid.layers.elementwise_add(x=short, y=conv2)
-
-        layer_helper = LayerHelper(self.full_name(), act="relu")
-        return layer_helper.append_activation(y)
+        y = fluid.layers.elementwise_add(x=short, y=conv2, act="relu")
+        return y
 
 
 class BasicBlock(fluid.dygraph.Layer):
@@ -165,10 +162,8 @@ class BasicBlock(fluid.dygraph.Layer):
             short = inputs
         else:
             short = self.short(inputs)
-        y = fluid.layers.elementwise_add(x=short, y=conv1)
-
-        layer_helper = LayerHelper(self.full_name(), act="relu")
-        return layer_helper.append_activation(y)
+        y = fluid.layers.elementwise_add(x=short, y=conv1, act="relu")
+        return y
 
 
 class ResNet(fluid.dygraph.Layer):

ppcls/modeling/architectures/resnet_name.py

@@ -1,213 +0,0 @@
-import numpy as np
-import argparse
-import ast
-import paddle
-import paddle.fluid as fluid
-from paddle.fluid.param_attr import ParamAttr
-from paddle.fluid.layer_helper import LayerHelper
-from paddle.fluid.dygraph.nn import Conv2D, Pool2D, BatchNorm, Linear
-from paddle.fluid.dygraph.base import to_variable
-
-from paddle.fluid import framework
-
-import math
-import sys
-import time
-
-class ConvBNLayer(fluid.dygraph.Layer):
-    def __init__(self,
-                 num_channels,
-                 num_filters,
-                 filter_size,
-                 stride=1,
-                 groups=1,
-                 act=None,
-                 name=None):
-        super(ConvBNLayer, self).__init__()
-
-        self._conv = Conv2D(
-            num_channels=num_channels,
-            num_filters=num_filters,
-            filter_size=filter_size,
-            stride=stride,
-            padding=(filter_size - 1) // 2,
-            groups=groups,
-            act=None,
-            param_attr=ParamAttr(name=name + "_weights"),
-            bias_attr=False)
-        if name == "conv1":
-            bn_name = "bn_" + name
-        else:
-            bn_name = "bn" + name[3:]
-        self._batch_norm = BatchNorm(num_filters, 
-                                     act=act,
-                                     param_attr=ParamAttr(name=bn_name + '_scale'),
-                                     bias_attr=ParamAttr(bn_name + '_offset'),
-                                     moving_mean_name=bn_name + '_mean',
-                                     moving_variance_name=bn_name + '_variance')
-
-    def forward(self, inputs):
-        y = self._conv(inputs)
-        y = self._batch_norm(y)
-        return y
-
-
-class BottleneckBlock(fluid.dygraph.Layer):
-    def __init__(self,
-                 num_channels,
-                 num_filters,
-                 stride,
-                 shortcut=True,
-                 name=None):
-        super(BottleneckBlock, self).__init__()
-
-        self.conv0 = ConvBNLayer(
-            num_channels=num_channels,
-            num_filters=num_filters,
-            filter_size=1,
-            act='relu',
-            name=name+"_branch2a")
-        self.conv1 = ConvBNLayer(
-            num_channels=num_filters,
-            num_filters=num_filters,
-            filter_size=3,
-            stride=stride,
-            act='relu',
-            name=name+"_branch2b")
-        self.conv2 = ConvBNLayer(
-            num_channels=num_filters,
-            num_filters=num_filters * 4,
-            filter_size=1,
-            act=None,
-            name=name+"_branch2c")
-
-        if not shortcut:
-            self.short = ConvBNLayer(
-                num_channels=num_channels,
-                num_filters=num_filters * 4,
-                filter_size=1,
-                stride=stride,
-                name=name + "_branch1")
-
-        self.shortcut = shortcut
-
-        self._num_channels_out = num_filters * 4
-
-    def forward(self, inputs):
-        y = self.conv0(inputs)
-        conv1 = self.conv1(y)
-        conv2 = self.conv2(conv1)
-
-        if self.shortcut:
-            short = inputs
-        else:
-            short = self.short(inputs)
-
-        y = fluid.layers.elementwise_add(x=short, y=conv2)
-
-        layer_helper = LayerHelper(self.full_name(), act='relu')
-        return layer_helper.append_activation(y)
-
-
-class ResNet(fluid.dygraph.Layer):
-    def __init__(self, layers=50, class_dim=1000):
-        super(ResNet, self).__init__()
-
-        self.layers = layers
-        supported_layers = [50, 101, 152]
-        assert layers in supported_layers, \
-            "supported layers are {} but input layer is {}".format(supported_layers, layers)
-
-        if layers == 50:
-            depth = [3, 4, 6, 3]
-        elif layers == 101:
-            depth = [3, 4, 23, 3]
-        elif layers == 152:
-            depth = [3, 8, 36, 3]
-        num_channels = [64, 256, 512, 1024]
-        num_filters = [64, 128, 256, 512]
-
-        self.conv = ConvBNLayer(
-            num_channels=3,
-            num_filters=64,
-            filter_size=7,
-            stride=2,
-            act='relu',
-            name="conv1")
-        self.pool2d_max = Pool2D(
-            pool_size=3,
-            pool_stride=2,
-            pool_padding=1,
-            pool_type='max')
-
-        self.bottleneck_block_list = []
-        for block in range(len(depth)):
-            shortcut = False
-            for i in range(depth[block]):
-                if layers in [101, 152] and block == 2:
-                    if i == 0:
-                        conv_name="res"+str(block+2)+"a"
-                    else:
-                        conv_name="res"+str(block+2)+"b"+str(i)
-                else:
-                    conv_name="res"+str(block+2)+chr(97+i)
-                bottleneck_block = self.add_sublayer(
-                    'bb_%d_%d' % (block, i),
-                    BottleneckBlock(
-                        num_channels=num_channels[block]
-                        if i == 0 else num_filters[block] * 4,
-                        num_filters=num_filters[block],
-                        stride=2 if i == 0 and block != 0 else 1,
-                        shortcut=shortcut,
-                        name=conv_name))
-                self.bottleneck_block_list.append(bottleneck_block)
-                shortcut = True
-
-        self.pool2d_avg = Pool2D(
-            pool_size=7, pool_type='avg', global_pooling=True)
-
-        self.pool2d_avg_output = num_filters[len(num_filters) - 1] * 4 * 1 * 1
-
-        stdv = 1.0 / math.sqrt(2048 * 1.0)
-
-        self.out = Linear(self.pool2d_avg_output,
-                      class_dim,
-                      param_attr=ParamAttr(
-                          initializer=fluid.initializer.Uniform(-stdv, stdv), name="fc_0.w_0"),
-                      bias_attr=ParamAttr(name="fc_0.b_0"))
-
-    def forward(self, inputs):
-        y = self.conv(inputs)
-        y = self.pool2d_max(y)
-        for bottleneck_block in self.bottleneck_block_list:
-            y = bottleneck_block(y)
-        y = self.pool2d_avg(y)
-        y = fluid.layers.reshape(y, shape=[-1, self.pool2d_avg_output])
-        y = self.out(y)
-        return y
-
-
-def ResNet50(**args):
-    model = ResNet(layers=50, **args)
-    return model
-
-
-def ResNet101(**args):
-    model = ResNet(layers=101, **args)
-    return model
-
-
-def ResNet152(**args):
-    model = ResNet(layers=152, **args)
-    return model
-
-
-if __name__ == "__main__":
-    import numpy as np
-    place = fluid.CPUPlace()
-    with fluid.dygraph.guard(place): 
-        model = ResNet50()
-        img = np.random.uniform(0, 255, [1, 3, 224, 224]).astype('float32')
-        img = fluid.dygraph.to_variable(img)
-        res = model(img)
-        print(res.shape)

ppcls/modeling/architectures/resnet_vc.py

@@ -20,7 +20,6 @@ import numpy as np
 import paddle
 import paddle.fluid as fluid
 from paddle.fluid.param_attr import ParamAttr
-from paddle.fluid.layer_helper import LayerHelper
 from paddle.fluid.dygraph.nn import Conv2D, Pool2D, BatchNorm, Linear, Dropout
 
 import math
@@ -120,10 +119,8 @@ class BottleneckBlock(fluid.dygraph.Layer):
         else:
             short = self.short(inputs)
 
-        y = fluid.layers.elementwise_add(x=short, y=conv2)
-
-        layer_helper = LayerHelper(self.full_name(), act='relu')
-        return layer_helper.append_activation(y)
+        y = fluid.layers.elementwise_add(x=short, y=conv2, act='relu')
+        return y
 
 
 class BasicBlock(fluid.dygraph.Layer):
@@ -167,10 +164,8 @@ class BasicBlock(fluid.dygraph.Layer):
             short = inputs
         else:
             short = self.short(inputs)
-        y = fluid.layers.elementwise_add(x=short, y=conv1)
-
-        layer_helper = LayerHelper(self.full_name(), act='relu')
-        return layer_helper.append_activation(y)
+        y = fluid.layers.elementwise_add(x=short, y=conv1, act='relu')
+        return y
 
 
 class ResNet_vc(fluid.dygraph.Layer):

ppcls/modeling/architectures/resnet_vd.py

@@ -20,7 +20,6 @@ import numpy as np
 import paddle
 import paddle.fluid as fluid
 from paddle.fluid.param_attr import ParamAttr
-from paddle.fluid.layer_helper import LayerHelper
 from paddle.fluid.dygraph.nn import Conv2D, Pool2D, BatchNorm, Linear, Dropout
 
 import math
@@ -130,10 +129,8 @@ class BottleneckBlock(fluid.dygraph.Layer):
             short = inputs
         else:
             short = self.short(inputs)
-        y = fluid.layers.elementwise_add(x=short, y=conv2)
-
-        layer_helper = LayerHelper(self.full_name(), act='relu')
-        return layer_helper.append_activation(y)
+        y = fluid.layers.elementwise_add(x=short, y=conv2, act='relu')
+        return y
 
 
 class BasicBlock(fluid.dygraph.Layer):
@@ -179,10 +176,8 @@ class BasicBlock(fluid.dygraph.Layer):
             short = inputs
         else:
             short = self.short(inputs)
-        y = fluid.layers.elementwise_add(x=short, y=conv1)
-
-        layer_helper = LayerHelper(self.full_name(), act='relu')
-        return layer_helper.append_activation(y)
+        y = fluid.layers.elementwise_add(x=short, y=conv1, act='relu')
+        return y
 
 
 class ResNet_vd(fluid.dygraph.Layer):

ppcls/modeling/architectures/resnext.py

@@ -20,7 +20,6 @@ import numpy as np
 import paddle
 import paddle.fluid as fluid
 from paddle.fluid.param_attr import ParamAttr
-from paddle.fluid.layer_helper import LayerHelper
 from paddle.fluid.dygraph.nn import Conv2D, Pool2D, BatchNorm, Linear, Dropout
 
 import math
@@ -122,10 +121,8 @@ class BottleneckBlock(fluid.dygraph.Layer):
         else:
             short = self.short(inputs)
 
-        y = fluid.layers.elementwise_add(x=short, y=conv2)
-
-        layer_helper = LayerHelper(self.full_name(), act='relu')
-        return layer_helper.append_activation(y)
+        y = fluid.layers.elementwise_add(x=short, y=conv2, act='relu')
+        return y
 
 
 class ResNeXt(fluid.dygraph.Layer):

ppcls/modeling/architectures/resnext_vd.py

@@ -20,7 +20,6 @@ import numpy as np
 import paddle
 import paddle.fluid as fluid
 from paddle.fluid.param_attr import ParamAttr
-from paddle.fluid.layer_helper import LayerHelper
 from paddle.fluid.dygraph.nn import Conv2D, Pool2D, BatchNorm, Linear, Dropout
 
 import math
@@ -46,7 +45,11 @@ class ConvBNLayer(fluid.dygraph.Layer):
 
         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)
+            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,
@@ -131,10 +134,8 @@ class BottleneckBlock(fluid.dygraph.Layer):
         else:
             short = self.short(inputs)
 
-        y = fluid.layers.elementwise_add(x=short, y=conv2)
-
-        layer_helper = LayerHelper(self.full_name(), act='relu')
-        return layer_helper.append_activation(y)
+        y = fluid.layers.elementwise_add(x=short, y=conv2, act='relu')
+        return y
 
 
 class ResNeXt(fluid.dygraph.Layer):

ppcls/modeling/architectures/se_resnet_vd.py

@@ -19,7 +19,6 @@ import numpy as np
 import paddle
 import paddle.fluid as fluid
 from paddle.fluid.param_attr import ParamAttr
-from paddle.fluid.layer_helper import LayerHelper
 from paddle.fluid.dygraph.nn import Conv2D, Pool2D, BatchNorm, Linear, Dropout
 
 import math
@@ -137,10 +136,8 @@ class BottleneckBlock(fluid.dygraph.Layer):
             short = inputs
         else:
             short = self.short(inputs)
-        y = fluid.layers.elementwise_add(x=short, y=scale)
-
-        layer_helper = LayerHelper(self.full_name(), act='relu')
-        return layer_helper.append_activation(y)
+        y = fluid.layers.elementwise_add(x=short, y=scale, act='relu')
+        return y
 
 
 class BasicBlock(fluid.dygraph.Layer):
@@ -194,10 +191,8 @@ class BasicBlock(fluid.dygraph.Layer):
             short = inputs
         else:
             short = self.short(inputs)
-        y = fluid.layers.elementwise_add(x=short, y=scale)
-
-        layer_helper = LayerHelper(self.full_name(), act='relu')
-        return layer_helper.append_activation(y)
+        y = fluid.layers.elementwise_add(x=short, y=scale, act='relu')
+        return y
 
 
 class SELayer(fluid.dygraph.Layer):

ppcls/modeling/architectures/se_resnext_vd.py

@@ -20,7 +20,6 @@ import numpy as np
 import paddle
 import paddle.fluid as fluid
 from paddle.fluid.param_attr import ParamAttr
-from paddle.fluid.layer_helper import LayerHelper
 from paddle.fluid.dygraph.nn import Conv2D, Pool2D, BatchNorm, Linear, Dropout
 
 import math
@@ -131,10 +130,8 @@ class BottleneckBlock(fluid.dygraph.Layer):
             short = inputs
         else:
             short = self.short(inputs)
-        y = fluid.layers.elementwise_add(x=short, y=scale)
-
-        layer_helper = LayerHelper(self.full_name(), act='relu')
-        return layer_helper.append_activation(y)
+        y = fluid.layers.elementwise_add(x=short, y=scale, act='relu')
+        return y
 
 
 class SELayer(fluid.dygraph.Layer):

ppcls/modeling/architectures/shufflenet_v2.py

@@ -20,7 +20,6 @@ import numpy as np
 import paddle
 import paddle.fluid as fluid
 from paddle.fluid.param_attr import ParamAttr
-from paddle.fluid.layer_helper import LayerHelper
 from paddle.fluid.dygraph.nn import Conv2D, Pool2D, BatchNorm, Linear, Dropout
 from paddle.fluid.initializer import MSRA
 import math

ppcls/modeling/architectures/xception.py

@@ -1,7 +1,6 @@
 import paddle
 import paddle.fluid as fluid
 from paddle.fluid.param_attr import ParamAttr
-from paddle.fluid.layer_helper import LayerHelper
 from paddle.fluid.dygraph.nn import Conv2D, Pool2D, BatchNorm, Linear
 import math
 
@@ -99,11 +98,10 @@ class EntryFlowBottleneckBlock(fluid.dygraph.Layer):
     def forward(self, inputs):
         conv0 = inputs
         short = self._short(inputs)
-        layer_helper = LayerHelper(self.full_name(), act="relu")
         if self.relu_first:
-            conv0 = layer_helper.append_activation(conv0)
+            conv0 = fluid.layers.relu(conv0)
         conv1 = self._conv1(conv0)
-        conv2 = layer_helper.append_activation(conv1)
+        conv2 = fluid.layers.relu(conv1)
         conv2 = self._conv2(conv2)
         pool = self._pool(conv2)
         return fluid.layers.elementwise_add(x=short, y=pool)
@@ -177,12 +175,11 @@ class MiddleFlowBottleneckBlock(fluid.dygraph.Layer):
             name=name + "_branch2c_weights")
 
     def forward(self, inputs):
-        layer_helper = LayerHelper(self.full_name(), act="relu")
-        conv0 = layer_helper.append_activation(inputs)
+        conv0 = fluid.layers.relu(inputs)
         conv0 = self._conv_0(conv0)
-        conv1 = layer_helper.append_activation(conv0)
+        conv1 = fluid.layers.relu(conv0)
         conv1 = self._conv_1(conv1)
-        conv2 = layer_helper.append_activation(conv1)
+        conv2 = fluid.layers.relu(conv1)
         conv2 = self._conv_2(conv2)
         return fluid.layers.elementwise_add(x=inputs, y=conv2)
 
@@ -276,10 +273,9 @@ class ExitFlowBottleneckBlock(fluid.dygraph.Layer):
 
     def forward(self, inputs):
         short = self._short(inputs)
-        layer_helper = LayerHelper(self.full_name(), act="relu")
-        conv0 = layer_helper.append_activation(inputs)
+        conv0 = fluid.layers.relu(inputs)
         conv1 = self._conv_1(conv0)
-        conv2 = layer_helper.append_activation(conv1)
+        conv2 = fluid.layers.relu(conv1)
         conv2 = self._conv_2(conv2)
         pool = self._pool(conv2)
         return fluid.layers.elementwise_add(x=short, y=pool)
@@ -306,12 +302,11 @@ class ExitFlow(fluid.dygraph.Layer):
             bias_attr=ParamAttr(name="fc_offset"))
 
     def forward(self, inputs):
-        layer_helper = LayerHelper(self.full_name(), act="relu")
         conv0 = self._conv_0(inputs)
         conv1 = self._conv_1(conv0)
-        conv1 = layer_helper.append_activation(conv1)
+        conv1 = fluid.layers.relu(conv1)
         conv2 = self._conv_2(conv1)
-        conv2 = layer_helper.append_activation(conv2)
+        conv2 = fluid.layers.relu(conv2)
         pool = self._pool(conv2)
         pool = fluid.layers.reshape(pool, [0, -1])
         out = self._out(pool)

ppcls/modeling/architectures/xception_deeplab.py

@@ -1,7 +1,6 @@
 import paddle
 import paddle.fluid as fluid
 from paddle.fluid.param_attr import ParamAttr
-from paddle.fluid.layer_helper import LayerHelper
 from paddle.fluid.dygraph.nn import Conv2D, Pool2D, BatchNorm, Linear, Dropout
 
 __all__ = ["Xception41_deeplab", "Xception65_deeplab", "Xception71_deeplab"]
@@ -226,13 +225,12 @@ class Xception_Block(fluid.dygraph.Layer):
                 name=name + "/shortcut")
 
     def forward(self, inputs):
-        layer_helper = LayerHelper(self.full_name(), act='relu')
         if not self.activation_fn_in_separable_conv:
-            x = layer_helper.append_activation(inputs)
+            x = fluid.layers.relu(inputs)
             x = self._conv1(x)
-            x = layer_helper.append_activation(x)
+            x = fluid.layers.relu(x)
             x = self._conv2(x)
-            x = layer_helper.append_activation(x)
+            x = fluid.layers.relu(x)
             x = self._conv3(x)
         else:
             x = self._conv1(inputs)

tools/run.sh

@@ -5,5 +5,5 @@ export PYTHONPATH=$PWD:$PYTHONPATH
 python -m paddle.distributed.launch \
     --selected_gpus="0,1,2,3" \
     tools/train.py \
-        -c ./configs/ResNet/ResNet50_vd.yaml \
+        -c ./configs/ResNet/ResNet50.yaml \
         -o print_interval=10