paddlex 2.1.0__py3-none-any.whl → 3.0.0b2__py3-none-any.whl

paddlex/ppcls/arch/backbone/model_zoo/ghostnet.py

@@ -1,363 +0,0 @@
-# copyright (c) 2021 PaddlePaddle Authors. All Rights Reserve.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#    http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-# Code was based on https://github.com/huawei-noah/CV-Backbones/tree/master/ghostnet_pytorch
-
-import math
-import paddle
-from paddle import ParamAttr
-import paddle.nn as nn
-import paddle.nn.functional as F
-from paddle.nn import Conv2D, BatchNorm, AdaptiveAvgPool2D, Linear
-from paddle.regularizer import L2Decay
-from paddle.nn.initializer import Uniform, KaimingNormal
-
-from paddlex.ppcls.utils.save_load import load_dygraph_pretrain, load_dygraph_pretrain_from_url
-
-MODEL_URLS = {
-    "GhostNet_x0_5":
-    "https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/GhostNet_x0_5_pretrained.pdparams",
-    "GhostNet_x1_0":
-    "https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/GhostNet_x1_0_pretrained.pdparams",
-    "GhostNet_x1_3":
-    "https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/GhostNet_x1_3_pretrained.pdparams",
-}
-
-__all__ = list(MODEL_URLS.keys())
-
-
-class ConvBNLayer(nn.Layer):
-    def __init__(self,
-                 in_channels,
-                 out_channels,
-                 kernel_size,
-                 stride=1,
-                 groups=1,
-                 act="relu",
-                 name=None):
-        super(ConvBNLayer, self).__init__()
-        self._conv = Conv2D(
-            in_channels=in_channels,
-            out_channels=out_channels,
-            kernel_size=kernel_size,
-            stride=stride,
-            padding=(kernel_size - 1) // 2,
-            groups=groups,
-            weight_attr=ParamAttr(
-                initializer=KaimingNormal(), name=name + "_weights"),
-            bias_attr=False)
-        bn_name = name + "_bn"
-
-        self._batch_norm = BatchNorm(
-            num_channels=out_channels,
-            act=act,
-            param_attr=ParamAttr(
-                name=bn_name + "_scale", regularizer=L2Decay(0.0)),
-            bias_attr=ParamAttr(
-                name=bn_name + "_offset", regularizer=L2Decay(0.0)),
-            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 SEBlock(nn.Layer):
-    def __init__(self, num_channels, reduction_ratio=4, name=None):
-        super(SEBlock, self).__init__()
-        self.pool2d_gap = AdaptiveAvgPool2D(1)
-        self._num_channels = num_channels
-        stdv = 1.0 / math.sqrt(num_channels * 1.0)
-        med_ch = num_channels // reduction_ratio
-        self.squeeze = Linear(
-            num_channels,
-            med_ch,
-            weight_attr=ParamAttr(
-                initializer=Uniform(-stdv, stdv), name=name + "_1_weights"),
-            bias_attr=ParamAttr(name=name + "_1_offset"))
-        stdv = 1.0 / math.sqrt(med_ch * 1.0)
-        self.excitation = Linear(
-            med_ch,
-            num_channels,
-            weight_attr=ParamAttr(
-                initializer=Uniform(-stdv, stdv), name=name + "_2_weights"),
-            bias_attr=ParamAttr(name=name + "_2_offset"))
-
-    def forward(self, inputs):
-        pool = self.pool2d_gap(inputs)
-        pool = paddle.squeeze(pool, axis=[2, 3])
-        squeeze = self.squeeze(pool)
-        squeeze = F.relu(squeeze)
-        excitation = self.excitation(squeeze)
-        excitation = paddle.clip(x=excitation, min=0, max=1)
-        excitation = paddle.unsqueeze(excitation, axis=[2, 3])
-        out = paddle.multiply(inputs, excitation)
-        return out
-
-
-class GhostModule(nn.Layer):
-    def __init__(self,
-                 in_channels,
-                 output_channels,
-                 kernel_size=1,
-                 ratio=2,
-                 dw_size=3,
-                 stride=1,
-                 relu=True,
-                 name=None):
-        super(GhostModule, self).__init__()
-        init_channels = int(math.ceil(output_channels / ratio))
-        new_channels = int(init_channels * (ratio - 1))
-        self.primary_conv = ConvBNLayer(
-            in_channels=in_channels,
-            out_channels=init_channels,
-            kernel_size=kernel_size,
-            stride=stride,
-            groups=1,
-            act="relu" if relu else None,
-            name=name + "_primary_conv")
-        self.cheap_operation = ConvBNLayer(
-            in_channels=init_channels,
-            out_channels=new_channels,
-            kernel_size=dw_size,
-            stride=1,
-            groups=init_channels,
-            act="relu" if relu else None,
-            name=name + "_cheap_operation")
-
-    def forward(self, inputs):
-        x = self.primary_conv(inputs)
-        y = self.cheap_operation(x)
-        out = paddle.concat([x, y], axis=1)
-        return out
-
-
-class GhostBottleneck(nn.Layer):
-    def __init__(self,
-                 in_channels,
-                 hidden_dim,
-                 output_channels,
-                 kernel_size,
-                 stride,
-                 use_se,
-                 name=None):
-        super(GhostBottleneck, self).__init__()
-        self._stride = stride
-        self._use_se = use_se
-        self._num_channels = in_channels
-        self._output_channels = output_channels
-        self.ghost_module_1 = GhostModule(
-            in_channels=in_channels,
-            output_channels=hidden_dim,
-            kernel_size=1,
-            stride=1,
-            relu=True,
-            name=name + "_ghost_module_1")
-        if stride == 2:
-            self.depthwise_conv = ConvBNLayer(
-                in_channels=hidden_dim,
-                out_channels=hidden_dim,
-                kernel_size=kernel_size,
-                stride=stride,
-                groups=hidden_dim,
-                act=None,
-                name=name +
-                "_depthwise_depthwise"  # looks strange due to an old typo, will be fixed later.
-            )
-        if use_se:
-            self.se_block = SEBlock(num_channels=hidden_dim, name=name + "_se")
-        self.ghost_module_2 = GhostModule(
-            in_channels=hidden_dim,
-            output_channels=output_channels,
-            kernel_size=1,
-            relu=False,
-            name=name + "_ghost_module_2")
-        if stride != 1 or in_channels != output_channels:
-            self.shortcut_depthwise = ConvBNLayer(
-                in_channels=in_channels,
-                out_channels=in_channels,
-                kernel_size=kernel_size,
-                stride=stride,
-                groups=in_channels,
-                act=None,
-                name=name +
-                "_shortcut_depthwise_depthwise"  # looks strange due to an old typo, will be fixed later.
-            )
-            self.shortcut_conv = ConvBNLayer(
-                in_channels=in_channels,
-                out_channels=output_channels,
-                kernel_size=1,
-                stride=1,
-                groups=1,
-                act=None,
-                name=name + "_shortcut_conv")
-
-    def forward(self, inputs):
-        x = self.ghost_module_1(inputs)
-        if self._stride == 2:
-            x = self.depthwise_conv(x)
-        if self._use_se:
-            x = self.se_block(x)
-        x = self.ghost_module_2(x)
-        if self._stride == 1 and self._num_channels == self._output_channels:
-            shortcut = inputs
-        else:
-            shortcut = self.shortcut_depthwise(inputs)
-            shortcut = self.shortcut_conv(shortcut)
-        return paddle.add(x=x, y=shortcut)
-
-
-class GhostNet(nn.Layer):
-    def __init__(self, scale, class_num=1000):
-        super(GhostNet, self).__init__()
-        self.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.scale = scale
-        output_channels = int(self._make_divisible(16 * self.scale, 4))
-        self.conv1 = ConvBNLayer(
-            in_channels=3,
-            out_channels=output_channels,
-            kernel_size=3,
-            stride=2,
-            groups=1,
-            act="relu",
-            name="conv1")
-        # build inverted residual blocks
-        idx = 0
-        self.ghost_bottleneck_list = []
-        for k, exp_size, c, use_se, s in self.cfgs:
-            in_channels = output_channels
-            output_channels = int(self._make_divisible(c * self.scale, 4))
-            hidden_dim = int(self._make_divisible(exp_size * self.scale, 4))
-            ghost_bottleneck = self.add_sublayer(
-                name="_ghostbottleneck_" + str(idx),
-                sublayer=GhostBottleneck(
-                    in_channels=in_channels,
-                    hidden_dim=hidden_dim,
-                    output_channels=output_channels,
-                    kernel_size=k,
-                    stride=s,
-                    use_se=use_se,
-                    name="_ghostbottleneck_" + str(idx)))
-            self.ghost_bottleneck_list.append(ghost_bottleneck)
-            idx += 1
-        # build last several layers
-        in_channels = output_channels
-        output_channels = int(self._make_divisible(exp_size * self.scale, 4))
-        self.conv_last = ConvBNLayer(
-            in_channels=in_channels,
-            out_channels=output_channels,
-            kernel_size=1,
-            stride=1,
-            groups=1,
-            act="relu",
-            name="conv_last")
-        self.pool2d_gap = AdaptiveAvgPool2D(1)
-        in_channels = output_channels
-        self._fc0_output_channels = 1280
-        self.fc_0 = ConvBNLayer(
-            in_channels=in_channels,
-            out_channels=self._fc0_output_channels,
-            kernel_size=1,
-            stride=1,
-            act="relu",
-            name="fc_0")
-        self.dropout = nn.Dropout(p=0.2)
-        stdv = 1.0 / math.sqrt(self._fc0_output_channels * 1.0)
-        self.fc_1 = Linear(
-            self._fc0_output_channels,
-            class_num,
-            weight_attr=ParamAttr(
-                name="fc_1_weights", initializer=Uniform(-stdv, stdv)),
-            bias_attr=ParamAttr(name="fc_1_offset"))
-
-    def forward(self, inputs):
-        x = self.conv1(inputs)
-        for ghost_bottleneck in self.ghost_bottleneck_list:
-            x = ghost_bottleneck(x)
-        x = self.conv_last(x)
-        x = self.pool2d_gap(x)
-        x = self.fc_0(x)
-        x = self.dropout(x)
-        x = paddle.reshape(x, shape=[-1, self._fc0_output_channels])
-        x = self.fc_1(x)
-        return x
-
-    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 _load_pretrained(pretrained, model, model_url, use_ssld=False):
-    if pretrained is False:
-        pass
-    elif pretrained is True:
-        load_dygraph_pretrain_from_url(model, model_url, use_ssld=use_ssld)
-    elif isinstance(pretrained, str):
-        load_dygraph_pretrain(model, pretrained)
-    else:
-        raise RuntimeError(
-            "pretrained type is not available. Please use `string` or `boolean` type."
-        )
-
-
-def GhostNet_x0_5(pretrained=False, use_ssld=False, **kwargs):
-    model = GhostNet(scale=0.5, **kwargs)
-    _load_pretrained(
-        pretrained, model, MODEL_URLS["GhostNet_x0_5"], use_ssld=use_ssld)
-    return model
-
-
-def GhostNet_x1_0(pretrained=False, use_ssld=False, **kwargs):
-    model = GhostNet(scale=1.0, **kwargs)
-    _load_pretrained(
-        pretrained, model, MODEL_URLS["GhostNet_x1_0"], use_ssld=use_ssld)
-    return model
-
-
-def GhostNet_x1_3(pretrained=False, use_ssld=False, **kwargs):
-    model = GhostNet(scale=1.3, **kwargs)
-    _load_pretrained(
-        pretrained, model, MODEL_URLS["GhostNet_x1_3"], use_ssld=use_ssld)
-    return model

paddlex/ppcls/arch/backbone/model_zoo/googlenet.py

@@ -1,229 +0,0 @@
-import paddle
-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
-
-from paddlex.ppcls.utils.save_load import load_dygraph_pretrain, load_dygraph_pretrain_from_url
-
-MODEL_URLS = {
-    "GoogLeNet":
-    "https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/GoogLeNet_pretrained.pdparams",
-}
-
-__all__ = list(MODEL_URLS.keys())
-
-
-def xavier(channels, filter_size, name):
-    stdv = (3.0 / (filter_size**2 * channels))**0.5
-    param_attr = ParamAttr(
-        initializer=Uniform(-stdv, stdv), name=name + "_weights")
-    return param_attr
-
-
-class ConvLayer(nn.Layer):
-    def __init__(self,
-                 num_channels,
-                 num_filters,
-                 filter_size,
-                 stride=1,
-                 groups=1,
-                 act=None,
-                 name=None):
-        super(ConvLayer, self).__init__()
-
-        self._conv = Conv2D(
-            in_channels=num_channels,
-            out_channels=num_filters,
-            kernel_size=filter_size,
-            stride=stride,
-            padding=(filter_size - 1) // 2,
-            groups=groups,
-            weight_attr=ParamAttr(name=name + "_weights"),
-            bias_attr=False)
-
-    def forward(self, inputs):
-        y = self._conv(inputs)
-        return y
-
-
-class Inception(nn.Layer):
-    def __init__(self,
-                 input_channels,
-                 output_channels,
-                 filter1,
-                 filter3R,
-                 filter3,
-                 filter5R,
-                 filter5,
-                 proj,
-                 name=None):
-        super(Inception, self).__init__()
-
-        self._conv1 = ConvLayer(
-            input_channels, filter1, 1, name="inception_" + name + "_1x1")
-        self._conv3r = ConvLayer(
-            input_channels,
-            filter3R,
-            1,
-            name="inception_" + name + "_3x3_reduce")
-        self._conv3 = ConvLayer(
-            filter3R, filter3, 3, name="inception_" + name + "_3x3")
-        self._conv5r = ConvLayer(
-            input_channels,
-            filter5R,
-            1,
-            name="inception_" + name + "_5x5_reduce")
-        self._conv5 = ConvLayer(
-            filter5R, filter5, 5, name="inception_" + name + "_5x5")
-        self._pool = MaxPool2D(kernel_size=3, stride=1, padding=1)
-
-        self._convprj = ConvLayer(
-            input_channels, proj, 1, name="inception_" + name + "_3x3_proj")
-
-    def forward(self, inputs):
-        conv1 = self._conv1(inputs)
-
-        conv3r = self._conv3r(inputs)
-        conv3 = self._conv3(conv3r)
-
-        conv5r = self._conv5r(inputs)
-        conv5 = self._conv5(conv5r)
-
-        pool = self._pool(inputs)
-        convprj = self._convprj(pool)
-
-        cat = paddle.concat([conv1, conv3, conv5, convprj], axis=1)
-        cat = F.relu(cat)
-        return cat
-
-
-class GoogLeNetDY(nn.Layer):
-    def __init__(self, class_num=1000):
-        super(GoogLeNetDY, self).__init__()
-        self._conv = ConvLayer(3, 64, 7, 2, name="conv1")
-        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")
-
-        self._ince3a = Inception(
-            192, 192, 64, 96, 128, 16, 32, 32, name="ince3a")
-        self._ince3b = Inception(
-            256, 256, 128, 128, 192, 32, 96, 64, name="ince3b")
-
-        self._ince4a = Inception(
-            480, 480, 192, 96, 208, 16, 48, 64, name="ince4a")
-        self._ince4b = Inception(
-            512, 512, 160, 112, 224, 24, 64, 64, name="ince4b")
-        self._ince4c = Inception(
-            512, 512, 128, 128, 256, 24, 64, 64, name="ince4c")
-        self._ince4d = Inception(
-            512, 512, 112, 144, 288, 32, 64, 64, name="ince4d")
-        self._ince4e = Inception(
-            528, 528, 256, 160, 320, 32, 128, 128, name="ince4e")
-
-        self._ince5a = Inception(
-            832, 832, 256, 160, 320, 32, 128, 128, name="ince5a")
-        self._ince5b = Inception(
-            832, 832, 384, 192, 384, 48, 128, 128, name="ince5b")
-
-        self._pool_5 = AdaptiveAvgPool2D(1)
-
-        self._drop = Dropout(p=0.4, mode="downscale_in_infer")
-        self._fc_out = Linear(
-            1024,
-            class_num,
-            weight_attr=xavier(1024, 1, "out"),
-            bias_attr=ParamAttr(name="out_offset"))
-        self._pool_o1 = AvgPool2D(kernel_size=5, stride=3)
-        self._conv_o1 = ConvLayer(512, 128, 1, name="conv_o1")
-        self._fc_o1 = Linear(
-            1152,
-            1024,
-            weight_attr=xavier(2048, 1, "fc_o1"),
-            bias_attr=ParamAttr(name="fc_o1_offset"))
-        self._drop_o1 = Dropout(p=0.7, mode="downscale_in_infer")
-        self._out1 = Linear(
-            1024,
-            class_num,
-            weight_attr=xavier(1024, 1, "out1"),
-            bias_attr=ParamAttr(name="out1_offset"))
-        self._pool_o2 = AvgPool2D(kernel_size=5, stride=3)
-        self._conv_o2 = ConvLayer(528, 128, 1, name="conv_o2")
-        self._fc_o2 = Linear(
-            1152,
-            1024,
-            weight_attr=xavier(2048, 1, "fc_o2"),
-            bias_attr=ParamAttr(name="fc_o2_offset"))
-        self._drop_o2 = Dropout(p=0.7, mode="downscale_in_infer")
-        self._out2 = Linear(
-            1024,
-            class_num,
-            weight_attr=xavier(1024, 1, "out2"),
-            bias_attr=ParamAttr(name="out2_offset"))
-
-    def forward(self, inputs):
-        x = self._conv(inputs)
-        x = self._pool(x)
-        x = self._conv_1(x)
-        x = self._conv_2(x)
-        x = self._pool(x)
-
-        x = self._ince3a(x)
-        x = self._ince3b(x)
-        x = self._pool(x)
-
-        ince4a = self._ince4a(x)
-        x = self._ince4b(ince4a)
-        x = self._ince4c(x)
-        ince4d = self._ince4d(x)
-        x = self._ince4e(ince4d)
-        x = self._pool(x)
-
-        x = self._ince5a(x)
-        ince5b = self._ince5b(x)
-
-        x = self._pool_5(ince5b)
-        x = self._drop(x)
-        x = paddle.squeeze(x, axis=[2, 3])
-        out = self._fc_out(x)
-
-        x = self._pool_o1(ince4a)
-        x = self._conv_o1(x)
-        x = paddle.flatten(x, start_axis=1, stop_axis=-1)
-        x = self._fc_o1(x)
-        x = F.relu(x)
-        x = self._drop_o1(x)
-        out1 = self._out1(x)
-
-        x = self._pool_o2(ince4d)
-        x = self._conv_o2(x)
-        x = paddle.flatten(x, start_axis=1, stop_axis=-1)
-        x = self._fc_o2(x)
-        x = self._drop_o2(x)
-        out2 = self._out2(x)
-        return [out, out1, out2]
-
-
-def _load_pretrained(pretrained, model, model_url, use_ssld=False):
-    if pretrained is False:
-        pass
-    elif pretrained is True:
-        load_dygraph_pretrain_from_url(model, model_url, use_ssld=use_ssld)
-    elif isinstance(pretrained, str):
-        load_dygraph_pretrain(model, pretrained)
-    else:
-        raise RuntimeError(
-            "pretrained type is not available. Please use `string` or `boolean` type."
-        )
-
-
-def GoogLeNet(pretrained=False, use_ssld=False, **kwargs):
-    model = GoogLeNetDY(**kwargs)
-    _load_pretrained(
-        pretrained, model, MODEL_URLS["GoogLeNet"], use_ssld=use_ssld)
-    return model