ImageProcess/deploy/python/imageClearONNXModel_to_static.py

from paddle.static import InputSpec
import paddle

class ClearupNet(paddle.nn.Layer):
    def __init__(self):
        super(ClearupNet, self).__init__()
        self.conv0 = paddle.nn.Conv2D(in_channels=3, out_channels=16, kernel_size=[3, 3], padding=1)
        self.conv1 = paddle.nn.Conv2D(in_channels=16, out_channels=32, kernel_size=[3, 3], stride=2, padding=1)
        self.conv2 = paddle.nn.Conv2D(in_channels=32, out_channels=64, kernel_size=[3, 3], stride=2, padding=1)
        self.conv3 = paddle.nn.Conv2D(in_channels=64, out_channels=64, kernel_size=[3, 3], padding=1)
        self.conv4 = paddle.nn.Conv2D(in_channels=64, out_channels=64, kernel_size=[3, 3], padding=1)
        self.conv5 = paddle.nn.Conv2D(in_channels=64, out_channels=64, kernel_size=[3, 3], padding=1)
        self.conv6 = paddle.nn.Conv2D(in_channels=64, out_channels=64, kernel_size=[3, 3], padding=1)
        self.conv7 = paddle.nn.Conv2D(in_channels=64, out_channels=64, kernel_size=[3, 3], padding=1)
        self.conv8 = paddle.nn.Conv2D(in_channels=64, out_channels=64, kernel_size=[3, 3], padding=1)
        self.conv9 = paddle.nn.Conv2D(in_channels=64, out_channels=64, kernel_size=[3, 3], padding=1)
        self.conv10 = paddle.nn.Conv2D(in_channels=64, out_channels=64, kernel_size=[3, 3], padding=1)
        self.conv11 = paddle.nn.Conv2D(in_channels=64, out_channels=64, kernel_size=[3, 3], padding=1)
        self.conv12 = paddle.nn.Conv2D(in_channels=64, out_channels=64, kernel_size=[3, 3], padding=1)
        self.conv13 = paddle.nn.Conv2D(in_channels=64, out_channels=64, kernel_size=[3, 3], padding=1)
        self.conv_trans0 = paddle.nn.Conv2DTranspose(in_channels=64, out_channels=32, kernel_size=[3, 3], stride=2, padding=1, output_padding=1, bias_attr=False)
        self.batchnorm0 = paddle.nn.BatchNorm(num_channels=32, momentum=0.8999999761581421, epsilon=9.999999747378752e-06, is_test=True)
        self.conv_trans1 = paddle.nn.Conv2DTranspose(in_channels=32, out_channels=16, kernel_size=[3, 3], stride=2, padding=1, output_padding=1, bias_attr=False)
        self.batchnorm1 = paddle.nn.BatchNorm(num_channels=16, momentum=0.8999999761581421, epsilon=9.999999747378752e-06, is_test=True)
        self.conv14 = paddle.nn.Conv2D(in_channels=16, out_channels=3, kernel_size=[3, 3], padding=1)
        self.sigmoid0 = paddle.nn.Sigmoid()

    def forward(self, x2paddle_input):
        x2paddle_169 = self.conv0(x2paddle_input)
        x2paddle_105 = paddle.clip(x=x2paddle_169, max=6.0, min=0.0)
        x2paddle_172 = self.conv1(x2paddle_105)
        x2paddle_108 = paddle.clip(x=x2paddle_172, max=6.0, min=0.0)
        x2paddle_175 = self.conv2(x2paddle_108)
        x2paddle_111 = paddle.clip(x=x2paddle_175, max=6.0, min=0.0)
        x2paddle_178 = self.conv3(x2paddle_111)
        x2paddle_114 = paddle.clip(x=x2paddle_178, max=6.0, min=0.0)
        x2paddle_181 = self.conv4(x2paddle_114)
        x2paddle_117 = paddle.clip(x=x2paddle_181, max=6.0, min=0.0)
        x2paddle_118 = paddle.add(x=x2paddle_111, y=x2paddle_117)
        x2paddle_119 = paddle.clip(x=x2paddle_118, max=6.0, min=0.0)
        x2paddle_184 = self.conv5(x2paddle_119)
        x2paddle_122 = paddle.clip(x=x2paddle_184, max=6.0, min=0.0)
        x2paddle_187 = self.conv6(x2paddle_122)
        x2paddle_125 = paddle.clip(x=x2paddle_187, max=6.0, min=0.0)
        x2paddle_126 = paddle.add(x=x2paddle_119, y=x2paddle_125)
        x2paddle_127 = paddle.clip(x=x2paddle_126, max=6.0, min=0.0)
        x2paddle_190 = self.conv7(x2paddle_127)
        x2paddle_130 = paddle.clip(x=x2paddle_190, max=6.0, min=0.0)
        x2paddle_193 = self.conv8(x2paddle_130)
        x2paddle_133 = paddle.clip(x=x2paddle_193, max=6.0, min=0.0)
        x2paddle_134 = paddle.add(x=x2paddle_127, y=x2paddle_133)
        x2paddle_135 = paddle.clip(x=x2paddle_134, max=6.0, min=0.0)
        x2paddle_196 = self.conv9(x2paddle_135)
        x2paddle_138 = paddle.clip(x=x2paddle_196, max=6.0, min=0.0)
        x2paddle_199 = self.conv10(x2paddle_138)
        x2paddle_141 = paddle.clip(x=x2paddle_199, max=6.0, min=0.0)
        x2paddle_142 = paddle.add(x=x2paddle_135, y=x2paddle_141)
        x2paddle_143 = paddle.clip(x=x2paddle_142, max=6.0, min=0.0)
        x2paddle_202 = self.conv11(x2paddle_143)
        x2paddle_146 = paddle.clip(x=x2paddle_202, max=6.0, min=0.0)
        x2paddle_205 = self.conv12(x2paddle_146)
        x2paddle_149 = paddle.clip(x=x2paddle_205, max=6.0, min=0.0)
        x2paddle_150 = paddle.add(x=x2paddle_143, y=x2paddle_149)
        x2paddle_151 = paddle.clip(x=x2paddle_150, max=6.0, min=0.0)
        x2paddle_152 = paddle.add(x=x2paddle_111, y=x2paddle_151)
        x2paddle_208 = self.conv13(x2paddle_152)
        x2paddle_155 = paddle.clip(x=x2paddle_208, max=6.0, min=0.0)
        x2paddle_156 = self.conv_trans0(x2paddle_155)
        x2paddle_157 = self.batchnorm0(x2paddle_156)
        x2paddle_158 = paddle.clip(x=x2paddle_157, max=6.0, min=0.0)
        x2paddle_159 = paddle.add(x=x2paddle_108, y=x2paddle_158)
        x2paddle_160 = self.conv_trans1(x2paddle_159)
        x2paddle_161 = self.batchnorm1(x2paddle_160)
        x2paddle_162 = paddle.clip(x=x2paddle_161, max=6.0, min=0.0)
        x2paddle_163 = paddle.add(x=x2paddle_105, y=x2paddle_162)
        x2paddle_211 = self.conv14(x2paddle_163)
        x2paddle_166 = paddle.clip(x=x2paddle_211, max=6.0, min=0.0)
        x2paddle_167 = paddle.add(x=x2paddle_input, y=x2paddle_166)
        x2paddle_output = self.sigmoid0(x2paddle_167)
        return x2paddle_output

paddle.disable_static()
params = paddle.load(r'doc_clean/doc_clean_pd_model/model.pdparams')
model = ClearupNet()
model.set_dict(params, use_structured_name=True)
input_spec = InputSpec([1, 3, 256, 256], 'float32', 'x')
model.eval()
paddle.jit.save(
    layer=model,
    path='doc_clearup_infer_model/inference_model',
    input_spec=[input_spec])
print('doc_clearup inference model saved in ./doc_clearup_infer_model')