How to use the mxnet.symbol.Activation function in mxnet

fix_gamma=False, eps=self.eps)
        scale4b15_branch2b = bn4b15_branch2b
        res4b15_branch2b_relu = mx.symbol.Activation(name='res4b15_branch2b_relu', data=scale4b15_branch2b, act_type='relu')
        res4b15_branch2c = mx.symbol.Convolution(name='res4b15_branch2c', data=res4b15_branch2b_relu, num_filter=1024,
                                                 pad=(0, 0), kernel=(1, 1), stride=(1, 1), no_bias=True)
        bn4b15_branch2c = mx.symbol.BatchNorm(name='bn4b15_branch2c', data=res4b15_branch2c, use_global_stats=True,
                                              fix_gamma=False, eps=self.eps)
        scale4b15_branch2c = bn4b15_branch2c
        res4b15 = mx.symbol.broadcast_add(name='res4b15', *[res4b14_relu, scale4b15_branch2c])
        res4b15_relu = mx.symbol.Activation(name='res4b15_relu', data=res4b15, act_type='relu')
        res4b16_branch2a = mx.symbol.Convolution(name='res4b16_branch2a', data=res4b15_relu, num_filter=256, pad=(0, 0),
                                                 kernel=(1, 1), stride=(1, 1), no_bias=True)
        bn4b16_branch2a = mx.symbol.BatchNorm(name='bn4b16_branch2a', data=res4b16_branch2a, use_global_stats=True,
                                              fix_gamma=False, eps=self.eps)
        scale4b16_branch2a = bn4b16_branch2a
        res4b16_branch2a_relu = mx.symbol.Activation(name='res4b16_branch2a_relu', data=scale4b16_branch2a, act_type='relu')
        res4b16_branch2b = mx.symbol.Convolution(name='res4b16_branch2b', data=res4b16_branch2a_relu, num_filter=256,
                                                 pad=(1, 1), kernel=(3, 3), stride=(1, 1), no_bias=True)
        bn4b16_branch2b = mx.symbol.BatchNorm(name='bn4b16_branch2b', data=res4b16_branch2b, use_global_stats=True,
                                              fix_gamma=False, eps=self.eps)
        scale4b16_branch2b = bn4b16_branch2b
        res4b16_branch2b_relu = mx.symbol.Activation(name='res4b16_branch2b_relu', data=scale4b16_branch2b, act_type='relu')
        res4b16_branch2c = mx.symbol.Convolution(name='res4b16_branch2c', data=res4b16_branch2b_relu, num_filter=1024,
                                                 pad=(0, 0), kernel=(1, 1), stride=(1, 1), no_bias=True)
        bn4b16_branch2c = mx.symbol.BatchNorm(name='bn4b16_branch2c', data=res4b16_branch2c, use_global_stats=True,
                                              fix_gamma=False, eps=self.eps)
        scale4b16_branch2c = bn4b16_branch2c
        res4b16 = mx.symbol.broadcast_add(name='res4b16', *[res4b15_relu, scale4b16_branch2c])
        res4b16_relu = mx.symbol.Activation(name='res4b16_relu', data=res4b16, act_type='relu')
        res4b17_branch2a = mx.symbol.Convolution(name='res4b17_branch2a', data=res4b16_relu, num_filter=256, pad=(0, 0),
                                                 kernel=(1, 1), stride=(1, 1), no_bias=True)
        bn4b17_branch2a = mx.symbol.BatchNorm(name='bn4b17_branch2a', data=res4b17_branch2a, use_global_stats=True,

conv3_1 = mx.symbol.Convolution(
        data=pool2, kernel=(3, 3), pad=(1, 1), num_filter=256, name="conv3_1")
    relu3_1 = mx.symbol.Activation(data=conv3_1, act_type="relu", name="relu3_1")
    conv3_2 = mx.symbol.Convolution(
        data=relu3_1, kernel=(3, 3), pad=(1, 1), num_filter=256, name="conv3_2")
    relu3_2 = mx.symbol.Activation(data=conv3_2, act_type="relu", name="relu3_2")
    conv3_3 = mx.symbol.Convolution(
        data=relu3_2, kernel=(3, 3), pad=(1, 1), num_filter=256, name="conv3_3")
    relu3_3 = mx.symbol.Activation(data=conv3_3, act_type="relu", name="relu3_3")
    pool3 = mx.symbol.Pooling(
        data=relu3_3, pool_type="max", kernel=(2, 2), stride=(2, 2), \
        pooling_convention="full", name="pool3")
    # group 4
    conv4_1 = mx.symbol.Convolution(
        data=pool3, kernel=(3, 3), pad=(1, 1), num_filter=512, name="conv4_1")
    relu4_1 = mx.symbol.Activation(data=conv4_1, act_type="relu", name="relu4_1")
    conv4_2 = mx.symbol.Convolution(
        data=relu4_1, kernel=(3, 3), pad=(1, 1), num_filter=512, name="conv4_2")
    relu4_2 = mx.symbol.Activation(data=conv4_2, act_type="relu", name="relu4_2")
    conv4_3 = mx.symbol.Convolution(
        data=relu4_2, kernel=(3, 3), pad=(1, 1), num_filter=512, name="conv4_3")
    relu4_3 = mx.symbol.Activation(data=conv4_3, act_type="relu", name="relu4_3")
    pool4 = mx.symbol.Pooling(
        data=relu4_3, pool_type="max", kernel=(2, 2), stride=(2, 2), name="pool4")
    # group 5
    conv5_1 = mx.symbol.Convolution(
        data=pool4, kernel=(3, 3), pad=(1, 1), num_filter=512, name="conv5_1")
    relu5_1 = mx.symbol.Activation(data=conv5_1, act_type="relu", name="relu5_1")
    conv5_2 = mx.symbol.Convolution(
        data=relu5_1, kernel=(3, 3), pad=(1, 1), num_filter=512, name="conv5_2")
    relu5_2 = mx.symbol.Activation(data=conv5_2, act_type="relu", name="relu5_2")
    conv5_3 = mx.symbol.Convolution(

fix_gamma=False, eps=self.eps)
        scale4b13_branch2b = bn4b13_branch2b
        res4b13_branch2b_relu = mx.symbol.Activation(name='res4b13_branch2b_relu', data=scale4b13_branch2b, act_type='relu')
        res4b13_branch2c = mx.symbol.Convolution(name='res4b13_branch2c', data=res4b13_branch2b_relu, num_filter=1024,
                                                 pad=(0, 0), kernel=(1, 1), stride=(1, 1), no_bias=True)
        bn4b13_branch2c = mx.symbol.BatchNorm(name='bn4b13_branch2c', data=res4b13_branch2c, use_global_stats=True,
                                              fix_gamma=False, eps=self.eps)
        scale4b13_branch2c = bn4b13_branch2c
        res4b13 = mx.symbol.broadcast_add(name='res4b13', *[res4b12_relu, scale4b13_branch2c])
        res4b13_relu = mx.symbol.Activation(name='res4b13_relu', data=res4b13, act_type='relu')
        res4b14_branch2a = mx.symbol.Convolution(name='res4b14_branch2a', data=res4b13_relu, num_filter=256, pad=(0, 0),
                                                 kernel=(1, 1), stride=(1, 1), no_bias=True)
        bn4b14_branch2a = mx.symbol.BatchNorm(name='bn4b14_branch2a', data=res4b14_branch2a, use_global_stats=True,
                                              fix_gamma=False, eps=self.eps)
        scale4b14_branch2a = bn4b14_branch2a
        res4b14_branch2a_relu = mx.symbol.Activation(name='res4b14_branch2a_relu', data=scale4b14_branch2a, act_type='relu')
        res4b14_branch2b = mx.symbol.Convolution(name='res4b14_branch2b', data=res4b14_branch2a_relu, num_filter=256,
                                                 pad=(1, 1), kernel=(3, 3), stride=(1, 1), no_bias=True)
        bn4b14_branch2b = mx.symbol.BatchNorm(name='bn4b14_branch2b', data=res4b14_branch2b, use_global_stats=True,
                                              fix_gamma=False, eps=self.eps)
        scale4b14_branch2b = bn4b14_branch2b
        res4b14_branch2b_relu = mx.symbol.Activation(name='res4b14_branch2b_relu', data=scale4b14_branch2b, act_type='relu')
        res4b14_branch2c = mx.symbol.Convolution(name='res4b14_branch2c', data=res4b14_branch2b_relu, num_filter=1024,
                                                 pad=(0, 0), kernel=(1, 1), stride=(1, 1), no_bias=True)
        bn4b14_branch2c = mx.symbol.BatchNorm(name='bn4b14_branch2c', data=res4b14_branch2c, use_global_stats=True,
                                              fix_gamma=False, eps=self.eps)
        scale4b14_branch2c = bn4b14_branch2c
        res4b14 = mx.symbol.broadcast_add(name='res4b14', *[res4b13_relu, scale4b14_branch2c])
        res4b14_relu = mx.symbol.Activation(name='res4b14_relu', data=res4b14, act_type='relu')
        res4b15_branch2a = mx.symbol.Convolution(name='res4b15_branch2a', data=res4b14_relu, num_filter=256, pad=(0, 0),
                                                 kernel=(1, 1), stride=(1, 1), no_bias=True)
        bn4b15_branch2a = mx.symbol.BatchNorm(name='bn4b15_branch2a', data=res4b15_branch2a, use_global_stats=True,

Mconv1_stage4_L2 = mx.symbol.Convolution(name='Mconv1_stage4_L2', data=concat_stage4 , num_filter=128, pad=(3,3), kernel=(7,7), stride=(1,1), no_bias=False)
    Mrelu1_stage4_L2 = mx.symbol.Activation(name='Mrelu1_stage4_L2', data=Mconv1_stage4_L2 , act_type='relu')
    Mconv2_stage4_L1 = mx.symbol.Convolution(name='Mconv2_stage4_L1', data=Mrelu1_stage4_L1 , num_filter=128, pad=(3,3), kernel=(7,7), stride=(1,1), no_bias=False)
    Mrelu2_stage4_L1 = mx.symbol.Activation(name='Mrelu2_stage4_L1', data=Mconv2_stage4_L1 , act_type='relu')
    Mconv2_stage4_L2 = mx.symbol.Convolution(name='Mconv2_stage4_L2', data=Mrelu1_stage4_L2 , num_filter=128, pad=(3,3), kernel=(7,7), stride=(1,1), no_bias=False)
    Mrelu2_stage4_L2 = mx.symbol.Activation(name='Mrelu2_stage4_L2', data=Mconv2_stage4_L2 , act_type='relu')
    Mconv3_stage4_L1 = mx.symbol.Convolution(name='Mconv3_stage4_L1', data=Mrelu2_stage4_L1 , num_filter=128, pad=(3,3), kernel=(7,7), stride=(1,1), no_bias=False)
    Mrelu3_stage4_L1 = mx.symbol.Activation(name='Mrelu3_stage4_L1', data=Mconv3_stage4_L1 , act_type='relu')
    Mconv3_stage4_L2 = mx.symbol.Convolution(name='Mconv3_stage4_L2', data=Mrelu2_stage4_L2 , num_filter=128, pad=(3,3), kernel=(7,7), stride=(1,1), no_bias=False)
    Mrelu3_stage4_L2 = mx.symbol.Activation(name='Mrelu3_stage4_L2', data=Mconv3_stage4_L2 , act_type='relu')
    Mconv4_stage4_L1 = mx.symbol.Convolution(name='Mconv4_stage4_L1', data=Mrelu3_stage4_L1 , num_filter=128, pad=(3,3), kernel=(7,7), stride=(1,1), no_bias=False)
    Mrelu4_stage4_L1 = mx.symbol.Activation(name='Mrelu4_stage4_L1', data=Mconv4_stage4_L1 , act_type='relu')
    Mconv4_stage4_L2 = mx.symbol.Convolution(name='Mconv4_stage4_L2', data=Mrelu3_stage4_L2 , num_filter=128, pad=(3,3), kernel=(7,7), stride=(1,1), no_bias=False)
    Mrelu4_stage4_L2 = mx.symbol.Activation(name='Mrelu4_stage4_L2', data=Mconv4_stage4_L2 , act_type='relu')
    Mconv5_stage4_L1 = mx.symbol.Convolution(name='Mconv5_stage4_L1', data=Mrelu4_stage4_L1 , num_filter=128, pad=(3,3), kernel=(7,7), stride=(1,1), no_bias=False)
    Mrelu5_stage4_L1 = mx.symbol.Activation(name='Mrelu5_stage4_L1', data=Mconv5_stage4_L1 , act_type='relu')
    Mconv5_stage4_L2 = mx.symbol.Convolution(name='Mconv5_stage4_L2', data=Mrelu4_stage4_L2 , num_filter=128, pad=(3,3), kernel=(7,7), stride=(1,1), no_bias=False)
    Mrelu5_stage4_L2 = mx.symbol.Activation(name='Mrelu5_stage4_L2', data=Mconv5_stage4_L2 , act_type='relu')
    Mconv6_stage4_L1 = mx.symbol.Convolution(name='Mconv6_stage4_L1', data=Mrelu5_stage4_L1 , num_filter=128, pad=(0,0), kernel=(1,1), stride=(1,1), no_bias=False)
    Mrelu6_stage4_L1 = mx.symbol.Activation(name='Mrelu6_stage4_L1', data=Mconv6_stage4_L1 , act_type='relu')
    Mconv6_stage4_L2 = mx.symbol.Convolution(name='Mconv6_stage4_L2', data=Mrelu5_stage4_L2 , num_filter=128, pad=(0,0), kernel=(1,1), stride=(1,1), no_bias=False)
    Mrelu6_stage4_L2 = mx.symbol.Activation(name='Mrelu6_stage4_L2', data=Mconv6_stage4_L2 , act_type='relu')
    Mconv7_stage4_L1 = mx.symbol.Convolution(name='Mconv7_stage4_L1', data=Mrelu6_stage4_L1 , num_filter=numoflinks*2, pad=(0,0), kernel=(1,1), stride=(1,1), no_bias=False)
    Mconv7_stage4_L2 = mx.symbol.Convolution(name='Mconv7_stage4_L2', data=Mrelu6_stage4_L2 , num_filter=numofparts, pad=(0,0), kernel=(1,1), stride=(1,1), no_bias=False)
    concat_stage5 = mx.symbol.Concat(name='concat_stage5', *[Mconv7_stage4_L1,Mconv7_stage4_L2,relu4_4_CPM] )
    Mconv1_stage5_L1 = mx.symbol.Convolution(name='Mconv1_stage5_L1', data=concat_stage5 , num_filter=128, pad=(3,3), kernel=(7,7), stride=(1,1), no_bias=False)
    Mrelu1_stage5_L1 = mx.symbol.Activation(name='Mrelu1_stage5_L1', data=Mconv1_stage5_L1 , act_type='relu')
    Mconv1_stage5_L2 = mx.symbol.Convolution(name='Mconv1_stage5_L2', data=concat_stage5 , num_filter=128, pad=(3,3), kernel=(7,7), stride=(1,1), no_bias=False)
    Mrelu1_stage5_L2 = mx.symbol.Activation(name='Mrelu1_stage5_L2', data=Mconv1_stage5_L2 , act_type='relu')
    Mconv2_stage5_L1 = mx.symbol.Convolution(name='Mconv2_stage5_L1', data=Mrelu1_stage5_L1 , num_filter=128, pad=(3,3), kernel=(7,7), stride=(1,1), no_bias=False)
    Mrelu2_stage5_L1 = mx.symbol.Activation(name='Mrelu2_stage5_L1', data=Mconv2_stage5_L1 , act_type='relu')
    Mconv2_stage5_L2 = mx.symbol.Convolution(name='Mconv2_stage5_L2', data=Mrelu1_stage5_L2 , num_filter=128, pad=(3,3), kernel=(7,7), stride=(1,1), no_bias=False)

res4b15_branch2a_relu = mx.symbol.Activation(name='res4b15_branch2a_relu', data=scale4b15_branch2a,
                                                     act_type='relu')
        res4b15_branch2b = mx.symbol.Convolution(name='res4b15_branch2b', data=res4b15_branch2a_relu, num_filter=256,
                                                 pad=(1, 1), kernel=(3, 3), stride=(1, 1), no_bias=True)
        bn4b15_branch2b = mx.symbol.BatchNorm(name='bn4b15_branch2b', data=res4b15_branch2b, use_global_stats=True,
                                              fix_gamma=False, eps = self.eps)
        scale4b15_branch2b = bn4b15_branch2b
        res4b15_branch2b_relu = mx.symbol.Activation(name='res4b15_branch2b_relu', data=scale4b15_branch2b,
                                                     act_type='relu')
        res4b15_branch2c = mx.symbol.Convolution(name='res4b15_branch2c', data=res4b15_branch2b_relu, num_filter=1024,
                                                 pad=(0, 0), kernel=(1, 1), stride=(1, 1), no_bias=True)
        bn4b15_branch2c = mx.symbol.BatchNorm(name='bn4b15_branch2c', data=res4b15_branch2c, use_global_stats=True,
                                              fix_gamma=False, eps = self.eps)
        scale4b15_branch2c = bn4b15_branch2c
        res4b15 = mx.symbol.broadcast_add(name='res4b15', *[res4b14_relu, scale4b15_branch2c])
        res4b15_relu = mx.symbol.Activation(name='res4b15_relu', data=res4b15, act_type='relu')
        res4b16_branch2a = mx.symbol.Convolution(name='res4b16_branch2a', data=res4b15_relu, num_filter=256, pad=(0, 0),
                                                 kernel=(1, 1), stride=(1, 1), no_bias=True)
        bn4b16_branch2a = mx.symbol.BatchNorm(name='bn4b16_branch2a', data=res4b16_branch2a, use_global_stats=True,
                                              fix_gamma=False, eps = self.eps)
        scale4b16_branch2a = bn4b16_branch2a
        res4b16_branch2a_relu = mx.symbol.Activation(name='res4b16_branch2a_relu', data=scale4b16_branch2a,
                                                     act_type='relu')
        res4b16_branch2b = mx.symbol.Convolution(name='res4b16_branch2b', data=res4b16_branch2a_relu, num_filter=256,
                                                 pad=(1, 1), kernel=(3, 3), stride=(1, 1), no_bias=True)
        bn4b16_branch2b = mx.symbol.BatchNorm(name='bn4b16_branch2b', data=res4b16_branch2b, use_global_stats=True,
                                              fix_gamma=False, eps = self.eps)
        scale4b16_branch2b = bn4b16_branch2b
        res4b16_branch2b_relu = mx.symbol.Activation(name='res4b16_branch2b_relu', data=scale4b16_branch2b,
                                                     act_type='relu')
        res4b16_branch2c = mx.symbol.Convolution(name='res4b16_branch2c', data=res4b16_branch2b_relu, num_filter=1024,
                                                 pad=(0, 0), kernel=(1, 1), stride=(1, 1), no_bias=True)

res4b16_branch2a_relu = mx.symbol.Activation(name='res4b16_branch2a_relu', data=scale4b16_branch2a,
                                                     act_type='relu')
        res4b16_branch2b = mx.symbol.Convolution(name='res4b16_branch2b', data=res4b16_branch2a_relu, num_filter=256,
                                                 pad=(1, 1), kernel=(3, 3), stride=(1, 1), no_bias=True)
        bn4b16_branch2b = mx.symbol.BatchNorm(name='bn4b16_branch2b', data=res4b16_branch2b, use_global_stats=True,
                                              fix_gamma=False, eps=self.eps)
        scale4b16_branch2b = bn4b16_branch2b
        res4b16_branch2b_relu = mx.symbol.Activation(name='res4b16_branch2b_relu', data=scale4b16_branch2b,
                                                     act_type='relu')
        res4b16_branch2c = mx.symbol.Convolution(name='res4b16_branch2c', data=res4b16_branch2b_relu, num_filter=1024,
                                                 pad=(0, 0), kernel=(1, 1), stride=(1, 1), no_bias=True)
        bn4b16_branch2c = mx.symbol.BatchNorm(name='bn4b16_branch2c', data=res4b16_branch2c, use_global_stats=True,
                                              fix_gamma=False, eps=self.eps)
        scale4b16_branch2c = bn4b16_branch2c
        res4b16 = mx.symbol.broadcast_add(name='res4b16', *[res4b15_relu, scale4b16_branch2c])
        res4b16_relu = mx.symbol.Activation(name='res4b16_relu', data=res4b16, act_type='relu')
        res4b17_branch2a = mx.symbol.Convolution(name='res4b17_branch2a', data=res4b16_relu, num_filter=256, pad=(0, 0),
                                                 kernel=(1, 1), stride=(1, 1), no_bias=True)
        bn4b17_branch2a = mx.symbol.BatchNorm(name='bn4b17_branch2a', data=res4b17_branch2a, use_global_stats=True,
                                              fix_gamma=False, eps=self.eps)
        scale4b17_branch2a = bn4b17_branch2a
        res4b17_branch2a_relu = mx.symbol.Activation(name='res4b17_branch2a_relu', data=scale4b17_branch2a,
                                                     act_type='relu')
        res4b17_branch2b = mx.symbol.Convolution(name='res4b17_branch2b', data=res4b17_branch2a_relu, num_filter=256,
                                                 pad=(1, 1), kernel=(3, 3), stride=(1, 1), no_bias=True)
        bn4b17_branch2b = mx.symbol.BatchNorm(name='bn4b17_branch2b', data=res4b17_branch2b, use_global_stats=True,
                                              fix_gamma=False, eps=self.eps)
        scale4b17_branch2b = bn4b17_branch2b
        res4b17_branch2b_relu = mx.symbol.Activation(name='res4b17_branch2b_relu', data=scale4b17_branch2b,
                                                     act_type='relu')
        res4b17_branch2c = mx.symbol.Convolution(name='res4b17_branch2c', data=res4b17_branch2b_relu, num_filter=1024,
                                                 pad=(0, 0), kernel=(1, 1), stride=(1, 1), no_bias=True)

fix_gamma=False, eps=self.eps)
        scale4b2_branch2b = bn4b2_branch2b
        res4b2_branch2b_relu = mx.symbol.Activation(name='res4b2_branch2b_relu', data=scale4b2_branch2b, act_type='relu')
        res4b2_branch2c = mx.symbol.Convolution(name='res4b2_branch2c', data=res4b2_branch2b_relu, num_filter=1024,
                                                pad=(0, 0), kernel=(1, 1), stride=(1, 1), no_bias=True)
        bn4b2_branch2c = mx.symbol.BatchNorm(name='bn4b2_branch2c', data=res4b2_branch2c, use_global_stats=True,
                                             fix_gamma=False, eps=self.eps)
        scale4b2_branch2c = bn4b2_branch2c
        res4b2 = mx.symbol.broadcast_add(name='res4b2', *[res4b1_relu, scale4b2_branch2c])
        res4b2_relu = mx.symbol.Activation(name='res4b2_relu', data=res4b2, act_type='relu')
        res4b3_branch2a = mx.symbol.Convolution(name='res4b3_branch2a', data=res4b2_relu, num_filter=256, pad=(0, 0),
                                                kernel=(1, 1), stride=(1, 1), no_bias=True)
        bn4b3_branch2a = mx.symbol.BatchNorm(name='bn4b3_branch2a', data=res4b3_branch2a, use_global_stats=True,
                                             fix_gamma=False, eps=self.eps)
        scale4b3_branch2a = bn4b3_branch2a
        res4b3_branch2a_relu = mx.symbol.Activation(name='res4b3_branch2a_relu', data=scale4b3_branch2a, act_type='relu')
        res4b3_branch2b = mx.symbol.Convolution(name='res4b3_branch2b', data=res4b3_branch2a_relu, num_filter=256,
                                                pad=(1, 1), kernel=(3, 3), stride=(1, 1), no_bias=True)
        bn4b3_branch2b = mx.symbol.BatchNorm(name='bn4b3_branch2b', data=res4b3_branch2b, use_global_stats=True,
                                             fix_gamma=False, eps=self.eps)
        scale4b3_branch2b = bn4b3_branch2b
        res4b3_branch2b_relu = mx.symbol.Activation(name='res4b3_branch2b_relu', data=scale4b3_branch2b, act_type='relu')
        res4b3_branch2c = mx.symbol.Convolution(name='res4b3_branch2c', data=res4b3_branch2b_relu, num_filter=1024,
                                                pad=(0, 0), kernel=(1, 1), stride=(1, 1), no_bias=True)
        bn4b3_branch2c = mx.symbol.BatchNorm(name='bn4b3_branch2c', data=res4b3_branch2c, use_global_stats=True,
                                             fix_gamma=False, eps=self.eps)
        scale4b3_branch2c = bn4b3_branch2c
        res4b3 = mx.symbol.broadcast_add(name='res4b3', *[res4b2_relu, scale4b3_branch2c])
        res4b3_relu = mx.symbol.Activation(name='res4b3_relu', data=res4b3, act_type='relu')
        res4b4_branch2a = mx.symbol.Convolution(name='res4b4_branch2a', data=res4b3_relu, num_filter=256, pad=(0, 0),
                                                kernel=(1, 1), stride=(1, 1), no_bias=True)
        bn4b4_branch2a = mx.symbol.BatchNorm(name='bn4b4_branch2a', data=res4b4_branch2a, use_global_stats=True,

def get_resnet_v1_conv4(self, data):
        conv1 = mx.symbol.Convolution(name='conv1', data=data, num_filter=64, pad=(3, 3), kernel=(7, 7), stride=(2, 2),
                                      no_bias=True)
        bn_conv1 = mx.symbol.BatchNorm(name='bn_conv1', data=conv1, use_global_stats=True, fix_gamma=False, eps=self.eps)
        scale_conv1 = bn_conv1
        conv1_relu = mx.symbol.Activation(name='conv1_relu', data=scale_conv1, act_type='relu')
        pool1 = mx.symbol.Pooling(name='pool1', data=conv1_relu, pooling_convention='full', pad=(0, 0), kernel=(3, 3),
                                  stride=(2, 2), pool_type='max')
        res2a_branch1 = mx.symbol.Convolution(name='res2a_branch1', data=pool1, num_filter=256, pad=(0, 0), kernel=(1, 1),
                                              stride=(1, 1), no_bias=True)
        bn2a_branch1 = mx.symbol.BatchNorm(name='bn2a_branch1', data=res2a_branch1, use_global_stats=True, fix_gamma=False, eps=self.eps)
        scale2a_branch1 = bn2a_branch1
        res2a_branch2a = mx.symbol.Convolution(name='res2a_branch2a', data=pool1, num_filter=64, pad=(0, 0), kernel=(1, 1),
                                               stride=(1, 1), no_bias=True)
        bn2a_branch2a = mx.symbol.BatchNorm(name='bn2a_branch2a', data=res2a_branch2a, use_global_stats=True,
                                            fix_gamma=False, eps=self.eps)
        scale2a_branch2a = bn2a_branch2a
        res2a_branch2a_relu = mx.symbol.Activation(name='res2a_branch2a_relu', data=scale2a_branch2a, act_type='relu')
        res2a_branch2b = mx.symbol.Convolution(name='res2a_branch2b', data=res2a_branch2a_relu, num_filter=64, pad=(1, 1),
                                               kernel=(3, 3), stride=(1, 1), no_bias=True)
        bn2a_branch2b = mx.symbol.BatchNorm(name='bn2a_branch2b', data=res2a_branch2b, use_global_stats=True,
                                            fix_gamma=False, eps=self.eps)

res3b2_branch2a_relu = mx.symbol.Activation(name='res3b2_branch2a_relu', data=scale3b2_branch2a,
                                                    act_type='relu')
        res3b2_branch2b = mx.symbol.Convolution(name='res3b2_branch2b', data=res3b2_branch2a_relu, num_filter=128,
                                                pad=(1, 1), kernel=(3, 3), stride=(1, 1), no_bias=True)
        bn3b2_branch2b = mx.symbol.BatchNorm(name='bn3b2_branch2b', data=res3b2_branch2b, use_global_stats=True,
                                             fix_gamma=False, eps=eps)
        scale3b2_branch2b = bn3b2_branch2b
        res3b2_branch2b_relu = mx.symbol.Activation(name='res3b2_branch2b_relu', data=scale3b2_branch2b,
                                                    act_type='relu')
        res3b2_branch2c = mx.symbol.Convolution(name='res3b2_branch2c', data=res3b2_branch2b_relu, num_filter=512,
                                                pad=(0, 0), kernel=(1, 1), stride=(1, 1), no_bias=True)
        bn3b2_branch2c = mx.symbol.BatchNorm(name='bn3b2_branch2c', data=res3b2_branch2c, use_global_stats=True,
                                             fix_gamma=False, eps=eps)
        scale3b2_branch2c = bn3b2_branch2c
        res3b2 = mx.symbol.broadcast_add(name='res3b2', *[res3b1_relu, scale3b2_branch2c])
        res3b2_relu = mx.symbol.Activation(name='res3b2_relu', data=res3b2, act_type='relu')
        res3b3_branch2a = mx.symbol.Convolution(name='res3b3_branch2a', data=res3b2_relu, num_filter=128, pad=(0, 0),
                                                kernel=(1, 1), stride=(1, 1), no_bias=True)
        bn3b3_branch2a = mx.symbol.BatchNorm(name='bn3b3_branch2a', data=res3b3_branch2a, use_global_stats=True,
                                             fix_gamma=False, eps=eps)
        scale3b3_branch2a = bn3b3_branch2a
        res3b3_branch2a_relu = mx.symbol.Activation(name='res3b3_branch2a_relu', data=scale3b3_branch2a,
                                                    act_type='relu')
        if with_dpyramid:
            res3b3_branch2b_offset = mx.symbol.Convolution(name='res3b3_branch2b_offset', data=res3b3_branch2a_relu,
                                                           num_filter=72, pad=(1, 1), kernel=(3, 3), stride=(1, 1))
            res3b3_branch2b = mx.contrib.symbol.DeformableConvolution(name='res3b3_branch2b', data=res3b3_branch2a_relu,
                                                                      offset=res3b3_branch2b_offset,
                                                                      num_filter=128, pad=(1, 1), kernel=(3, 3),
                                                                      num_deformable_group=4,
                                                                      stride=(1, 1), no_bias=True)
        else:

fix_gamma=False, eps=self.eps)
        scale4b6_branch2a = bn4b6_branch2a
        res4b6_branch2a_relu = mx.symbol.Activation(name='res4b6_branch2a_relu', data=scale4b6_branch2a, act_type='relu')
        res4b6_branch2b = mx.symbol.Convolution(name='res4b6_branch2b', data=res4b6_branch2a_relu, num_filter=256,
                                                pad=(1, 1), kernel=(3, 3), stride=(1, 1), no_bias=True)
        bn4b6_branch2b = mx.symbol.BatchNorm(name='bn4b6_branch2b', data=res4b6_branch2b, use_global_stats=True,
                                             fix_gamma=False, eps=self.eps)
        scale4b6_branch2b = bn4b6_branch2b
        res4b6_branch2b_relu = mx.symbol.Activation(name='res4b6_branch2b_relu', data=scale4b6_branch2b, act_type='relu')
        res4b6_branch2c = mx.symbol.Convolution(name='res4b6_branch2c', data=res4b6_branch2b_relu, num_filter=1024,
                                                pad=(0, 0), kernel=(1, 1), stride=(1, 1), no_bias=True)
        bn4b6_branch2c = mx.symbol.BatchNorm(name='bn4b6_branch2c', data=res4b6_branch2c, use_global_stats=True,
                                             fix_gamma=False, eps=self.eps)
        scale4b6_branch2c = bn4b6_branch2c
        res4b6 = mx.symbol.broadcast_add(name='res4b6', *[res4b5_relu, scale4b6_branch2c])
        res4b6_relu = mx.symbol.Activation(name='res4b6_relu', data=res4b6, act_type='relu')
        res4b7_branch2a = mx.symbol.Convolution(name='res4b7_branch2a', data=res4b6_relu, num_filter=256, pad=(0, 0),
                                                kernel=(1, 1), stride=(1, 1), no_bias=True)
        bn4b7_branch2a = mx.symbol.BatchNorm(name='bn4b7_branch2a', data=res4b7_branch2a, use_global_stats=True,
                                             fix_gamma=False, eps=self.eps)
        scale4b7_branch2a = bn4b7_branch2a
        res4b7_branch2a_relu = mx.symbol.Activation(name='res4b7_branch2a_relu', data=scale4b7_branch2a, act_type='relu')
        res4b7_branch2b = mx.symbol.Convolution(name='res4b7_branch2b', data=res4b7_branch2a_relu, num_filter=256,
                                                pad=(1, 1), kernel=(3, 3), stride=(1, 1), no_bias=True)
        bn4b7_branch2b = mx.symbol.BatchNorm(name='bn4b7_branch2b', data=res4b7_branch2b, use_global_stats=True,
                                             fix_gamma=False, eps=self.eps)
        scale4b7_branch2b = bn4b7_branch2b
        res4b7_branch2b_relu = mx.symbol.Activation(name='res4b7_branch2b_relu', data=scale4b7_branch2b, act_type='relu')
        res4b7_branch2c = mx.symbol.Convolution(name='res4b7_branch2c', data=res4b7_branch2b_relu, num_filter=1024,
                                                pad=(0, 0), kernel=(1, 1), stride=(1, 1), no_bias=True)
        bn4b7_branch2c = mx.symbol.BatchNorm(name='bn4b7_branch2c', data=res4b7_branch2c, use_global_stats=True,
                                             fix_gamma=False, eps=self.eps)