1h-8学习（2）：1h-8适配之int8直接量化+转.cambricon格式

最新推荐文章于 2023-04-03 11:20:27 发布
最新推荐文章于 2023-04-03 11:20:27 发布
阅读量470 收藏
点赞数
分类专栏： 1-h8
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/weixin_42068754/article/details/106494534
版权

我尝试量化的模型是我自己训练的VGG_gtsdb_voc_SSD_300x300_iter_60000.caffemodel

目录结构

在这里插入图片描述
在这里插入图片描述

int8直接量化

修改depoly.prototxt

depoly.prototxt就是训练模型时生成的，只需要修改detection_out层的save_output_param。我这些操作都是在虚拟机上进行的，而不是工作站上，gtsdb相关文件全放在/home/jqy/jqy_nfs_server/HCAI1H_HOST_SDK/expr/e02_detection_ssd/model/gtsdb目录下面。

name: "VGG_gtsdb_voc_SSD_300x300_deploy"
input: "data"
input_shape {
  dim: 1
  dim: 3
  dim: 300
  dim: 300
}
layer {
  name: "conv1_1"
  type: "Convolution"
  bottom: "data"
  top: "conv1_1"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 64
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "relu1_1"
  type: "ReLU"
  bottom: "conv1_1"
  top: "conv1_1"
}
layer {
  name: "conv1_2"
  type: "Convolution"
  bottom: "conv1_1"
  top: "conv1_2"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 64
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "relu1_2"
  type: "ReLU"
  bottom: "conv1_2"
  top: "conv1_2"
}
layer {
  name: "pool1"
  type: "Pooling"
  bottom: "conv1_2"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "conv2_1"
  type: "Convolution"
  bottom: "pool1"
  top: "conv2_1"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 128
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "relu2_1"
  type: "ReLU"
  bottom: "conv2_1"
  top: "conv2_1"
}
layer {
  name: "conv2_2"
  type: "Convolution"
  bottom: "conv2_1"
  top: "conv2_2"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 128
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "relu2_2"
  type: "ReLU"
  bottom: "conv2_2"
  top: "conv2_2"
}
layer {
  name: "pool2"
  type: "Pooling"
  bottom: "conv2_2"
  top: "pool2"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "conv3_1"
  type: "Convolution"
  bottom: "pool2"
  top: "conv3_1"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 256
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "relu3_1"
  type: "ReLU"
  bottom: "conv3_1"
  top: "conv3_1"
}
layer {
  name: "conv3_2"
  type: "Convolution"
  bottom: "conv3_1"
  top: "conv3_2"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 256
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "relu3_2"
  type: "ReLU"
  bottom: "conv3_2"
  top: "conv3_2"
}
layer {
  name: "conv3_3"
  type: "Convolution"
  bottom: "conv3_2"
  top: "conv3_3"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 256
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "relu3_3"
  type: "ReLU"
  bottom: "conv3_3"
  top: "conv3_3"
}
layer {
  name: "pool3"
  type: "Pooling"
  bottom: "conv3_3"
  top: "pool3"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "conv4_1"
  type: "Convolution"
  bottom: "pool3"
  top: "conv4_1"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "relu4_1"
  type: "ReLU"
  bottom: "conv4_1"
  top: "conv4_1"
}
layer {
  name: "conv4_2"
  type: "Convolution"
  bottom: "conv4_1"
  top: "conv4_2"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "relu4_2"
  type: "ReLU"
  bottom: "conv4_2"
  top: "conv4_2"
}
layer {
  name: "conv4_3"
  type: "Convolution"
  bottom: "conv4_2"
  top: "conv4_3"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "relu4_3"
  type: "ReLU"
  bottom: "conv4_3"
  top: "conv4_3"
}
layer {
  name: "pool4"
  type: "Pooling"
  bottom: "conv4_3"
  top: "pool4"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "conv5_1"
  type: "Convolution"
  bottom: "pool4"
  top: "conv5_1"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
    dilation: 1
  }
}
layer {
  name: "relu5_1"
  type: "ReLU"
  bottom: "conv5_1"
  top: "conv5_1"
}
layer {
  name: "conv5_2"
  type: "Convolution"
  bottom: "conv5_1"
  top: "conv5_2"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
    dilation: 1
  }
}
layer {
  name: "relu5_2"
  type: "ReLU"
  bottom: "conv5_2"
  top: "conv5_2"
}
layer {
  name: "conv5_3"
  type: "Convolution"
  bottom: "conv5_2"
  top: "conv5_3"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
    dilation: 1
  }
}
layer {
  name: "relu5_3"
  type: "ReLU"
  bottom: "conv5_3"
  top: "conv5_3"
}
layer {
  name: "pool5"
  type: "Pooling"
  bottom: "conv5_3"
  top: "pool5"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 1
    pad: 1
  }
}
layer {
  name: "fc6"
  type: "Convolution"
  bottom: "pool5"
  top: "fc6"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 1024
    pad: 6
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
    dilation: 6
  }
}
layer {
  name: "relu6"
  type: "ReLU"
  bottom: "fc6"
  top: "fc6"
}
layer {
  name: "fc7"
  type: "Convolution"
  bottom: "fc6"
  top: "fc7"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 1024
    kernel_size: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "relu7"
  type: "ReLU"
  bottom: "fc7"
  top: "fc7"
}
layer {
  name: "conv6_1"
  type: "Convolution"
  bottom: "fc7"
  top: "conv6_1"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 256
    pad: 0
    kernel_size: 1
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv6_1_relu"
  type: "ReLU"
  bottom: "conv6_1"
  top: "conv6_1"
}
layer {
  name: "conv6_2"
  type: "Convolution"
  bottom: "conv6_1"
  top: "conv6_2"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
    stride: 2
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv6_2_relu"
  type: "ReLU"
  bottom: "conv6_2"
  top: "conv6_2"
}
layer {
  name: "conv7_1"
  type: "Convolution"
  bottom: "conv6_2"
  top: "conv7_1"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 128
    pad: 0
    kernel_size: 1
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv7_1_relu"
  type: "ReLU"
  bottom: "conv7_1"
  top: "conv7_1"
}
layer {
  name: "conv7_2"
  type: "Convolution"
  bottom: "conv7_1"
  top: "conv7_2"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 256
    pad: 1
    kernel_size: 3
    stride: 2
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv7_2_relu"
  type: "ReLU"
  bottom: "conv7_2"
  top: "conv7_2"
}
layer {
  name: "conv8_1"
  type: "Convolution"
  bottom: "conv7_2"
  top: "conv8_1"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 128
    pad: 0
    kernel_size: 1
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv8_1_relu"
  type: "ReLU"
  bottom: "conv8_1"
  top: "conv8_1"
}
layer {
  name: "conv8_2"
  type: "Convolution"
  bottom: "conv8_1"
  top: "conv8_2"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 256
    pad: 0
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv8_2_relu"
  type: "ReLU"
  bottom: "conv8_2"
  top: "conv8_2"
}
layer {
  name: "conv9_1"
  type: "Convolution"
  bottom: "conv8_2"
  top: "conv9_1"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 128
    pad: 0
    kernel_size: 1
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv9_1_relu"
  type: "ReLU"
  bottom: "conv9_1"
  top: "conv9_1"
}
layer {
  name: "conv9_2"
  type: "Convolution"
  bottom: "conv9_1"
  top: "conv9_2"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 256
    pad: 0
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv9_2_relu"
  type: "ReLU"
  bottom: "conv9_2"
  top: "conv9_2"
}
layer {
  name: "conv4_3_norm"
  type: "Normalize"
  bottom: "conv4_3"
  top: "conv4_3_norm"
  norm_param {
    across_spatial: false
    scale_filler {
      type: "constant"
      value: 20.0
    }
    channel_shared: false
  }
}
layer {
  name: "conv4_3_norm_mbox_loc"
  type: "Convolution"
  bottom: "conv4_3_norm"
  top: "conv4_3_norm_mbox_loc"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 16
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv4_3_norm_mbox_loc_perm"
  type: "Permute"
  bottom: "conv4_3_norm_mbox_loc"
  top: "conv4_3_norm_mbox_loc_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "conv4_3_norm_mbox_loc_flat"
  type: "Flatten"
  bottom: "conv4_3_norm_mbox_loc_perm"
  top: "conv4_3_norm_mbox_loc_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "conv4_3_norm_mbox_conf1"
  type: "Convolution"
  bottom: "conv4_3_norm"
  top: "conv4_3_norm_mbox_conf1"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 20
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv4_3_norm_mbox_conf1_perm"
  type: "Permute"
  bottom: "conv4_3_norm_mbox_conf1"
  top: "conv4_3_norm_mbox_conf1_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "conv4_3_norm_mbox_conf1_flat"
  type: "Flatten"
  bottom: "conv4_3_norm_mbox_conf1_perm"
  top: "conv4_3_norm_mbox_conf1_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "conv4_3_norm_mbox_priorbox"
  type: "PriorBox"
  bottom: "conv4_3_norm"
  bottom: "data"
  top: "conv4_3_norm_mbox_priorbox"
  prior_box_param {
    min_size: 30.0
    max_size: 60.0
    aspect_ratio: 2.0
    flip: true
    clip: false
    variance: 0.10000000149
    variance: 0.10000000149
    variance: 0.20000000298
    variance: 0.20000000298
    step: 8.0
    offset: 0.5
  }
}
layer {
  name: "fc7_mbox_loc"
  type: "Convolution"
  bottom: "fc7"
  top: "fc7_mbox_loc"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 24
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "fc7_mbox_loc_perm"
  type: "Permute"
  bottom: "fc7_mbox_loc"
  top: "fc7_mbox_loc_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "fc7_mbox_loc_flat"
  type: "Flatten"
  bottom: "fc7_mbox_loc_perm"
  top: "fc7_mbox_loc_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "fc7_mbox_conf1"
  type: "Convolution"
  bottom: "fc7"
  top: "fc7_mbox_conf1"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 30
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "fc7_mbox_conf1_perm"
  type: "Permute"
  bottom: "fc7_mbox_conf1"
  top: "fc7_mbox_conf1_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "fc7_mbox_conf1_flat"
  type: "Flatten"
  bottom: "fc7_mbox_conf1_perm"
  top: "fc7_mbox_conf1_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "fc7_mbox_priorbox"
  type: "PriorBox"
  bottom: "fc7"
  bottom: "data"
  top: "fc7_mbox_priorbox"
  prior_box_param {
    min_size: 60.0
    max_size: 111.0
    aspect_ratio: 2.0
    aspect_ratio: 3.0
    flip: true
    clip: false
    variance: 0.10000000149
    variance: 0.10000000149
    variance: 0.20000000298
    variance: 0.20000000298
    step: 16.0
    offset: 0.5
  }
}
layer {
  name: "conv6_2_mbox_loc"
  type: "Convolution"
  bottom: "conv6_2"
  top: "conv6_2_mbox_loc"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 24
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv6_2_mbox_loc_perm"
  type: "Permute"
  bottom: "conv6_2_mbox_loc"
  top: "conv6_2_mbox_loc_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "conv6_2_mbox_loc_flat"
  type: "Flatten"
  bottom: "conv6_2_mbox_loc_perm"
  top: "conv6_2_mbox_loc_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "conv6_2_mbox_conf1"
  type: "Convolution"
  bottom: "conv6_2"
  top: "conv6_2_mbox_conf1"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 30
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv6_2_mbox_conf1_perm"
  type: "Permute"
  bottom: "conv6_2_mbox_conf1"
  top: "conv6_2_mbox_conf1_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "conv6_2_mbox_conf1_flat"
  type: "Flatten"
  bottom: "conv6_2_mbox_conf1_perm"
  top: "conv6_2_mbox_conf1_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "conv6_2_mbox_priorbox"
  type: "PriorBox"
  bottom: "conv6_2"
  bottom: "data"
  top: "conv6_2_mbox_priorbox"
  prior_box_param {
    min_size: 111.0
    max_size: 162.0
    aspect_ratio: 2.0
    aspect_ratio: 3.0
    flip: true
    clip: false
    variance: 0.10000000149
    variance: 0.10000000149
    variance: 0.20000000298
    variance: 0.20000000298
    step: 32.0
    offset: 0.5
  }
}
layer {
  name: "conv7_2_mbox_loc"
  type: "Convolution"
  bottom: "conv7_2"
  top: "conv7_2_mbox_loc"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 24
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv7_2_mbox_loc_perm"
  type: "Permute"
  bottom: "conv7_2_mbox_loc"
  top: "conv7_2_mbox_loc_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "conv7_2_mbox_loc_flat"
  type: "Flatten"
  bottom: "conv7_2_mbox_loc_perm"
  top: "conv7_2_mbox_loc_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "conv7_2_mbox_conf1"
  type: "Convolution"
  bottom: "conv7_2"
  top: "conv7_2_mbox_conf1"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 30
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv7_2_mbox_conf1_perm"
  type: "Permute"
  bottom: "conv7_2_mbox_conf1"
  top: "conv7_2_mbox_conf1_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "conv7_2_mbox_conf1_flat"
  type: "Flatten"
  bottom: "conv7_2_mbox_conf1_perm"
  top: "conv7_2_mbox_conf1_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "conv7_2_mbox_priorbox"
  type: "PriorBox"
  bottom: "conv7_2"
  bottom: "data"
  top: "conv7_2_mbox_priorbox"
  prior_box_param {
    min_size: 162.0
    max_size: 213.0
    aspect_ratio: 2.0
    aspect_ratio: 3.0
    flip: true
    clip: false
    variance: 0.10000000149
    variance: 0.10000000149
    variance: 0.20000000298
    variance: 0.20000000298
    step: 64.0
    offset: 0.5
  }
}
layer {
  name: "conv8_2_mbox_loc"
  type: "Convolution"
  bottom: "conv8_2"
  top: "conv8_2_mbox_loc"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 16
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv8_2_mbox_loc_perm"
  type: "Permute"
  bottom: "conv8_2_mbox_loc"
  top: "conv8_2_mbox_loc_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "conv8_2_mbox_loc_flat"
  type: "Flatten"
  bottom: "conv8_2_mbox_loc_perm"
  top: "conv8_2_mbox_loc_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "conv8_2_mbox_conf1"
  type: "Convolution"
  bottom: "conv8_2"
  top: "conv8_2_mbox_conf1"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 20
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv8_2_mbox_conf1_perm"
  type: "Permute"
  bottom: "conv8_2_mbox_conf1"
  top: "conv8_2_mbox_conf1_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "conv8_2_mbox_conf1_flat"
  type: "Flatten"
  bottom: "conv8_2_mbox_conf1_perm"
  top: "conv8_2_mbox_conf1_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "conv8_2_mbox_priorbox"
  type: "PriorBox"
  bottom: "conv8_2"
  bottom: "data"
  top: "conv8_2_mbox_priorbox"
  prior_box_param {
    min_size: 213.0
    max_size: 264.0
    aspect_ratio: 2.0
    flip: true
    clip: false
    variance: 0.10000000149
    variance: 0.10000000149
    variance: 0.20000000298
    variance: 0.20000000298
    step: 100.0
    offset: 0.5
  }
}
layer {
  name: "conv9_2_mbox_loc"
  type: "Convolution"
  bottom: "conv9_2"
  top: "conv9_2_mbox_loc"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 16
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv9_2_mbox_loc_perm"
  type: "Permute"
  bottom: "conv9_2_mbox_loc"
  top: "conv9_2_mbox_loc_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "conv9_2_mbox_loc_flat"
  type: "Flatten"
  bottom: "conv9_2_mbox_loc_perm"
  top: "conv9_2_mbox_loc_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "conv9_2_mbox_conf1"
  type: "Convolution"
  bottom: "conv9_2"
  top: "conv9_2_mbox_conf1"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 20
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv9_2_mbox_conf1_perm"
  type: "Permute"
  bottom: "conv9_2_mbox_conf1"
  top: "conv9_2_mbox_conf1_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "conv9_2_mbox_conf1_flat"
  type: "Flatten"
  bottom: "conv9_2_mbox_conf1_perm"
  top: "conv9_2_mbox_conf1_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "conv9_2_mbox_priorbox"
  type: "PriorBox"
  bottom: "conv9_2"
  bottom: "data"
  top: "conv9_2_mbox_priorbox"
  prior_box_param {
    min_size: 264.0
    max_size: 315.0
    aspect_ratio: 2.0
    flip: true
    clip: false
    variance: 0.10000000149
    variance: 0.10000000149
    variance: 0.20000000298
    variance: 0.20000000298
    step: 300.0
    offset: 0.5
  }
}
layer {
  name: "mbox_loc"
  type: "Concat"
  bottom: "conv4_3_norm_mbox_loc_flat"
  bottom: "fc7_mbox_loc_flat"
  bottom: "conv6_2_mbox_loc_flat"
  bottom: "conv7_2_mbox_loc_flat"
  bottom: "conv8_2_mbox_loc_flat"
  bottom: "conv9_2_mbox_loc_flat"
  top: "mbox_loc"
  concat_param {
    axis: 1
  }
}
layer {
  name: "mbox_conf1"
  type: "Concat"
  bottom: "conv4_3_norm_mbox_conf1_flat"
  bottom: "fc7_mbox_conf1_flat"
  bottom: "conv6_2_mbox_conf1_flat"
  bottom: "conv7_2_mbox_conf1_flat"
  bottom: "conv8_2_mbox_conf1_flat"
  bottom: "conv9_2_mbox_conf1_flat"
  top: "mbox_conf1"
  concat_param {
    axis: 1
  }
}
layer {
  name: "mbox_priorbox"
  type: "Concat"
  bottom: "conv4_3_norm_mbox_priorbox"
  bottom: "fc7_mbox_priorbox"
  bottom: "conv6_2_mbox_priorbox"
  bottom: "conv7_2_mbox_priorbox"
  bottom: "conv8_2_mbox_priorbox"
  bottom: "conv9_2_mbox_priorbox"
  top: "mbox_priorbox"
  concat_param {
    axis: 2
  }
}
layer {
  name: "mbox_conf1_reshape"
  type: "Reshape"
  bottom: "mbox_conf1"
  top: "mbox_conf1_reshape"
  reshape_param {
    shape {
      dim: 0
      dim: -1
      dim: 5
    }
  }
}
layer {
  name: "mbox_conf1_softmax"
  type: "Softmax"
  bottom: "mbox_conf1_reshape"
  top: "mbox_conf1_softmax"
  softmax_param {
    axis: 2
  }
}
layer {
  name: "mbox_conf1_flatten"
  type: "Flatten"
  bottom: "mbox_conf1_softmax"
  top: "mbox_conf1_flatten"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "detection_out"
  type: "DetectionOutput"
  bottom: "mbox_loc"
  bottom: "mbox_conf1_flatten"
  bottom: "mbox_priorbox"
  top: "detection_out"
  include {
    phase: TEST
  }
  detection_output_param {
    num_classes: 5
    share_location: true
    background_label_id: 0
    nms_param {
      nms_threshold: 0.449999988079
      top_k: 400
    }
    save_output_param {
      output_directory: "/home/jqy/jqy_nfs_server/HCAI1H_HOST_SDK/expr/gtsdb_ssd/model"
      output_name_prefix: "comp4_det_test_"
      output_format: "VOC"
      label_map_file: "/home/jqy/jqy_nfs_server/HCAI1H_HOST_SDK/expr/gtsdb_ssd/model/labelmap_voc.prototxt"
      name_size_file: "/home/jqy/jqy_nfs_server/HCAI1H_HOST_SDK/expr/gtsdb_ssd/model/test_name_size.txt"
      num_test_image: 225
    }
    code_type: CENTER_SIZE
    keep_top_k: 200
    confidence_threshold: 0.00999999977648
  }
}

修改float32_convert_fix8.ini

[model]
original_models_path = model/deploy.prototxtt # 待量化的原始网络结构文件
save_model_path = model/ssd_float32_gtsdb.fix8.prototxt # 量化后网络结构文件

[data]
# 注意以下图片路径只能用其中一个
images_folder_path = ./file_list # 图片路径，里面写了验证集图片的路径
# images_db_path = /lmdb_path # lmdb数据路径
used_images_num = 32 # 迭代的次数。当网络batchsize为1，该值为8时，共迭代8次，读取8张图片；当网络的batchsize为4，该值为8时，共迭代8次，读取32张图片

[weights]
original_weights_path = model/VGG_gtsdb_voc_SSD_300x300_iter_60000.caffemodel # 待量化的.caffemodel权重文件

[preprocess]
mean = 104,117,123 # 均值
std = 1.0 # 缩小倍数，这个std参数会在生成的fix8网络的第一层卷积处，默认是1。
scale = 300, 300 # 图片路径images_folder_path时图片高和宽，即输入层是ImageData层。
crop = 300, 300 # 图片路径images_db_path时图片高和宽，即输入层是Data层。

[config]
int8_op_list = Conv, FC, LRN # 8bit算子列表
use_firstconv = 1 # 是否使用到第一层卷积

具体操作

操作前

操作前需要的文件：deploy.prototxt，float32_convert_fix8.ini，labelmap_voc.prototxt，test_name_size.txt，VGG_gtsdb_voc_SSD_300x300_iter_60000.caffemodel

操作方案一

cd /home/jqy/jqy_nfs_server/HCAI1H_HOST_SDK/expr/gtsdb_ssd # 进入要量化的项目的根目录
export LD_LIBRARY_PATH=/home/jqy/jqy_nfs_server/HCAI1H_HOST_SDK/lib/x86 # 导入需要用到的库
/home/jqy/jqy_nfs_server/HCAI1H_HOST_SDK/tools/generate_fix8_pt -ini_file model/float32_convert_fix8.ini 2>&1 | tee model/float2int.log # 运行量化工具

操作方案二

我把操作一的命令写进了quantify.sh中

#!/bin/sh

PATH_ROOT=../..
PATH_TOOL=${PATH_ROOT}/tools
PATH_LIB=${PATH_ROOT}/lib
PATH_MODEL=${PATH_ROOT}/expr/gtsdb_ssd/model

export LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:${PATH_LIB}/x86

${PATH_TOOL}/generate_fix8_pt -ini_file ${PATH_MODEL}/float32_convert_fix8.ini 2>&1 | tee ${PATH_MODEL}/float2int.log

cd /home/jqy/jqy_nfs_server/HCAI1H_HOST_SDK/expr/gtsdb_ssd # 进入要量化的项目的根目录
./quantify.sh

操作后

model目录下生成ssd_float32_gtsdb.fix8.prototxt，float2int.log，comp4_det_test_1~4.txt。

转寒武纪.cambricon 模型

操作前

转换前需要的文件：ssd_float32_gtsdb.fix8.prototxt，VGG_gtsdb_voc_SSD_300x300_iter_60000.caffemodel。

操作方案一

cd /home/jqy/jqy_nfs_server/HCAI1H_HOST_SDK/expr/gtsdb_ssd/model
/home/jqy/jqy_nfs_server/HCAI1H_HOST_SDK/tools/caffe genoff -model ./ssd_float32_gtsdb.fix8.prototxt -weights ./VGG_gtsdb_voc_SSD_300x300_iter_60000.caffemodel -mname gtsdb_ssd -mcore 1H8 2>&1 | tee ./caffe2cambricon.log

操作方案二

我把操作一写进genoff.sh中

#!/bin/sh

PATH_ROOT=../..
PATH_TOOL=${PATH_ROOT}/tools
PATH_LIB=${PATH_ROOT}/lib
PATH_GTSDB=${PATH_ROOT}/expr/gtsdb_ssd
PATH_MODEL=${PATH_GTSDB}/model/ssd_float32_gtsdb.fix8.prototxt
PATH_WEIGHTS=${PATH_GTSDB}/model/VGG_gtsdb_voc_SSD_300x300_iter_60000.caffemodel

export LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:${PATH_LIB}/x86

${PATH_TOOL}/caffe genoff -model ${PATH_MODEL} -weights ${PATH_WEIGHTS} \
                          -mname ${PATH_GTSDB}/model/gtsdb_ssd -mcore 1H8 \
2>&1 | tee ${PATH_GTSDB}/model/caffe2cambricon.log

cd /home/jqy/jqy_nfs_server/HCAI1H_HOST_SDK/expr/gtsdb_ssd # 进入要量化的项目的根目录
./genoff.sh

操作后

model目录下生成gtsdb_ssd.cambricon，gtsdb_ssd.cambricon_twins，caffe2cambricon.log。
最后我们需要用到的就是gtsdb_ssd.cambricon这个文件。

超超越越一亿粉丝
关注
  • 0
    点赞
  • 踩
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
专栏目录
<汇编语言程序设计> 课堂笔记
pb1995的博客
07-31 1487
1.小端模式，是指数据的高字节保存在内存的高地址中，而数据的低字节保存在内存的低地址中，这种存储模式将地址的高低和数据位权有效地结合起来，高地址部分权值高，低地址部分权值低，和我们的逻辑方法一致。   2.MD5加密：单向算法，只能从字符串计算出MD5值，不能逆向计算出源代码（因为并非一一对应的，可能有多个源码对应一个MD5）。MD5的碰撞。应用：RAR密码   3.静态的数据（RAR,图
vt2-to-pico-8：Vortex Tracker到PICO-8音乐转换器
02-05
1. **解析器**：这部分代码负责读取Vortex Tracker的音乐文件（可能为VT2或VT3格式），解析其内部结构，提取出音符、节奏、音效等音乐元素。 2. **编码算法**：由于PICO-8的内存有限（仅4KB的 carts空间），音乐...
1h-8学习（1）：1h-8适配之int8直接量化+转.cambricon格式
weixin_42068754的博客
05-21 490
我尝试量化的模型是我自己训练的VGG_gtsdb_voc_SSD_300x300_iter_60000.caffemodel 网络结构文件对比 网络结构文件有五个：train.prototxt（训练时网络结构）、test.prototxt（测试评估时网络结构）、deploy.prototxt（实际图片检测网络结构）、ssd_float32_dense.prototxt（适配1-h8的全精度网络结构）、ssd_float32_dense.fix8.prototxt（量化完成后的网络结构）。因为Convolut
使用tensorflow自带的工具进行直接8bit量化
andeyeluguo的博客
07-03 7297
首先可以使用docker安装一个最新的cpu版本的tensorflow docker pull tensorflow/tensorflow:latest 1. bazel安装见博客。 2. 在github上下载tensorflow-master的源代码并unzip cd tensorflow-master 3.编译工具 由于新版的tensorflow代码有了变化，旧版的t...
常见int中断
weixin_61669837的博客
02-19 1028
常见int中断 中断基础知识 中断向量表 int中断的机器码 `int 21h`: `int 10h`: 视频中断 `int 16h`: 键盘中断 `int 09h`: 键盘的输入将会引发9号中断 `int 08h`: 时间中断 `int 1h`单步中断 `int 13h`: 磁盘中断
tensorflow的量化教程(1)
u012101561的博客
09-10 1万+
前段时间利用tensorflow的量化工具做了量化训练，精度损失很小，有时甚至比浮点模型精度更好一点，确实强大。利用tflite框架在3536上相比浮点模型有了2X左右的速度提升，现在做一个总结记录。 https://github.com/tensorflow/tensorflow/tree/master/tensorflow/contrib/quantize， 这是tensorflow的量化...
ITU-T H.222.0建议书 iso13818-1-CN.zip
11-04
ISO 13818-1是MPEG-2传输层的标准，它是MPEG-2系统的一部分，用于规范数字电视和多媒体数据的传输和存储。 MPEG-2（Moving Picture Experts Group-2）是由ISO和IEC联合制定的一系列标准，用于数字视频和音频的压缩...
3DS-Pico8：改为查看https：github.comjtothebellfake-08
02-06
标题中的“3DS-Pico8：改为查看https：github.comjtothebellfake-08”指的是一个关于在任天堂3DS平台上运行Pico8的项目，该项目的源代码或资源可能已经迁移到了GitHub上的特定仓库。Pico8是一个虚拟游戏机和编程环境...
3-10-1(列表之ArrayAdapter适配).7z
01-30
这个“3-10-1(列表之ArrayAdapter适配).7z”压缩包可能包含了一个关于如何使用ArrayAdapter来显示列表数据的教学资源。现在，我们将深入探讨ArrayAdapter的工作原理及其在Android开发中的应用。 ArrayAdapter是...
HCS-Pre- L2（H19-371）.pdf
02-13
本文主要涉及华为的HCS-Pre-L2（H19-371）认证的相关知识点，主要涵盖了数据中心基础设施的多个方面，如机柜、UPS不间断电源系统、精密配电柜、空调系统、管理系统以及安全和可靠性设计。以下是这些知识点的详细说明...
寒武纪MLU270安装运行Pytorch yolov3实录
HC_wood的博客
04-03 1635
注：本教程仅供摩米实验室内部学习适用。
DOS功能调用
The simple, The best.
10-13 3224
AH功能调用参数返回参数00程序终止(同INT 20H)CS=程序段前缀　01键盘输入并回显　AL=输入字符02显示输出DL=输出字符　03异步通迅输入　AL=输入数据04异步通迅输出DL=输出数据　05打印机输出DL=输出字符　06直接控制台I/ODL=FF(输入)DL=字符(输出)AL=输入字符07键盘输入(无回显)　AL=输入字符08键盘输入(无回显)检测Ctrl-Break　AL=输入字符
【环境搭建】cambricon测试
luolinll1212的专栏
09-09 618
# -*- coding: utf-8 -*- import torch_mlu import torch_mlu.core.mlu_model as ct import torch_mlu.core.mlu_quantize as mlu_quantize import torch import numpy as np import torchvision.transforms as transforms from torchvision.models.resnet import resnet50 fro
AI芯片：寒武纪Cambricon-X结构分析
热门推荐
evolone的专栏
09-10 1万+
五、Cambricon-X Cambricon-X是针对稀疏系数的矩阵计算架构。 深鉴科技的韩松等人的研究发现，可以将传统的深度学习网络模型的许多权重系数去掉，甚至能去掉90%以上，而并不影响模型的计算精度。如下图所示。 目前的深度学习模型的权重系数太多，造成需要的乘法计算非常多，计算时间长，速度慢。 相信，未来的模型会更加复杂，需要的计算更多，时间更久。 未来把模型进行系数删减，就...
INT 21H
wyyy2088511的博客
04-21 1万+
INT 21H是指令自动转入中断子程序的入口 上面这句话很难理解吧，相信很多新手都看不懂在说什么。 下面我来举个例子： 以8086 CPU的汇编为例,输出一个字符串，就要使用如下指令： MOV AH,09H INT 21H 假如要在显示器显示输入一个字符串，实际上就是要调用DOS系统的功能来实现。 当然，DOS是包括多种功能，如接受用户输入，显示输出，输出到打印机打印等...... 每一个功能，都有一个编号，其中，在“显示器显示输出”这个功能的编号是09 MOV AH,09H 这个就表示把09这个编号放.
量化_深度学习
kyle1314608的博客
11-27 1835
、 一、模型量化的背景需求 Resnet-152神经网络的提出证明了越宽越深越大的模型往往比越窄越浅越小的模型精度要高，但是越宽越深越大的模型对计算资源要求更高，而现在模型应用越来越倾向于从云端部署到边缘侧，受限于边缘侧设备的计算资源，我们不得不考虑设备存储空间（storage）、设备内存大小（memory）、设备运行功耗（power）及时延性（latency）等等问题，特别是在移动终端和嵌入式设备等资源受限的边缘侧应用场景中更加需要我们进行优化。因此，为了解决此类问题模型量化应运而生，本篇我们将探讨模型量
宿主机程序开发方法
weixin_44705725的博客
07-13 387
最近在学习1-H8芯片，这是我对于老师给的资料的一部分的总结，好难哦，看看不懂 主要介绍宿主机上的程序开发方法，即如何移植一个第三方深度学习应用程序的 方法。归纳起来主要有三个过程： 8bit 模型生成 由于 8bit 神经网络模型能够显著减少模型占用的存储空间和处理带宽，目前 1H8 只支 持 8bit 模型，而在其它平台（如 CPU 或 GPU）上训练出来的模型（以 caffe 为例，模型 ...
openvino使用（一）转换并量化（INT8）分类网络模型
霹雳吧啦Wz
09-09 9804
在pycharm中使用openvino包，不能直接使用图标启动，要使用终端启动。如果不知道pycharm的启动文件在哪，可以通过以下指令查找： sudo find / -name pycharm.sh 找到后进入pycharm.sh所在文件夹，执行该启动脚本： ./pycharm.sh 将onnx模型转成IR格式（FP16除了模型小一点，没任何提速）： python mo.py --input_model ~/my_project/resnet34.onnx --output_dir ~/openvin
1h-8学习（3）：SSD模型在1-h8上运行
weixin_42068754的博客
06-02 351
我这部分的实验都是在HCAI1H_HOST_SDK下的，只作为体验。 编译程序 修改ssd_detection_offline.cpp，我这边只改了标签到输出的映射，跟我之前训练的对应： 修改/home/jqy/jqy_nfs_server/HCAI1H_HOST_SDK/expr下的CMakeLists.txt cmake_minimum_required(VERSION 3.5) project(edu_expr) set( CMAKE_CXX_FLAGS "-std=c++11" ) #set
com.alibaba.cloud:spring-cloud-starter-alibaba-nacos-discovery:2022.0.0.0
最新发布
08-01
根据引用[1]和引用[3]的信息，您在项目中添加了com.alibaba.cloud:spring-cloud-starter-alibaba-nacos-discovery:2022.0.0.0依赖后，项目无法启动。根据引用[2]提供的GitHub地址，您可以尝试从GitHub上下载最新的代码，以解决此问题。另外，根据引用[3]中提供的springboot版本和Nacos Discovery版本的对应关系，您可以尝试使用适配的版本来解决问题。

“相关推荐”对你有帮助么？

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值