Nvidia Jetson Tx2 使用 VGG_VOC0712_SSD_300x300 模型(一)

最新推荐文章于 2021-06-09 12:18:46 发布
最新推荐文章于 2021-06-09 12:18:46 发布
阅读量1.8k 收藏 1
点赞数
分类专栏： 机器学习 AI 算法模型 C/C++/VC 文章标签： nvidia Tx2 PluginFactory VGG_VOC0712_SSD
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.youkuaiyun.com/ikevin/article/details/79584753
版权

        Nvidia Jetson Tx2 性能是否逆天我并不清楚，但从产品意义上来讲，Tx2也就是个半成品：

            1.二次开发接口不友好，本身还有很多Bug。比如自定义网络Layer时，不支持fp16，只能使用fp32。说是要再3.0.4版本才修复？

            2.sample的代码真不敢恭维，完全没有条理，比较难读。

        Tx2上TensorRT是3.0，跑VGG_VOC0712_SSD_300x300模型有很多Layer不认，如Flatten，Reshape等。需要自己通过PluginFactory接口进行实现。

        再Tx2上跑VGG_VOC0712_SSD_300x300模型步骤如下：

                1.修改deploy文件适应TensorRT，主要是将不识别的layer的参数注释掉；

                2.对不识别的layer通过PluginFactory接口进行实现；

                3.使用CudaEngine对model进行序列化，形成TensorRT可识别的cached model文件；

                4.使用CudaEngine对cached model进行反序列化，并进行预测业务处理；

1.修改deploy文件适应TensorRT，主要是将不识别的layer的参数注释掉

name: "VGG_VOC0712_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
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 64
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 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
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 64
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 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
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 128
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 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
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 128
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 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
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 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
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 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
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 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
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 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
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 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
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 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
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 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
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 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
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 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
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 1024
    pad: 6
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 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
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 1024
    kernel_size: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 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
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    pad: 0
    kernel_size: 1
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 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
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
    stride: 2
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 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
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 128
    pad: 0
    kernel_size: 1
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 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
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    pad: 1
    kernel_size: 3
    stride: 2
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 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
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 128
    pad: 0
    kernel_size: 1
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 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
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    pad: 0
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 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
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 128
    pad: 0
    kernel_size: 1
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 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
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    pad: 0
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 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
#    }
#    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
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 16
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 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_conf"
  type: "Convolution"
  bottom: "conv4_3_norm"
  top: "conv4_3_norm_mbox_conf"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 84
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "conv4_3_norm_mbox_conf_perm"
  type: "Permute"
  bottom: "conv4_3_norm_mbox_conf"
  top: "conv4_3_norm_mbox_conf_perm"
#  permute_param {
#    order: 0
#    order: 2
#    order: 3
#    order: 1
#  }
}
layer {
  name: "conv4_3_norm_mbox_conf_flat"
  type: "Flatten"
  bottom: "conv4_3_norm_mbox_conf_perm"
  top: "conv4_3_norm_mbox_conf_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
#    flip: true
#    clip: false
#    variance: 0.1
#    variance: 0.1
#    variance: 0.2
#    variance: 0.2
#    step: 8
#    offset: 0.5
#  }
}
layer {
  name: "fc7_mbox_loc"
  type: "Convolution"
  bottom: "fc7"
  top: "fc7_mbox_loc"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 24
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 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_conf"
  type: "Convolution"
  bottom: "fc7"
  top: "fc7_mbox_conf"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 126
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "fc7_mbox_conf_perm"
  type: "Permute"
  bottom: "fc7_mbox_conf"
  top: "fc7_mbox_conf_perm"
#  permute_param {
#    order: 0
#    order: 2
#    order: 3
#    order: 1
#  }
}
layer {
  name: "fc7_mbox_conf_flat"
  type: "Flatten"
  bottom: "fc7_mbox_conf_perm"
  top: "fc7_mbox_conf_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
#    aspect_ratio: 3
#    flip: true
#    clip: false
#    variance: 0.1
#    variance: 0.1
#    variance: 0.2
#    variance: 0.2
#    step: 16
#    offset: 0.5
#  }
}
layer {
  name: "conv6_2_mbox_loc"
  type: "Convolution"
  bottom: "conv6_2"
  top: "conv6_2_mbox_loc"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 24
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 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_conf"
  type: "Convolution"
  bottom: "conv6_2"
  top: "conv6_2_mbox_conf"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 126
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "conv6_2_mbox_conf_perm"
  type: "Permute"
  bottom: "conv6_2_mbox_conf"
  top: "conv6_2_mbox_conf_perm"
#  permute_param {
#    order: 0
#    order: 2
#    order: 3
#    order: 1
#  }
}
layer {
  name: "conv6_2_mbox_conf_flat"
  type: "Flatten"
  bottom: "conv6_2_mbox_conf_perm"
  top: "conv6_2_mbox_conf_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
#    aspect_ratio: 3
#    flip: true
#    clip: false
#    variance: 0.1
#    variance: 0.1
#    variance: 0.2
#    variance: 0.2
#    step: 32
#    offset: 0.5
#  }
}
layer {
  name: "conv7_2_mbox_loc"
  type: "Convolution"
  bottom: "conv7_2"
  top: "conv7_2_mbox_loc"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 24
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 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_conf"
  type: "Convolution"
  bottom: "conv7_2"
  top: "conv7_2_mbox_conf"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 126
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "conv7_2_mbox_conf_perm"
  type: "Permute"
  bottom: "conv7_2_mbox_conf"
  top: "conv7_2_mbox_conf_perm"
#  permute_param {
#    order: 0
#    order: 2
#    order: 3
#    order: 1
#  }
}
layer {
  name: "conv7_2_mbox_conf_flat"
  type: "Flatten"
  bottom: "conv7_2_mbox_conf_perm"
  top: "conv7_2_mbox_conf_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
#    aspect_ratio: 3
#    flip: true
#    clip: false
#    variance: 0.1
#    variance: 0.1
#    variance: 0.2
#    variance: 0.2
#    step: 64
#    offset: 0.5
#  }
}
layer {
  name: "conv8_2_mbox_loc"
  type: "Convolution"
  bottom: "conv8_2"
  top: "conv8_2_mbox_loc"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 16
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 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_conf"
  type: "Convolution"
  bottom: "conv8_2"
  top: "conv8_2_mbox_conf"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 84
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "conv8_2_mbox_conf_perm"
  type: "Permute"
  bottom: "conv8_2_mbox_conf"
  top: "conv8_2_mbox_conf_perm"
#  permute_param {
#    order: 0
#    order: 2
#    order: 3
#    order: 1
#  }
}
layer {
  name: "conv8_2_mbox_conf_flat"
  type: "Flatten"
  bottom: "conv8_2_mbox_conf_perm"
  top: "conv8_2_mbox_conf_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
#    flip: true
#    clip: false
#    variance: 0.1
#    variance: 0.1
#    variance: 0.2
#    variance: 0.2
#    step: 100
#    offset: 0.5
#  }
}
layer {
  name: "conv9_2_mbox_loc"
  type: "Convolution"
  bottom: "conv9_2"
  top: "conv9_2_mbox_loc"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 16
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 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_conf"
  type: "Convolution"
  bottom: "conv9_2"
  top: "conv9_2_mbox_conf"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 84
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "conv9_2_mbox_conf_perm"
  type: "Permute"
  bottom: "conv9_2_mbox_conf"
  top: "conv9_2_mbox_conf_perm"
#  permute_param {
#    order: 0
#    order: 2
#    order: 3
#    order: 1
#  }
}
layer {
  name: "conv9_2_mbox_conf_flat"
  type: "Flatten"
  bottom: "conv9_2_mbox_conf_perm"
  top: "conv9_2_mbox_conf_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
#    flip: true
#    clip: false
#    variance: 0.1
#    variance: 0.1
#    variance: 0.2
#    variance: 0.2
#    step: 300
#    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_conf"
  type: "Concat"
  bottom: "conv4_3_norm_mbox_conf_flat"
  bottom: "fc7_mbox_conf_flat"
  bottom: "conv6_2_mbox_conf_flat"
  bottom: "conv7_2_mbox_conf_flat"
  bottom: "conv8_2_mbox_conf_flat"
  bottom: "conv9_2_mbox_conf_flat"
  top: "mbox_conf"
  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_conf_reshape"
  type: "Reshape"
  bottom: "mbox_conf"
  top: "mbox_conf_reshape"
  reshape_param {
    shape {
      dim: 0
      dim: -1
      dim: 21
    }
  }
}
layer {
  name: "mbox_conf_softmax"
  type: "Softmax"
  bottom: "mbox_conf_reshape"
  top: "mbox_conf_softmax"
  softmax_param {
    axis: 2
  }
}
layer {
  name: "mbox_conf_flatten"
  type: "Flatten"
  bottom: "mbox_conf_softmax"
  top: "mbox_conf_flatten"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "detection_out"
  type: "DetectionOutput"
  bottom: "mbox_loc"
  bottom: "mbox_conf_flatten"
  bottom: "mbox_priorbox"
  top: "detection_out"
  top: "detection_out2"
  include {
    phase: TEST
  }
#  detection_output_param {
#    num_classes: 21
#    share_location: true
#    background_label_id: 0
#    nms_param {
#      nms_threshold: 0.45
#      top_k: 400
#    }
#    code_type: CENTER_SIZE
#    keep_top_k: 200
#    confidence_threshold: 0.5
#  }
}


Jetson_TX2_TX2i_Module_DataSheet_v01.rar_JETSON TX2_Jason TX2 da
09-22
8. **应用示例**：可能包含实际应用案例，展示Jetson TX2和TX2i在物联网、自动驾驶、无人机等领域的使用方式。 9. **故障排查**：提供常见问题和解决办法，帮助开发者快速解决遇到的问题。 10. **安全性和合规性**...
Jetson_TX2_Module_DataSheet_v1.1
04-28
Jetson TX2 incorporates these same GPU architectural enhancements to further increase performance and reduce power consumption for computationally intensive workloads. The previous (Maxwell) GPU ...
VGG_VOC0712_SSD_300x300_iter_120000.ckpt.zip
08-05
Note: SSD300* and SSD512* are the latest models. Current code should reproduce these results.
models_VGGNet_VOC0712_SSD_300x300.tar.gz
07-02
已训练好的VGGNet模型可导入直接使用。具体使用说明可参考https://blog.youkuaiyun.com/u010677365/article/details/80881040。
SSD-300 VGG-based
08-05
Note: SSD300* and SSD512* are the latest models. Current code should reproduce these results.
Nvidia Jetson Tx2 使用 VGG_VOC0712_SSD_300x300 模型(二)
ikevin的专栏
03-21 1238
直接上代码:PluginFactory.h#ifndef __PLUGIN_FACTORY_H__ #define __PLUGIN_FACTORY_H__ #include <algorithm> #include <cassert> #include <iostream> #include <cstring> #include <sys/...
SSD-300 VGG-based weights 权重包含两种ssd300的权重
11-18
SSD_300_vggmodel，包含两种ssd300： Model Training data Testing data mAP SSD-300 VGG-based VOC07+12+COCO trainval VOC07 test SSD-300 VGG-based VOC07+12 trainval VOC07 test -
NVIDIA_Jetson_Linux_Driver_Package-32.4.3.zip
09-27
NVIDIA Jetson系列是专为嵌入式计算和人工智能应用设计的一系列高性能、低功耗的开发板，其中TX2型号尤为常见。针对这类开发板，NVIDIA提供了详尽的Linux驱动程序包，以支持开发者进行高效、稳定的应用开发。本篇将...
NVIDIA Jetson TX2介绍
01-19
详细介绍了NVIDIA TX2套件的基础和软件架构，总结的很到位
nv_jetson_tx2_developer_kit_user_guide.pdf
03-25
英伟达Jetson TX2的用户手册, 开发者专用. nv_jetson_tx2_developer_kit_user_guide
VGG_VOC0712Plus_SSD_300x300_iter_240000.caffemodel
07-01
SSD-caffe已训练好的300x300模型，找国外同学下载的官方模型，基于VOC2007+VOC2012训练的Plus版本，训练了24万轮次，实测VOC2007数据集4952张图片，mAP为90%，实测部分输出如下。同时还有训练好的SSD512模型，同样是官方下载，训练24万轮。 I0701 12:37:55.655375 32319 caffe.cpp:155] Finetuning from models/VGGNet/VOC0712Plus/SSD_300x300/VGG_VOC0712Plus_SSD_300x300_iter_240000.caffemodel I0701 12:37:56.035286 32319 net.cpp:761] Ignoring source layer mbox_loss I0701 12:37:56.036597 32319 caffe.cpp:251] Starting Optimization I0701 12:37:56.036615 32319 solver.cpp:294] Solving VGG_VOC0712Plus_SSD_300x300_train I0701 12:37:56.036620 32319 solver.cpp:295] Learning Rate Policy: multistep I0701 12:37:56.115556 32319 solver.cpp:332] Iteration 0, loss = 0.898412 I0701 12:37:56.115597 32319 solver.cpp:433] Iteration 0, Testing net (#0) I0701 12:37:56.130832 32319 net.cpp:693] Ignoring source layer mbox_loss I0701 12:40:53.262286 32319 solver.cpp:546] Test net output #0: detection_eval = 0.904216 I0701 12:40:53.262420 32319 solver.cpp:337] Optimization Done. I0701 12:40:53.262426 32319 caffe.cpp:254] Optimization Done.
VGG_VOC0712_SSD_300x300.ckpt.rar
07-24
[SSD-300 VGG-based] | VOC07+12+COCO trainval | VOC07 test | 0.817 | - |原文中指定模型
VGG_VOC0712_SSD_300x300_iter_120000.caffemodel
08-21
VGG_VOC0712_SSD_300x300_iter_120000.caffemodel，caffe-SSD下已经训练好的VGG模型文件，希望对大家有所帮助。
models_VGGNet_VOC0712_SSD_300x300.zip
09-02
训练好的模型models_VGGNet_VOC0712_SSD_300x300，有需要自行下载。
ssd300_VOC_120000.pth
03-27
ssd300_VOC_120000.pth
Jetson TX2刷机及模型调用
yx868yx的博客
05-14 1103
一、刷机 刚买回来的TX2装的是纯净的Ubantu 16.04的系统，需要刷机，用到ubuntu系统的主机，HDMI显示屏等 Jetson TX2 自带ubuntu 16.04 系统，首次开机时，进入的是以nvidia用户登录的Ubuntu命令行界面。如果要使用图形化界面，需要安装Nvidia Linux驱动，Nvidia 驱动安装通过sudo su 输入密码：nvidia，切换root权限用户。...
在jetson tx2上使用tensorrt加速推理tensorflow2模型
weixin_43842032的博客
12-31 2843
在jetson tx2上安装tensorflow2.0并使用tensorrt加速推理目的运行环境准备jetpack更新tensorflow 2.0安装工作流程准备开始需要注意试一试 目的 学习tensorrt主要目的还是将其应用到板子上,在上一篇博客中,介绍了怎么在主机中使用tensorrt,现在将其放到jetson设备上执行试试 运行环境准备 jetpack tensorflow ...
基于VGG网络的SSD算法
weixin_43999691的博客
06-09 2428
前言 关于目标检测算法，可以分成两类， 目标检测目前有 one-stage 和 two-stage 两种，two-stage 指的是检测算法需要分两步完成，首先需要获取候选区域，然后进行分类，比如R-CNN系列；与之相对的是 one-stage 检测，可以理解为一步到位，不需要单独寻找候选区域，典型的有SSD/YOLO。 作者：HRain 链接：https://www.jianshu.com/p/468e08f739bd 来源：简书 著作权归作者所有。商业转载请联系作者获得授权，非商业转载请注明出处
OpenCV-dnn加载SSD300-Model目标检测
04-17
利用opencv-dnn加载SSD300-model进行目标检测，可以检测输入的图片，也可以利用USB-camera实时检测（目标包括人、汽车、狗等等），资源包含源代码和可执行程序（release文件夹下的exe文件可以直接运行测试）
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