Upload 4 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+MobileNetSSD_deploy.caffemodel filter=lfs diff=lfs merge=lfs -text

MobileNetSSD_deploy.caffemodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:761c86fbae3d8361dd454f7c740a964f62975ed32f4324b8b85994edec30f6af
+size 23147564

MobileNetSSD_deploy.prototxt.txt

@@ -0,0 +1,1912 @@
+name: "MobileNet-SSD"
+input: "data"
+input_shape {
+  dim: 1
+  dim: 3
+  dim: 300
+  dim: 300
+}
+layer {
+  name: "conv0"
+  type: "Convolution"
+  bottom: "data"
+  top: "conv0"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 32
+    pad: 1
+    kernel_size: 3
+    stride: 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv0/relu"
+  type: "ReLU"
+  bottom: "conv0"
+  top: "conv0"
+}
+layer {
+  name: "conv1/dw"
+  type: "Convolution"
+  bottom: "conv0"
+  top: "conv1/dw"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 32
+    pad: 1
+    kernel_size: 3
+    group: 32
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv1/dw/relu"
+  type: "ReLU"
+  bottom: "conv1/dw"
+  top: "conv1/dw"
+}
+layer {
+  name: "conv1"
+  type: "Convolution"
+  bottom: "conv1/dw"
+  top: "conv1"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 64
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv1/relu"
+  type: "ReLU"
+  bottom: "conv1"
+  top: "conv1"
+}
+layer {
+  name: "conv2/dw"
+  type: "Convolution"
+  bottom: "conv1"
+  top: "conv2/dw"
+  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
+    stride: 2
+    group: 64
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv2/dw/relu"
+  type: "ReLU"
+  bottom: "conv2/dw"
+  top: "conv2/dw"
+}
+layer {
+  name: "conv2"
+  type: "Convolution"
+  bottom: "conv2/dw"
+  top: "conv2"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 128
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv2/relu"
+  type: "ReLU"
+  bottom: "conv2"
+  top: "conv2"
+}
+layer {
+  name: "conv3/dw"
+  type: "Convolution"
+  bottom: "conv2"
+  top: "conv3/dw"
+  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
+    group: 128
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv3/dw/relu"
+  type: "ReLU"
+  bottom: "conv3/dw"
+  top: "conv3/dw"
+}
+layer {
+  name: "conv3"
+  type: "Convolution"
+  bottom: "conv3/dw"
+  top: "conv3"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 128
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv3/relu"
+  type: "ReLU"
+  bottom: "conv3"
+  top: "conv3"
+}
+layer {
+  name: "conv4/dw"
+  type: "Convolution"
+  bottom: "conv3"
+  top: "conv4/dw"
+  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
+    stride: 2
+    group: 128
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv4/dw/relu"
+  type: "ReLU"
+  bottom: "conv4/dw"
+  top: "conv4/dw"
+}
+layer {
+  name: "conv4"
+  type: "Convolution"
+  bottom: "conv4/dw"
+  top: "conv4"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 256
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv4/relu"
+  type: "ReLU"
+  bottom: "conv4"
+  top: "conv4"
+}
+layer {
+  name: "conv5/dw"
+  type: "Convolution"
+  bottom: "conv4"
+  top: "conv5/dw"
+  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
+    group: 256
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv5/dw/relu"
+  type: "ReLU"
+  bottom: "conv5/dw"
+  top: "conv5/dw"
+}
+layer {
+  name: "conv5"
+  type: "Convolution"
+  bottom: "conv5/dw"
+  top: "conv5"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 256
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv5/relu"
+  type: "ReLU"
+  bottom: "conv5"
+  top: "conv5"
+}
+layer {
+  name: "conv6/dw"
+  type: "Convolution"
+  bottom: "conv5"
+  top: "conv6/dw"
+  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
+    group: 256
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv6/dw/relu"
+  type: "ReLU"
+  bottom: "conv6/dw"
+  top: "conv6/dw"
+}
+layer {
+  name: "conv6"
+  type: "Convolution"
+  bottom: "conv6/dw"
+  top: "conv6"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 512
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv6/relu"
+  type: "ReLU"
+  bottom: "conv6"
+  top: "conv6"
+}
+layer {
+  name: "conv7/dw"
+  type: "Convolution"
+  bottom: "conv6"
+  top: "conv7/dw"
+  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
+    group: 512
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv7/dw/relu"
+  type: "ReLU"
+  bottom: "conv7/dw"
+  top: "conv7/dw"
+}
+layer {
+  name: "conv7"
+  type: "Convolution"
+  bottom: "conv7/dw"
+  top: "conv7"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 512
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv7/relu"
+  type: "ReLU"
+  bottom: "conv7"
+  top: "conv7"
+}
+layer {
+  name: "conv8/dw"
+  type: "Convolution"
+  bottom: "conv7"
+  top: "conv8/dw"
+  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
+    group: 512
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv8/dw/relu"
+  type: "ReLU"
+  bottom: "conv8/dw"
+  top: "conv8/dw"
+}
+layer {
+  name: "conv8"
+  type: "Convolution"
+  bottom: "conv8/dw"
+  top: "conv8"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 512
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv8/relu"
+  type: "ReLU"
+  bottom: "conv8"
+  top: "conv8"
+}
+layer {
+  name: "conv9/dw"
+  type: "Convolution"
+  bottom: "conv8"
+  top: "conv9/dw"
+  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
+    group: 512
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv9/dw/relu"
+  type: "ReLU"
+  bottom: "conv9/dw"
+  top: "conv9/dw"
+}
+layer {
+  name: "conv9"
+  type: "Convolution"
+  bottom: "conv9/dw"
+  top: "conv9"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 512
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv9/relu"
+  type: "ReLU"
+  bottom: "conv9"
+  top: "conv9"
+}
+layer {
+  name: "conv10/dw"
+  type: "Convolution"
+  bottom: "conv9"
+  top: "conv10/dw"
+  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
+    group: 512
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv10/dw/relu"
+  type: "ReLU"
+  bottom: "conv10/dw"
+  top: "conv10/dw"
+}
+layer {
+  name: "conv10"
+  type: "Convolution"
+  bottom: "conv10/dw"
+  top: "conv10"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 512
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv10/relu"
+  type: "ReLU"
+  bottom: "conv10"
+  top: "conv10"
+}
+layer {
+  name: "conv11/dw"
+  type: "Convolution"
+  bottom: "conv10"
+  top: "conv11/dw"
+  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
+    group: 512
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv11/dw/relu"
+  type: "ReLU"
+  bottom: "conv11/dw"
+  top: "conv11/dw"
+}
+layer {
+  name: "conv11"
+  type: "Convolution"
+  bottom: "conv11/dw"
+  top: "conv11"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 512
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv11/relu"
+  type: "ReLU"
+  bottom: "conv11"
+  top: "conv11"
+}
+layer {
+  name: "conv12/dw"
+  type: "Convolution"
+  bottom: "conv11"
+  top: "conv12/dw"
+  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
+    group: 512
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv12/dw/relu"
+  type: "ReLU"
+  bottom: "conv12/dw"
+  top: "conv12/dw"
+}
+layer {
+  name: "conv12"
+  type: "Convolution"
+  bottom: "conv12/dw"
+  top: "conv12"
+  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: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv12/relu"
+  type: "ReLU"
+  bottom: "conv12"
+  top: "conv12"
+}
+layer {
+  name: "conv13/dw"
+  type: "Convolution"
+  bottom: "conv12"
+  top: "conv13/dw"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 1024
+    pad: 1
+    kernel_size: 3
+    group: 1024
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv13/dw/relu"
+  type: "ReLU"
+  bottom: "conv13/dw"
+  top: "conv13/dw"
+}
+layer {
+  name: "conv13"
+  type: "Convolution"
+  bottom: "conv13/dw"
+  top: "conv13"
+  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: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv13/relu"
+  type: "ReLU"
+  bottom: "conv13"
+  top: "conv13"
+}
+layer {
+  name: "conv14_1"
+  type: "Convolution"
+  bottom: "conv13"
+  top: "conv14_1"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 256
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv14_1/relu"
+  type: "ReLU"
+  bottom: "conv14_1"
+  top: "conv14_1"
+}
+layer {
+  name: "conv14_2"
+  type: "Convolution"
+  bottom: "conv14_1"
+  top: "conv14_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: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv14_2/relu"
+  type: "ReLU"
+  bottom: "conv14_2"
+  top: "conv14_2"
+}
+layer {
+  name: "conv15_1"
+  type: "Convolution"
+  bottom: "conv14_2"
+  top: "conv15_1"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 128
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv15_1/relu"
+  type: "ReLU"
+  bottom: "conv15_1"
+  top: "conv15_1"
+}
+layer {
+  name: "conv15_2"
+  type: "Convolution"
+  bottom: "conv15_1"
+  top: "conv15_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: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv15_2/relu"
+  type: "ReLU"
+  bottom: "conv15_2"
+  top: "conv15_2"
+}
+layer {
+  name: "conv16_1"
+  type: "Convolution"
+  bottom: "conv15_2"
+  top: "conv16_1"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 128
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv16_1/relu"
+  type: "ReLU"
+  bottom: "conv16_1"
+  top: "conv16_1"
+}
+layer {
+  name: "conv16_2"
+  type: "Convolution"
+  bottom: "conv16_1"
+  top: "conv16_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: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv16_2/relu"
+  type: "ReLU"
+  bottom: "conv16_2"
+  top: "conv16_2"
+}
+layer {
+  name: "conv17_1"
+  type: "Convolution"
+  bottom: "conv16_2"
+  top: "conv17_1"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 64
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv17_1/relu"
+  type: "ReLU"
+  bottom: "conv17_1"
+  top: "conv17_1"
+}
+layer {
+  name: "conv17_2"
+  type: "Convolution"
+  bottom: "conv17_1"
+  top: "conv17_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
+    stride: 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv17_2/relu"
+  type: "ReLU"
+  bottom: "conv17_2"
+  top: "conv17_2"
+}
+layer {
+  name: "conv11_mbox_loc"
+  type: "Convolution"
+  bottom: "conv11"
+  top: "conv11_mbox_loc"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 12
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv11_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv11_mbox_loc"
+  top: "conv11_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv11_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv11_mbox_loc_perm"
+  top: "conv11_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv11_mbox_conf"
+  type: "Convolution"
+  bottom: "conv11"
+  top: "conv11_mbox_conf"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 63
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv11_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv11_mbox_conf"
+  top: "conv11_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv11_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv11_mbox_conf_perm"
+  top: "conv11_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv11_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv11"
+  bottom: "data"
+  top: "conv11_mbox_priorbox"
+  prior_box_param {
+    min_size: 60.0
+    aspect_ratio: 2.0
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    offset: 0.5
+  }
+}
+layer {
+  name: "conv13_mbox_loc"
+  type: "Convolution"
+  bottom: "conv13"
+  top: "conv13_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
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv13_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv13_mbox_loc"
+  top: "conv13_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv13_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv13_mbox_loc_perm"
+  top: "conv13_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv13_mbox_conf"
+  type: "Convolution"
+  bottom: "conv13"
+  top: "conv13_mbox_conf"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 126
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv13_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv13_mbox_conf"
+  top: "conv13_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv13_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv13_mbox_conf_perm"
+  top: "conv13_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv13_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv13"
+  bottom: "data"
+  top: "conv13_mbox_priorbox"
+  prior_box_param {
+    min_size: 105.0
+    max_size: 150.0
+    aspect_ratio: 2.0
+    aspect_ratio: 3.0
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    offset: 0.5
+  }
+}
+layer {
+  name: "conv14_2_mbox_loc"
+  type: "Convolution"
+  bottom: "conv14_2"
+  top: "conv14_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
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv14_2_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv14_2_mbox_loc"
+  top: "conv14_2_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv14_2_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv14_2_mbox_loc_perm"
+  top: "conv14_2_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv14_2_mbox_conf"
+  type: "Convolution"
+  bottom: "conv14_2"
+  top: "conv14_2_mbox_conf"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 126
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv14_2_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv14_2_mbox_conf"
+  top: "conv14_2_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv14_2_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv14_2_mbox_conf_perm"
+  top: "conv14_2_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv14_2_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv14_2"
+  bottom: "data"
+  top: "conv14_2_mbox_priorbox"
+  prior_box_param {
+    min_size: 150.0
+    max_size: 195.0
+    aspect_ratio: 2.0
+    aspect_ratio: 3.0
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    offset: 0.5
+  }
+}
+layer {
+  name: "conv15_2_mbox_loc"
+  type: "Convolution"
+  bottom: "conv15_2"
+  top: "conv15_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
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv15_2_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv15_2_mbox_loc"
+  top: "conv15_2_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv15_2_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv15_2_mbox_loc_perm"
+  top: "conv15_2_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv15_2_mbox_conf"
+  type: "Convolution"
+  bottom: "conv15_2"
+  top: "conv15_2_mbox_conf"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 126
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv15_2_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv15_2_mbox_conf"
+  top: "conv15_2_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv15_2_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv15_2_mbox_conf_perm"
+  top: "conv15_2_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv15_2_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv15_2"
+  bottom: "data"
+  top: "conv15_2_mbox_priorbox"
+  prior_box_param {
+    min_size: 195.0
+    max_size: 240.0
+    aspect_ratio: 2.0
+    aspect_ratio: 3.0
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    offset: 0.5
+  }
+}
+layer {
+  name: "conv16_2_mbox_loc"
+  type: "Convolution"
+  bottom: "conv16_2"
+  top: "conv16_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
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv16_2_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv16_2_mbox_loc"
+  top: "conv16_2_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv16_2_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv16_2_mbox_loc_perm"
+  top: "conv16_2_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv16_2_mbox_conf"
+  type: "Convolution"
+  bottom: "conv16_2"
+  top: "conv16_2_mbox_conf"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 126
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv16_2_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv16_2_mbox_conf"
+  top: "conv16_2_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv16_2_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv16_2_mbox_conf_perm"
+  top: "conv16_2_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv16_2_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv16_2"
+  bottom: "data"
+  top: "conv16_2_mbox_priorbox"
+  prior_box_param {
+    min_size: 240.0
+    max_size: 285.0
+    aspect_ratio: 2.0
+    aspect_ratio: 3.0
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    offset: 0.5
+  }
+}
+layer {
+  name: "conv17_2_mbox_loc"
+  type: "Convolution"
+  bottom: "conv17_2"
+  top: "conv17_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
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv17_2_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv17_2_mbox_loc"
+  top: "conv17_2_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv17_2_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv17_2_mbox_loc_perm"
+  top: "conv17_2_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv17_2_mbox_conf"
+  type: "Convolution"
+  bottom: "conv17_2"
+  top: "conv17_2_mbox_conf"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 126
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv17_2_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv17_2_mbox_conf"
+  top: "conv17_2_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv17_2_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv17_2_mbox_conf_perm"
+  top: "conv17_2_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv17_2_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv17_2"
+  bottom: "data"
+  top: "conv17_2_mbox_priorbox"
+  prior_box_param {
+    min_size: 285.0
+    max_size: 300.0
+    aspect_ratio: 2.0
+    aspect_ratio: 3.0
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    offset: 0.5
+  }
+}
+layer {
+  name: "mbox_loc"
+  type: "Concat"
+  bottom: "conv11_mbox_loc_flat"
+  bottom: "conv13_mbox_loc_flat"
+  bottom: "conv14_2_mbox_loc_flat"
+  bottom: "conv15_2_mbox_loc_flat"
+  bottom: "conv16_2_mbox_loc_flat"
+  bottom: "conv17_2_mbox_loc_flat"
+  top: "mbox_loc"
+  concat_param {
+    axis: 1
+  }
+}
+layer {
+  name: "mbox_conf"
+  type: "Concat"
+  bottom: "conv11_mbox_conf_flat"
+  bottom: "conv13_mbox_conf_flat"
+  bottom: "conv14_2_mbox_conf_flat"
+  bottom: "conv15_2_mbox_conf_flat"
+  bottom: "conv16_2_mbox_conf_flat"
+  bottom: "conv17_2_mbox_conf_flat"
+  top: "mbox_conf"
+  concat_param {
+    axis: 1
+  }
+}
+layer {
+  name: "mbox_priorbox"
+  type: "Concat"
+  bottom: "conv11_mbox_priorbox"
+  bottom: "conv13_mbox_priorbox"
+  bottom: "conv14_2_mbox_priorbox"
+  bottom: "conv15_2_mbox_priorbox"
+  bottom: "conv16_2_mbox_priorbox"
+  bottom: "conv17_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"
+  include {
+    phase: TEST
+  }
+  detection_output_param {
+    num_classes: 21
+    share_location: true
+    background_label_id: 0
+    nms_param {
+      nms_threshold: 0.45
+      top_k: 100
+    }
+    code_type: CENTER_SIZE
+    keep_top_k: 100
+    confidence_threshold: 0.25
+  }
+}

app.py

@@ -0,0 +1,108 @@
+import gradio as gr
+import cv2
+import numpy as np
+from gradio_webrtc import WebRTC
+from pathlib import Path
+
+CLASSES = [
+    "background",
+    "aeroplane",
+    "bicycle",
+    "bird",
+    "boat",
+    "bottle",
+    "bus",
+    "car",
+    "cat",
+    "chair",
+    "cow",
+    "diningtable",
+    "dog",
+    "horse",
+    "motorbike",
+    "person",
+    "pottedplant",
+    "sheep",
+    "sofa",
+    "train",
+    "tvmonitor",
+]
+COLORS = np.random.uniform(0, 255, size=(len(CLASSES), 3))
+
+directory = Path(__file__).parent
+
+MODEL = str((directory / "MobileNetSSD_deploy.caffemodel").resolve())
+PROTOTXT = str((directory / "MobileNetSSD_deploy.prototxt.txt").resolve())
+net = cv2.dnn.readNetFromCaffe(PROTOTXT, MODEL)
+
+
+def detection(image, conf_threshold=0.3):
+
+    blob = cv2.dnn.blobFromImage(
+        cv2.resize(image, (300, 300)), 0.007843, (300, 300), 127.5
+    )
+    net.setInput(blob)
+
+    detections = net.forward()
+    image = cv2.resize(image, (500, 500))
+    (h, w) = image.shape[:2]
+    labels = []
+    for i in np.arange(0, detections.shape[2]):
+        confidence = detections[0, 0, i, 2]
+
+        if confidence > conf_threshold:
+            # extract the index of the class label from the `detections`,
+            # then compute the (x, y)-coordinates of the bounding box for
+            # the object
+            idx = int(detections[0, 0, i, 1])
+            box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
+            (startX, startY, endX, endY) = box.astype("int")
+
+            # display the prediction
+            label = f"{CLASSES[idx]}: {round(confidence * 100, 2)}%"
+            labels.append(label)
+            cv2.rectangle(image, (startX, startY), (endX, endY), COLORS[idx], 2)
+            y = startY - 15 if startY - 15 > 15 else startY + 15
+            cv2.putText(
+                image, label, (startX, y), cv2.FONT_HERSHEY_SIMPLEX, 0.5, COLORS[idx], 2
+            )
+    return image
+
+
+css=""".my-group {max-width: 600px !important; max-height: 600 !important;}
+                      .my-column {display: flex !important; justify-content: center !important; align-items: center !important};"""
+
+
+with gr.Blocks(css=css) as demo:
+    gr.HTML(
+        """
+    <h1 style='text-align: center'>
+    YOLOv10 Webcam Stream
+    </h1>
+    """)
+    gr.HTML(
+        """
+        <h3 style='text-align: center'>
+        <a href='https://arxiv.org/abs/2405.14458' target='_blank'>arXiv</a> | <a href='https://github.com/THU-MIG/yolov10' target='_blank'>github</a>
+        </h3>
+        """)
+    with gr.Column(elem_classes=["my-column"]):
+        with gr.Group(elem_classes=["my-group"]):
+            image = WebRTC(label="Strean")
+            conf_threshold = gr.Slider(
+                label="Confidence Threshold",
+                minimum=0.0,
+                maximum=1.0,
+                step=0.05,
+                value=0.30,
+            )
+        
+        image.webrtc_stream(
+            fn=detection,
+            inputs=[image],
+            stream_every=0.05,
+            time_limit=30
+        )
+
+if __name__ == '__main__':
+    demo.launch()

requirements.txt

@@ -0,0 +1,4 @@
+safetensors==0.4.3
+opencv-python
+https://huggingface.co/datasets/freddyaboulton/bucket/resolve/main/gradio-5.0.0b3-py3-none-any.whl
+https://huggingface.co/datasets/freddyaboulton/bucket/resolve/main/gradio_webrtc-0.0.1-py3-none-any.whl