基于C++代码的模型统一放置在Prj-Linux目录下

Prj-PHP/tests/model/CharacterRecognization.prototxt

@@ -1,123 +0,0 @@
-input: "data"
-input_dim: 1
-input_dim: 1
-input_dim: 30
-input_dim: 14
-layer {
-  name: "conv2d_1"
-  type: "Convolution"
-  bottom: "data"
-  top: "conv2d_1"
-  convolution_param {
-    num_output: 32
-    bias_term: true
-    pad: 0
-    kernel_size: 3
-    stride: 1
-  }
-}
-layer {
-  name: "activation_1"
-  type: "ReLU"
-  bottom: "conv2d_1"
-  top: "activation_1"
-}
-layer {
-  name: "max_pooling2d_1"
-  type: "Pooling"
-  bottom: "activation_1"
-  top: "max_pooling2d_1"
-  pooling_param {
-    pool: MAX
-    kernel_size: 2
-    stride: 2
-    pad: 0
-  }
-}
-layer {
-  name: "conv2d_2"
-  type: "Convolution"
-  bottom: "max_pooling2d_1"
-  top: "conv2d_2"
-  convolution_param {
-    num_output: 64
-    bias_term: true
-    pad: 0
-    kernel_size: 3
-    stride: 1
-  }
-}
-layer {
-  name: "activation_2"
-  type: "ReLU"
-  bottom: "conv2d_2"
-  top: "activation_2"
-}
-layer {
-  name: "max_pooling2d_2"
-  type: "Pooling"
-  bottom: "activation_2"
-  top: "max_pooling2d_2"
-  pooling_param {
-    pool: MAX
-    kernel_size: 2
-    stride: 2
-    pad: 0
-  }
-}
-layer {
-  name: "conv2d_3"
-  type: "Convolution"
-  bottom: "max_pooling2d_2"
-  top: "conv2d_3"
-  convolution_param {
-    num_output: 128
-    bias_term: true
-    pad: 0
-    kernel_size: 2
-    stride: 1
-  }
-}
-layer {
-  name: "activation_3"
-  type: "ReLU"
-  bottom: "conv2d_3"
-  top: "activation_3"
-}
-layer {
-  name: "flatten_1"
-  type: "Flatten"
-  bottom: "activation_3"
-  top: "flatten_1"
-}
-layer {
-  name: "dense_1"
-  type: "InnerProduct"
-  bottom: "flatten_1"
-  top: "dense_1"
-  inner_product_param {
-    num_output: 256
-  }
-}
-layer {
-  name: "relu2"
-  type: "ReLU"
-  bottom: "dense_1"
-  top: "relu2"
-}
-layer {
-  name: "dense2"
-  type: "InnerProduct"
-  bottom: "relu2"
-  top: "dense2"
-  inner_product_param {
-    num_output: 65
-  }
-}
-
-layer {
-  name: "prob"
-  type: "Softmax"
-  bottom: "dense2"
-  top: "prob"
-}

Prj-PHP/tests/model/HorizonalFinemapping.prototxt

@@ -1,95 +0,0 @@
-input: "data"
-input_dim: 1
-input_dim: 3
-input_dim: 16
-input_dim: 66
-layer {
-  name: "conv1"
-  type: "Convolution"
-  bottom: "data"
-  top: "conv1"
-  convolution_param {
-    num_output: 10
-    bias_term: true
-    pad: 0
-    kernel_size: 3
-    stride: 1
-  }
-}
-layer {
-  name: "relu1"
-  type: "ReLU"
-  bottom: "conv1"
-  top: "conv1"
-}
-layer {
-  name: "max_pooling2d_3"
-  type: "Pooling"
-  bottom: "conv1"
-  top: "max_pooling2d_3"
-  pooling_param {
-    pool: MAX
-    kernel_size: 2
-    stride: 2
-    pad: 0
-  }
-}
-layer {
-  name: "conv2"
-  type: "Convolution"
-  bottom: "max_pooling2d_3"
-  top: "conv2"
-  convolution_param {
-    num_output: 16
-    bias_term: true
-    pad: 0
-    kernel_size: 3
-    stride: 1
-  }
-}
-layer {
-  name: "relu2"
-  type: "ReLU"
-  bottom: "conv2"
-  top: "conv2"
-}
-layer {
-  name: "conv3"
-  type: "Convolution"
-  bottom: "conv2"
-  top: "conv3"
-  convolution_param {
-    num_output: 32
-    bias_term: true
-    pad: 0
-    kernel_size: 3
-    stride: 1
-  }
-}
-layer {
-  name: "relu3"
-  type: "ReLU"
-  bottom: "conv3"
-  top: "conv3"
-}
-layer {
-  name: "flatten_2"
-  type: "Flatten"
-  bottom: "conv3"
-  top: "flatten_2"
-}
-layer {
-  name: "dense"
-  type: "InnerProduct"
-  bottom: "flatten_2"
-  top: "dense"
-  inner_product_param {
-    num_output: 2
-  }
-}
-layer {
-  name: "relu4"
-  type: "ReLU"
-  bottom: "dense"
-  top: "dense"
-}

Prj-PHP/tests/model/README.md

@@ -0,0 +1,11 @@
+将/Prj-Linux/lpr/model目录下的
+cascade.xml
+CharacterRecognization.caffemodel
+CharacterRecognization.prototxt
+HorizonalFinemapping.caffemodel
+HorizonalFinemapping.prototxt
+SegmenationFree-Inception.caffemodel
+SegmenationFree-Inception.prototxt
+Segmentation.caffemodel
+Segmentation.prototxt
+放置在该目录

Prj-PHP/tests/model/Segmentation.prototxt

@@ -1,114 +0,0 @@
-input: "data"
-input_dim: 1
-input_dim: 1
-input_dim: 22
-input_dim: 22
-layer {
-  name: "conv2d_12"
-  type: "Convolution"
-  bottom: "data"
-  top: "conv2d_12"
-  convolution_param {
-    num_output: 16
-    bias_term: true
-    pad: 0
-    kernel_size: 3
-    stride: 1
-  }
-}
-layer {
-  name: "activation_18"
-  type: "ReLU"
-  bottom: "conv2d_12"
-  top: "activation_18"
-}
-layer {
-  name: "max_pooling2d_10"
-  type: "Pooling"
-  bottom: "activation_18"
-  top: "max_pooling2d_10"
-  pooling_param {
-    pool: MAX
-    kernel_size: 2
-    stride: 2
-    pad: 0
-  }
-}
-layer {
-  name: "conv2d_13"
-  type: "Convolution"
-  bottom: "max_pooling2d_10"
-  top: "conv2d_13"
-  convolution_param {
-    num_output: 16
-    bias_term: true
-    pad: 0
-    kernel_size: 3
-    stride: 1
-  }
-}
-layer {
-  name: "activation_19"
-  type: "ReLU"
-  bottom: "conv2d_13"
-  top: "activation_19"
-}
-layer {
-  name: "max_pooling2d_11"
-  type: "Pooling"
-  bottom: "activation_19"
-  top: "max_pooling2d_11"
-  pooling_param {
-    pool: MAX
-    kernel_size: 2
-    stride: 2
-    pad: 0
-  }
-}
-layer {
-  name: "flatten_6"
-  type: "Flatten"
-  bottom: "max_pooling2d_11"
-  top: "flatten_6"
-}
-layer {
-  name: "dense_9"
-  type: "InnerProduct"
-  bottom: "flatten_6"
-  top: "dense_9"
-  inner_product_param {
-    num_output: 256
-  }
-}
-layer {
-  name: "dropout_9"
-  type: "Dropout"
-  bottom: "dense_9"
-  top: "dropout_9"
-  dropout_param {
-    dropout_ratio: 0.5
-  }
-}
-layer {
-  name: "activation_20"
-  type: "ReLU"
-  bottom: "dropout_9"
-  top: "activation_20"
-}
-layer {
-  name: "dense_10"
-  type: "InnerProduct"
-  bottom: "activation_20"
-  top: "dense_10"
-  inner_product_param {
-    num_output: 3
-  }
-}
-
-
-  layer {
-  name: "prob"
-  type: "Softmax"
-  bottom: "dense_10"
-  top: "prob"
-}

Prj-PHP/tests/model/SegmentationFree.prototxt

@@ -1,318 +0,0 @@
-input: "data"
-input_dim: 1
-input_dim: 3
-input_dim: 160
-input_dim: 40
-layer {
-  name: "conv0"
-  type: "Convolution"
-  bottom: "data"
-  top: "conv0"
-  convolution_param {
-    num_output: 32
-    bias_term: true
-    pad_h: 1
-    pad_w: 1
-    kernel_h: 3
-    kernel_w: 3
-    stride_h: 1
-    stride_w: 1
-  }
-}
-layer {
-  name: "bn0"
-  type: "BatchNorm"
-  bottom: "conv0"
-  top: "bn0"
-  batch_norm_param {
-    moving_average_fraction: 0.99
-    eps: 0.001
-  }
-}
-layer {
-  name: "bn0_scale"
-  type: "Scale"
-  bottom: "bn0"
-  top: "bn0"
-  scale_param {
-    bias_term: true
-  }
-}
-layer {
-  name: "relu0"
-  type: "ReLU"
-  bottom: "bn0"
-  top: "bn0"
-}
-layer {
-  name: "pool0"
-  type: "Pooling"
-  bottom: "bn0"
-  top: "pool0"
-  pooling_param {
-    pool: MAX
-    kernel_h: 2
-    kernel_w: 2
-    stride_h: 2
-    stride_w: 2
-    pad_h: 0
-    pad_w: 0
-  }
-}
-layer {
-  name: "conv1"
-  type: "Convolution"
-  bottom: "pool0"
-  top: "conv1"
-  convolution_param {
-    num_output: 64
-    bias_term: true
-    pad_h: 1
-    pad_w: 1
-    kernel_h: 3
-    kernel_w: 3
-    stride_h: 1
-    stride_w: 1
-  }
-}
-layer {
-  name: "bn1"
-  type: "BatchNorm"
-  bottom: "conv1"
-  top: "bn1"
-  batch_norm_param {
-    moving_average_fraction: 0.99
-    eps: 0.001
-  }
-}
-layer {
-  name: "bn1_scale"
-  type: "Scale"
-  bottom: "bn1"
-  top: "bn1"
-  scale_param {
-    bias_term: true
-  }
-}
-layer {
-  name: "relu1"
-  type: "ReLU"
-  bottom: "bn1"
-  top: "bn1"
-}
-layer {
-  name: "pool1"
-  type: "Pooling"
-  bottom: "bn1"
-  top: "pool1"
-  pooling_param {
-    pool: MAX
-    kernel_h: 2
-    kernel_w: 2
-    stride_h: 2
-    stride_w: 2
-    pad_h: 0
-    pad_w: 0
-  }
-}
-layer {
-  name: "conv2"
-  type: "Convolution"
-  bottom: "pool1"
-  top: "conv2"
-  convolution_param {
-    num_output: 128
-    bias_term: true
-    pad_h: 1
-    pad_w: 1
-    kernel_h: 3
-    kernel_w: 3
-    stride_h: 1
-    stride_w: 1
-  }
-}
-layer {
-  name: "bn2"
-  type: "BatchNorm"
-  bottom: "conv2"
-  top: "bn2"
-  batch_norm_param {
-    moving_average_fraction: 0.99
-    eps: 0.001
-  }
-}
-layer {
-  name: "bn2_scale"
-  type: "Scale"
-  bottom: "bn2"
-  top: "bn2"
-  scale_param {
-    bias_term: true
-  }
-}
-layer {
-  name: "relu2"
-  type: "ReLU"
-  bottom: "bn2"
-  top: "bn2"
-}
-layer {
-  name: "pool2"
-  type: "Pooling"
-  bottom: "bn2"
-  top: "pool2"
-  pooling_param {
-    pool: MAX
-    kernel_h: 2
-    kernel_w: 2
-    stride_h: 2
-    stride_w: 2
-    pad_h: 0
-    pad_w: 0
-  }
-}
-layer {
-  name: "conv_512_15"
-  type: "Convolution"
-  bottom: "pool2"
-  top: "conv_512_15"
-  convolution_param {
-    num_output: 512
-    bias_term: true
-    pad_h: 0
-    pad_w: 0
-    kernel_h: 1
-    kernel_w: 5
-    stride_h: 1
-    stride_w: 1
-  }
-}
-layer {
-  name: "batch_normalization_1"
-  type: "BatchNorm"
-  bottom: "conv_512_15"
-  top: "batch_normalization_1"
-  batch_norm_param {
-    moving_average_fraction: 0.99
-    eps: 0.001
-  }
-}
-layer {
-  name: "batch_normalization_1_scale"
-  type: "Scale"
-  bottom: "batch_normalization_1"
-  top: "batch_normalization_1"
-  scale_param {
-    bias_term: true
-  }
-}
-layer {
-  name: "activation_1"
-  type: "ReLU"
-  bottom: "batch_normalization_1"
-  top: "batch_normalization_1"
-}
-layer {
-  name: "conv_512_51"
-  type: "Convolution"
-  bottom: "batch_normalization_1"
-  top: "conv_512_51"
-  convolution_param {
-    num_output: 512
-    bias_term: true
-    pad_h: 0
-    pad_w: 0
-    kernel_h: 5
-    kernel_w: 1
-    stride_h: 1
-    stride_w: 1
-  }
-}
-layer {
-  name: "batch_normalization_2"
-  type: "BatchNorm"
-  bottom: "conv_512_51"
-  top: "batch_normalization_2"
-  batch_norm_param {
-    moving_average_fraction: 0.99
-    eps: 0.001
-  }
-}
-layer {
-  name: "batch_normalization_2_scale"
-  type: "Scale"
-  bottom: "batch_normalization_2"
-  top: "batch_normalization_2"
-  scale_param {
-    bias_term: true
-  }
-}
-layer {
-  name: "activation_2"
-  type: "ReLU"
-  bottom: "batch_normalization_2"
-  top: "batch_normalization_2"
-}
-layer {
-  name: "conv_1024_11"
-  type: "Convolution"
-  bottom: "batch_normalization_2"
-  top: "conv_1024_11"
-  convolution_param {
-    num_output: 1024
-    bias_term: true
-    pad_h: 0
-    pad_w: 0
-    kernel_h: 1
-    kernel_w: 1
-    stride_h: 1
-    stride_w: 1
-  }
-}
-layer {
-  name: "batch_normalization_3"
-  type: "BatchNorm"
-  bottom: "conv_1024_11"
-  top: "batch_normalization_3"
-  batch_norm_param {
-    moving_average_fraction: 0.99
-    eps: 0.001
-  }
-}
-layer {
-  name: "batch_normalization_3_scale"
-  type: "Scale"
-  bottom: "batch_normalization_3"
-  top: "batch_normalization_3"
-  scale_param {
-    bias_term: true
-  }
-}
-layer {
-  name: "activation_3"
-  type: "ReLU"
-  bottom: "batch_normalization_3"
-  top: "batch_normalization_3"
-}
-layer {
-  name: "conv_class_11"
-  type: "Convolution"
-  bottom: "batch_normalization_3"
-  top: "conv_class_11"
-  convolution_param {
-    num_output: 84
-    bias_term: true
-    pad_h: 0
-    pad_w: 0
-    kernel_h: 1
-    kernel_w: 1
-    stride_h: 1
-    stride_w: 1
-  }
-}
-layer {
-  name: "prob"
-  type: "Softmax"
-  bottom: "conv_class_11"
-  top: "prob"
-}

Prj-Win/lpr/model/CharacterRecognization.prototxt

@@ -1,123 +0,0 @@
-input: "data"
-input_dim: 1
-input_dim: 1
-input_dim: 30
-input_dim: 14
-layer {
-  name: "conv2d_1"
-  type: "Convolution"
-  bottom: "data"
-  top: "conv2d_1"
-  convolution_param {
-    num_output: 32
-    bias_term: true
-    pad: 0
-    kernel_size: 3
-    stride: 1
-  }
-}
-layer {
-  name: "activation_1"
-  type: "ReLU"
-  bottom: "conv2d_1"
-  top: "activation_1"
-}
-layer {
-  name: "max_pooling2d_1"
-  type: "Pooling"
-  bottom: "activation_1"
-  top: "max_pooling2d_1"
-  pooling_param {
-    pool: MAX
-    kernel_size: 2
-    stride: 2
-    pad: 0
-  }
-}
-layer {
-  name: "conv2d_2"
-  type: "Convolution"
-  bottom: "max_pooling2d_1"
-  top: "conv2d_2"
-  convolution_param {
-    num_output: 64
-    bias_term: true
-    pad: 0
-    kernel_size: 3
-    stride: 1
-  }
-}
-layer {
-  name: "activation_2"
-  type: "ReLU"
-  bottom: "conv2d_2"
-  top: "activation_2"
-}
-layer {
-  name: "max_pooling2d_2"
-  type: "Pooling"
-  bottom: "activation_2"
-  top: "max_pooling2d_2"
-  pooling_param {
-    pool: MAX
-    kernel_size: 2
-    stride: 2
-    pad: 0
-  }
-}
-layer {
-  name: "conv2d_3"
-  type: "Convolution"
-  bottom: "max_pooling2d_2"
-  top: "conv2d_3"
-  convolution_param {
-    num_output: 128
-    bias_term: true
-    pad: 0
-    kernel_size: 2
-    stride: 1
-  }
-}
-layer {
-  name: "activation_3"
-  type: "ReLU"
-  bottom: "conv2d_3"
-  top: "activation_3"
-}
-layer {
-  name: "flatten_1"
-  type: "Flatten"
-  bottom: "activation_3"
-  top: "flatten_1"
-}
-layer {
-  name: "dense_1"
-  type: "InnerProduct"
-  bottom: "flatten_1"
-  top: "dense_1"
-  inner_product_param {
-    num_output: 256
-  }
-}
-layer {
-  name: "relu2"
-  type: "ReLU"
-  bottom: "dense_1"
-  top: "relu2"
-}
-layer {
-  name: "dense2"
-  type: "InnerProduct"
-  bottom: "relu2"
-  top: "dense2"
-  inner_product_param {
-    num_output: 65
-  }
-}
-
-layer {
-  name: "prob"
-  type: "Softmax"
-  bottom: "dense2"
-  top: "prob"
-}

Prj-Win/lpr/model/HorizonalFinemapping.prototxt

@@ -1,95 +0,0 @@
-input: "data"
-input_dim: 1
-input_dim: 3
-input_dim: 16
-input_dim: 66
-layer {
-  name: "conv1"
-  type: "Convolution"
-  bottom: "data"
-  top: "conv1"
-  convolution_param {
-    num_output: 10
-    bias_term: true
-    pad: 0
-    kernel_size: 3
-    stride: 1
-  }
-}
-layer {
-  name: "relu1"
-  type: "ReLU"
-  bottom: "conv1"
-  top: "conv1"
-}
-layer {
-  name: "max_pooling2d_3"
-  type: "Pooling"
-  bottom: "conv1"
-  top: "max_pooling2d_3"
-  pooling_param {
-    pool: MAX
-    kernel_size: 2
-    stride: 2
-    pad: 0
-  }
-}
-layer {
-  name: "conv2"
-  type: "Convolution"
-  bottom: "max_pooling2d_3"
-  top: "conv2"
-  convolution_param {
-    num_output: 16
-    bias_term: true
-    pad: 0
-    kernel_size: 3
-    stride: 1
-  }
-}
-layer {
-  name: "relu2"
-  type: "ReLU"
-  bottom: "conv2"
-  top: "conv2"
-}
-layer {
-  name: "conv3"
-  type: "Convolution"
-  bottom: "conv2"
-  top: "conv3"
-  convolution_param {
-    num_output: 32
-    bias_term: true
-    pad: 0
-    kernel_size: 3
-    stride: 1
-  }
-}
-layer {
-  name: "relu3"
-  type: "ReLU"
-  bottom: "conv3"
-  top: "conv3"
-}
-layer {
-  name: "flatten_2"
-  type: "Flatten"
-  bottom: "conv3"
-  top: "flatten_2"
-}
-layer {
-  name: "dense"
-  type: "InnerProduct"
-  bottom: "flatten_2"
-  top: "dense"
-  inner_product_param {
-    num_output: 2
-  }
-}
-layer {
-  name: "relu4"
-  type: "ReLU"
-  bottom: "dense"
-  top: "dense"
-}

Prj-Win/lpr/model/README.md

@@ -0,0 +1,9 @@
+将/Prj-Linux/lpr/model目录下的
+cascade.xml
+CharacterRecognization.caffemodel
+CharacterRecognization.prototxt
+HorizonalFinemapping.caffemodel
+HorizonalFinemapping.prototxt
+Segmentation.caffemodel
+Segmentation.prototxt
+放置在该目录

Prj-Win/lpr/model/Segmentation.prototxt

@@ -1,114 +0,0 @@
-input: "data"
-input_dim: 1
-input_dim: 1
-input_dim: 22
-input_dim: 22
-layer {
-  name: "conv2d_12"
-  type: "Convolution"
-  bottom: "data"
-  top: "conv2d_12"
-  convolution_param {
-    num_output: 16
-    bias_term: true
-    pad: 0
-    kernel_size: 3
-    stride: 1
-  }
-}
-layer {
-  name: "activation_18"
-  type: "ReLU"
-  bottom: "conv2d_12"
-  top: "activation_18"
-}
-layer {
-  name: "max_pooling2d_10"
-  type: "Pooling"
-  bottom: "activation_18"
-  top: "max_pooling2d_10"
-  pooling_param {
-    pool: MAX
-    kernel_size: 2
-    stride: 2
-    pad: 0
-  }
-}
-layer {
-  name: "conv2d_13"
-  type: "Convolution"
-  bottom: "max_pooling2d_10"
-  top: "conv2d_13"
-  convolution_param {
-    num_output: 16
-    bias_term: true
-    pad: 0
-    kernel_size: 3
-    stride: 1
-  }
-}
-layer {
-  name: "activation_19"
-  type: "ReLU"
-  bottom: "conv2d_13"
-  top: "activation_19"
-}
-layer {
-  name: "max_pooling2d_11"
-  type: "Pooling"
-  bottom: "activation_19"
-  top: "max_pooling2d_11"
-  pooling_param {
-    pool: MAX
-    kernel_size: 2
-    stride: 2
-    pad: 0
-  }
-}
-layer {
-  name: "flatten_6"
-  type: "Flatten"
-  bottom: "max_pooling2d_11"
-  top: "flatten_6"
-}
-layer {
-  name: "dense_9"
-  type: "InnerProduct"
-  bottom: "flatten_6"
-  top: "dense_9"
-  inner_product_param {
-    num_output: 256
-  }
-}
-layer {
-  name: "dropout_9"
-  type: "Dropout"
-  bottom: "dense_9"
-  top: "dropout_9"
-  dropout_param {
-    dropout_ratio: 0.5
-  }
-}
-layer {
-  name: "activation_20"
-  type: "ReLU"
-  bottom: "dropout_9"
-  top: "activation_20"
-}
-layer {
-  name: "dense_10"
-  type: "InnerProduct"
-  bottom: "activation_20"
-  top: "dense_10"
-  inner_product_param {
-    num_output: 3
-  }
-}
-
-
-  layer {
-  name: "prob"
-  type: "Softmax"
-  bottom: "dense_10"
-  top: "prob"
-}