when using mobilenet as it's backbone, why doesn't the faster rcnn work ？

[zjz5250]

when i try to train the faster rcnn model with mobilenetv1 as it's backbone, i found the rpn can find anchor_target correctly，i saved the anchor target imgs， but the rcnn can not classify the object at all， every sample was recognized as background。 who can tell me why？ appreciate！ the prototxt as follows：

name: "VGG_ILSVRC_16_layers" layer { name: 'input-data' type: 'Python' top: 'data' top: 'im_info' top: 'gt_boxes' python_param { module: 'roi_data_layer.layer' layer: 'RoIDataLayer' param_str: "'num_classes': 4" } }

layer { name: "conv1" type: "Convolution" bottom: "data" top: "conv1" param { lr_mult: 1 decay_mult: 1 } convolution_param { num_output: 32 bias_term: false pad: 1 kernel_size: 3 stride: 2 weight_filler { type: "msra" } } } layer { name: "conv1/bn" type: "BatchNorm" bottom: "conv1" top: "conv1" param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } batch_norm_param { use_global_stats: false eps: 1e-5 } } layer { name: "conv1/scale" type: "Scale" bottom: "conv1" top: "conv1" param { lr_mult: 1 decay_mult: 0 } param { lr_mult: 1 decay_mult: 0 } scale_param { filler { value: 1 } bias_term: true bias_filler { value: 0 } } } layer { name: "relu1" type: "ReLU" bottom: "conv1" top: "conv1" } layer { name: "conv2_1/dw" type: "Convolution" bottom: "conv1" top: "conv2_1/dw" param { lr_mult: 1 decay_mult: 1 } convolution_param { num_output: 32 bias_term: false pad: 1 kernel_size: 3 group: 32 engine: CAFFE stride: 1 weight_filler { type: "msra" } } } layer { name: "conv2_1/dw/bn" type: "BatchNorm" bottom: "conv2_1/dw" top: "conv2_1/dw" param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } batch_norm_param { use_global_stats: false eps: 1e-5 } } layer { name: "conv2_1/dw/scale" type: "Scale" bottom: "conv2_1/dw" top: "conv2_1/dw" param { lr_mult: 1 decay_mult: 0 } param { lr_mult: 1 decay_mult: 0 } scale_param { filler { value: 1 } bias_term: true bias_filler { value: 0 } } } layer { name: "relu2_1/dw" type: "ReLU" bottom: "conv2_1/dw" top: "conv2_1/dw" } layer { name: "conv2_1/sep" type: "Convolution" bottom: "conv2_1/dw" top: "conv2_1/sep" param { lr_mult: 1 decay_mult: 1 } convolution_param { num_output: 64 bias_term: false pad: 0 kernel_size: 1 stride: 1 weight_filler { type: "msra" } } } layer { name: "conv2_1/sep/bn" type: "BatchNorm" bottom: "conv2_1/sep" top: "conv2_1/sep" param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } batch_norm_param { use_global_stats: false eps: 1e-5 } } layer { name: "conv2_1/sep/scale" type: "Scale" bottom: "conv2_1/sep" top: "conv2_1/sep" param { lr_mult: 1 decay_mult: 0 } param { lr_mult: 1 decay_mult: 0 } scale_param { filler { value: 1 } bias_term: true bias_filler { value: 0 } } } layer { name: "relu2_1/sep" type: "ReLU" bottom: "conv2_1/sep" top: "conv2_1/sep" } layer { name: "conv2_2/dw" type: "Convolution" bottom: "conv2_1/sep" top: "conv2_2/dw" param { lr_mult: 1 decay_mult: 1 } convolution_param { num_output: 64 bias_term: false pad: 1 kernel_size: 3 group: 64 engine: CAFFE stride: 2 weight_filler { type: "msra" } } } layer { name: "conv2_2/dw/bn" type: "BatchNorm" bottom: "conv2_2/dw" top: "conv2_2/dw" param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } batch_norm_param { use_global_stats: false eps: 1e-5 } } layer { name: "conv2_2/dw/scale" type: "Scale" bottom: "conv2_2/dw" top: "conv2_2/dw" param { lr_mult: 1 decay_mult: 0 } param { lr_mult: 1 decay_mult: 0 } scale_param { filler { value: 1 } bias_term: true bias_filler { value: 0 } } } layer { name: "relu2_2/dw" type: "ReLU" bottom: "conv2_2/dw" top: "conv2_2/dw" } layer { name: "conv2_2/sep" type: "Convolution" bottom: "conv2_2/dw" top: "conv2_2/sep" param { lr_mult: 1 decay_mult: 1 } convolution_param { num_output: 128 bias_term: false pad: 0 kernel_size: 1 stride: 1 weight_filler { type: "msra" } } } layer { name: "conv2_2/sep/bn" type: "BatchNorm" bottom: "conv2_2/sep" top: "conv2_2/sep" param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } batch_norm_param { use_global_stats: false eps: 1e-5 } } layer { name: "conv2_2/sep/scale" type: "Scale" bottom: "conv2_2/sep" top: "conv2_2/sep" param { lr_mult: 1 decay_mult: 0 } param { lr_mult: 1 decay_mult: 0 } scale_param { filler { value: 1 } bias_term: true bias_filler { value: 0 } } } layer { name: "relu2_2/sep" type: "ReLU" bottom: "conv2_2/sep" top: "conv2_2/sep" } layer { name: "conv3_1/dw" type: "Convolution" bottom: "conv2_2/sep" top: "conv3_1/dw" param { lr_mult: 1 decay_mult: 1 } convolution_param { num_output: 128 bias_term: false pad: 1 kernel_size: 3 group: 128 engine: CAFFE stride: 1 weight_filler { type: "msra" } } } layer { name: "conv3_1/dw/bn" type: "BatchNorm" bottom: "conv3_1/dw" top: "conv3_1/dw" param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } batch_norm_param { use_global_stats: false eps: 1e-5 } } layer { name: "conv3_1/dw/scale" type: "Scale" bottom: "conv3_1/dw" top: "conv3_1/dw" param { lr_mult: 1 decay_mult: 0 } param { lr_mult: 1 decay_mult: 0 } scale_param { filler { value: 1 } bias_term: true bias_filler { value: 0 } } } layer { name: "relu3_1/dw" type: "ReLU" bottom: "conv3_1/dw" top: "conv3_1/dw" } layer { name: "conv3_1/sep" type: "Convolution" bottom: "conv3_1/dw" top: "conv3_1/sep" param { lr_mult: 1 decay_mult: 1 } convolution_param { num_output: 128 bias_term: false pad: 0 kernel_size: 1 stride: 1 weight_filler { type: "msra" } } } layer { name: "conv3_1/sep/bn" type: "BatchNorm" bottom: "conv3_1/sep" top: "conv3_1/sep" param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } batch_norm_param { use_global_stats: false eps: 1e-5 } } layer { name: "conv3_1/sep/scale" type: "Scale" bottom: "conv3_1/sep" top: "conv3_1/sep" param { lr_mult: 1 decay_mult: 0 } param { lr_mult: 1 decay_mult: 0 } scale_param { filler { value: 1 } bias_term: true bias_filler { value: 0 } } } layer { name: "relu3_1/sep" type: "ReLU" bottom: "conv3_1/sep" top: "conv3_1/sep" } layer { name: "conv3_2/dw" type: "Convolution" bottom: "conv3_1/sep" top: "conv3_2/dw" param { lr_mult: 1 decay_mult: 1 } convolution_param { num_output: 128 bias_term: false pad: 1 kernel_size: 3 group: 128 engine: CAFFE stride: 2 weight_filler { type: "msra" } } } layer { name: "conv3_2/dw/bn" type: "BatchNorm" bottom: "conv3_2/dw" top: "conv3_2/dw" param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } batch_norm_param { use_global_stats: false eps: 1e-5 } } layer { name: "conv3_2/dw/scale" type: "Scale" bottom: "conv3_2/dw" top: "conv3_2/dw" param { lr_mult: 1 decay_mult: 0 } param { lr_mult: 1 decay_mult: 0 } scale_param { filler { value: 1 } bias_term: true bias_filler { value: 0 } } } layer { name: "relu3_2/dw" type: "ReLU" bottom: "conv3_2/dw" top: "conv3_2/dw" } layer { name: "conv3_2/sep" type: "Convolution" bottom: "conv3_2/dw" top: "conv3_2/sep" param { lr_mult: 1 decay_mult: 1 } convolution_param { num_output: 256 bias_term: false pad: 0 kernel_size: 1 stride: 1 weight_filler { type: "msra" } } } layer { name: "conv3_2/sep/bn" type: "BatchNorm" bottom: "conv3_2/sep" top: "conv3_2/sep" param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } batch_norm_param { use_global_stats: false eps: 1e-5 } } layer { name: "conv3_2/sep/scale" type: "Scale" bottom: "conv3_2/sep" top: "conv3_2/sep" param { lr_mult: 1 decay_mult: 0 } param { lr_mult: 1 decay_mult: 0 } scale_param { filler { value: 1 } bias_term: true bias_filler { value: 0 } } } layer { name: "relu3_2/sep" type: "ReLU" bottom: "conv3_2/sep" top: "conv3_2/sep" } layer { name: "conv4_1/dw" type: "Convolution" bottom: "conv3_2/sep" top: "conv4_1/dw" param { lr_mult: 1 decay_mult: 1 } convolution_param { num_output: 256 bias_term: false pad: 1 kernel_size: 3 group: 256 engine: CAFFE stride: 1 weight_filler { type: "msra" } } } layer { name: "conv4_1/dw/bn" type: "BatchNorm" bottom: "conv4_1/dw" top: "conv4_1/dw" param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } batch_norm_param { use_global_stats: false eps: 1e-5 } } layer { name: "conv4_1/dw/scale" type: "Scale" bottom: "conv4_1/dw" top: "conv4_1/dw" param { lr_mult: 1 decay_mult: 0 } param { lr_mult: 1 decay_mult: 0 } scale_param { filler { value: 1 } bias_term: true bias_filler { value: 0 } } } layer { name: "relu4_1/dw" type: "ReLU" bottom: "conv4_1/dw" top: "conv4_1/dw" } layer { name: "conv4_1/sep" type: "Convolution" bottom: "conv4_1/dw" top: "conv4_1/sep" param { lr_mult: 1 decay_mult: 1 } convolution_param { num_output: 256 bias_term: false pad: 0 kernel_size: 1 stride: 1 weight_filler { type: "msra" } } } layer { name: "conv4_1/sep/bn" type: "BatchNorm" bottom: "conv4_1/sep" top: "conv4_1/sep" param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } batch_norm_param { use_global_stats: false eps: 1e-5 } } layer { name: "conv4_1/sep/scale" type: "Scale" bottom: "conv4_1/sep" top: "conv4_1/sep" param { lr_mult: 1 decay_mult: 0 } param { lr_mult: 1 decay_mult: 0 } scale_param { filler { value: 1 } bias_term: true bias_filler { value: 0 } } } layer { name: "relu4_1/sep" type: "ReLU" bottom: "conv4_1/sep" top: "conv4_1/sep" } layer { name: "conv4_2/dw" type: "Convolution" bottom: "conv4_1/sep" top: "conv4_2/dw" param { lr_mult: 1 decay_mult: 1 } convolution_param { num_output: 256 bias_term: false pad: 1 kernel_size: 3 group: 256 engine: CAFFE stride: 2 weight_filler { type: "msra" } } } layer { name: "conv4_2/dw/bn" type: "BatchNorm" bottom: "conv4_2/dw" top: "conv4_2/dw" param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } batch_norm_param { use_global_stats: false eps: 1e-5 } } layer { name: "conv4_2/dw/scale" type: "Scale" bottom: "conv4_2/dw" top: "conv4_2/dw" param { lr_mult: 1 decay_mult: 0 } param { lr_mult: 1 decay_mult: 0 } scale_param { filler { value: 1 } bias_term: true bias_filler { value: 0 } } } layer { name: "relu4_2/dw" type: "ReLU" bottom: "conv4_2/dw" top: "conv4_2/dw" } layer { name: "conv4_2/sep" type: "Convolution" bottom: "conv4_2/dw" top: "conv4_2/sep" param { lr_mult: 1 decay_mult: 1 } convolution_param { num_output: 512 bias_term: false pad: 0 kernel_size: 1 stride: 1 weight_filler { type: "msra" } } } layer { name: "conv4_2/sep/bn" type: "BatchNorm" bottom: "conv4_2/sep" top: "conv4_2/sep" param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } batch_norm_param { use_global_stats: false eps: 1e-5 } } layer { name: "conv4_2/sep/scale" type: "Scale" bottom: "conv4_2/sep" top: "conv4_2/sep" param { lr_mult: 1 decay_mult: 0 } param { lr_mult: 1 decay_mult: 0 } scale_param { filler { value: 1 } bias_term: true bias_filler { value: 0 } } } layer { name: "relu4_2/sep" type: "ReLU" bottom: "conv4_2/sep" top: "conv4_2/sep" } layer { name: "conv5_1/dw" type: "Convolution" bottom: "conv4_2/sep" top: "conv5_1/dw" param { lr_mult: 1 decay_mult: 1 } convolution_param { num_output: 512 bias_term: false pad: 1 kernel_size: 3 group: 512 engine: CAFFE stride: 1 weight_filler { type: "msra" } } } layer { name: "conv5_1/dw/bn" type: "BatchNorm" bottom: "conv5_1/dw" top: "conv5_1/dw" param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } batch_norm_param { use_global_stats: false eps: 1e-5 } } layer { name: "conv5_1/dw/scale" type: "Scale" bottom: "conv5_1/dw" top: "conv5_1/dw" param { lr_mult: 1 decay_mult: 0 } param { lr_mult: 1 decay_mult: 0 } scale_param { filler { value: 1 } bias_term: true bias_filler { value: 0 } } } layer { name: "relu5_1/dw" type: "ReLU" bottom: "conv5_1/dw" top: "conv5_1/dw" } layer { name: "conv5_1/sep" type: "Convolution" bottom: "conv5_1/dw" top: "conv5_1/sep" param { lr_mult: 1 decay_mult: 1 } convolution_param { num_output: 512 bias_term: false pad: 0 kernel_size: 1 stride: 1 weight_filler { type: "msra" } } } layer { name: "conv5_1/sep/bn" type: "BatchNorm" bottom: "conv5_1/sep" top: "conv5_1/sep" param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } batch_norm_param { use_global_stats: false eps: 1e-5 } } layer { name: "conv5_1/sep/scale" type: "Scale" bottom: "conv5_1/sep" top: "conv5_1/sep" param { lr_mult: 1 decay_mult: 0 } param { lr_mult: 1 decay_mult: 0 } scale_param { filler { value: 1 } bias_term: true bias_filler { value: 0 } } } layer { name: "relu5_1/sep" type: "ReLU" bottom: "conv5_1/sep" top: "conv5_1/sep" } layer { name: "conv5_2/dw" type: "Convolution" bottom: "conv5_1/sep" top: "conv5_2/dw" param { lr_mult: 1 decay_mult: 1 } convolution_param { num_output: 512 bias_term: false pad: 1 kernel_size: 3 group: 512 engine: CAFFE stride: 1 weight_filler { type: "msra" } } } layer { name: "conv5_2/dw/bn" type: "BatchNorm" bottom: "conv5_2/dw" top: "conv5_2/dw" param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } batch_norm_param { use_global_stats: false eps: 1e-5 } } layer { name: "conv5_2/dw/scale" type: "Scale" bottom: "conv5_2/dw" top: "conv5_2/dw" param { lr_mult: 1 decay_mult: 0 } param { lr_mult: 1 decay_mult: 0 } scale_param { filler { value: 1 } bias_term: true bias_filler { value: 0 } } } layer { name: "relu5_2/dw" type: "ReLU" bottom: "conv5_2/dw" top: "conv5_2/dw" } layer { name: "conv5_2/sep" type: "Convolution" bottom: "conv5_2/dw" top: "conv5_2/sep" param { lr_mult: 1 decay_mult: 1 } convolution_param { num_output: 512 bias_term: false pad: 0 kernel_size: 1 stride: 1 weight_filler { type: "msra" } } } layer { name: "conv5_2/sep/bn" type: "BatchNorm" bottom: "conv5_2/sep" top: "conv5_2/sep" param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } batch_norm_param { use_global_stats: false eps: 1e-5 } } layer { name: "conv5_2/sep/scale" type: "Scale" bottom: "conv5_2/sep" top: "conv5_2/sep" param { lr_mult: 1 decay_mult: 0 } param { lr_mult: 1 decay_mult: 0 } scale_param { filler { value: 1 } bias_term: true bias_filler { value: 0 } } } layer { name: "relu5_2/sep" type: "ReLU" bottom: "conv5_2/sep" top: "conv5_2/sep" } layer { name: "conv5_3/dw" type: "Convolution" bottom: "conv5_2/sep" top: "conv5_3/dw" param { lr_mult: 1 decay_mult: 1 } convolution_param { num_output: 512 bias_term: false pad: 1 kernel_size: 3 group: 512 engine: CAFFE stride: 1 weight_filler { type: "msra" } } } layer { name: "conv5_3/dw/bn" type: "BatchNorm" bottom: "conv5_3/dw" top: "conv5_3/dw" param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } batch_norm_param { use_global_stats: false eps: 1e-5 } } layer { name: "conv5_3/dw/scale" type: "Scale" bottom: "conv5_3/dw" top: "conv5_3/dw" param { lr_mult: 1 decay_mult: 0 } param { lr_mult: 1 decay_mult: 0 } scale_param { filler { value: 1 } bias_term: true bias_filler { value: 0 } } } layer { name: "relu5_3/dw" type: "ReLU" bottom: "conv5_3/dw" top: "conv5_3/dw" } layer { name: "conv5_3/sep" type: "Convolution" bottom: "conv5_3/dw" top: "conv5_3/sep" param { lr_mult: 1 decay_mult: 1 } convolution_param { num_output: 512 bias_term: false pad: 0 kernel_size: 1 stride: 1 weight_filler { type: "msra" } } } layer { name: "conv5_3/sep/bn" type: "BatchNorm" bottom: "conv5_3/sep" top: "conv5_3/sep" param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } batch_norm_param { use_global_stats: false eps: 1e-5 } } layer { name: "conv5_3/sep/scale" type: "Scale" bottom: "conv5_3/sep" top: "conv5_3/sep" param { lr_mult: 1 decay_mult: 0 } param { lr_mult: 1 decay_mult: 0 } scale_param { filler { value: 1 } bias_term: true bias_filler { value: 0 } } } layer { name: "relu5_3/sep" type: "ReLU" bottom: "conv5_3/sep" top: "conv5_3/sep" } layer { name: "conv5_4/dw" type: "Convolution" bottom: "conv5_3/sep" top: "conv5_4/dw" param { lr_mult: 1 decay_mult: 1 } convolution_param { num_output: 512 bias_term: false pad: 1 kernel_size: 3 group: 512 engine: CAFFE stride: 1 weight_filler { type: "msra" } } } layer { name: "conv5_4/dw/bn" type: "BatchNorm" bottom: "conv5_4/dw" top: "conv5_4/dw" param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } batch_norm_param { use_global_stats: false eps: 1e-5 } } layer { name: "conv5_4/dw/scale" type: "Scale" bottom: "conv5_4/dw" top: "conv5_4/dw" param { lr_mult: 1 decay_mult: 0 } param { lr_mult: 1 decay_mult: 0 } scale_param { filler { value: 1 } bias_term: true bias_filler { value: 0 } } } layer { name: "relu5_4/dw" type: "ReLU" bottom: "conv5_4/dw" top: "conv5_4/dw" } layer { name: "conv5_4/sep" type: "Convolution" bottom: "conv5_4/dw" top: "conv5_4/sep" param { lr_mult: 1 decay_mult: 1 } convolution_param { num_output: 512 bias_term: false pad: 0 kernel_size: 1 stride: 1 weight_filler { type: "msra" } } } layer { name: "conv5_4/sep/bn" type: "BatchNorm" bottom: "conv5_4/sep" top: "conv5_4/sep" param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } batch_norm_param { use_global_stats: false eps: 1e-5 } } layer { name: "conv5_4/sep/scale" type: "Scale" bottom: "conv5_4/sep" top: "conv5_4/sep" param { lr_mult: 1 decay_mult: 0 } param { lr_mult: 1 decay_mult: 0 } scale_param { filler { value: 1 } bias_term: true bias_filler { value: 0 } } } layer { name: "relu5_4/sep" type: "ReLU" bottom: "conv5_4/sep" top: "conv5_4/sep" } layer { name: "conv5_5/dw" type: "Convolution" bottom: "conv5_4/sep" top: "conv5_5/dw" param { lr_mult: 1 decay_mult: 1 } convolution_param { num_output: 512 bias_term: false pad: 1 kernel_size: 3 group: 512 engine: CAFFE stride: 1 weight_filler { type: "msra" } } } layer { name: "conv5_5/dw/bn" type: "BatchNorm" bottom: "conv5_5/dw" top: "conv5_5/dw" param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } batch_norm_param { use_global_stats: false eps: 1e-5 } } layer { name: "conv5_5/dw/scale" type: "Scale" bottom: "conv5_5/dw" top: "conv5_5/dw" param { lr_mult: 1 decay_mult: 0 } param { lr_mult: 1 decay_mult: 0 } scale_param { filler { value: 1 } bias_term: true bias_filler { value: 0 } } } layer { name: "relu5_5/dw" type: "ReLU" bottom: "conv5_5/dw" top: "conv5_5/dw" } layer { name: "conv5_5/sep" type: "Convolution" bottom: "conv5_5/dw" top: "conv5_5/sep" param { lr_mult: 1 decay_mult: 1 } convolution_param { num_output: 512 bias_term: false pad: 0 kernel_size: 1 stride: 1 weight_filler { type: "msra" } } } layer { name: "conv5_5/sep/bn" type: "BatchNorm" bottom: "conv5_5/sep" top: "conv5_5/sep" param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } batch_norm_param { use_global_stats: false eps: 1e-5 } } layer { name: "conv5_5/sep/scale" type: "Scale" bottom: "conv5_5/sep" top: "conv5_5/sep" param { lr_mult: 1 decay_mult: 0 } param { lr_mult: 1 decay_mult: 0 } scale_param { filler { value: 1 } bias_term: true bias_filler { value: 0 } } } layer { name: "relu5_5/sep" type: "ReLU" bottom: "conv5_5/sep" top: "conv5_5/sep" }

#========= RPN ============

layer { name: "rpn_conv/3x3" type: "Convolution" #bottom: "conv5_2/expand" bottom: "conv5_5/sep" top: "rpn/output" param { lr_mult: 1.0 } param { lr_mult: 2.0 } convolution_param { num_output: 512 kernel_size: 3 pad: 1 stride: 1 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" value: 0 } } } layer { name: "rpn_relu/3x3" type: "ReLU" bottom: "rpn/output" top: "rpn/output" }

layer { name: "rpn_cls_score" type: "Convolution" bottom: "rpn/output" top: "rpn_cls_score" param { lr_mult: 1.0 } param { lr_mult: 2.0 } convolution_param { num_output: 54 # 2(bg/fg) * 9(anchors) kernel_size: 1 pad: 0 stride: 1 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" value: 0 } } }

layer { name: "rpn_bbox_pred" type: "Convolution" bottom: "rpn/output" top: "rpn_bbox_pred" param { lr_mult: 1.0 } param { lr_mult: 2.0 } convolution_param { num_output: 108 # 4 * 9(anchors) kernel_size: 1 pad: 0 stride: 1 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" value: 0 } } }

layer { bottom: "rpn_cls_score" top: "rpn_cls_score_reshape" name: "rpn_cls_score_reshape" type: "Reshape" reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } } }

layer { name: 'rpn-data' type: 'Python' bottom: 'rpn_cls_score' bottom: 'gt_boxes' bottom: 'im_info' bottom: 'data' top: 'rpn_labels' top: 'rpn_bbox_targets' top: 'rpn_bbox_inside_weights' top: 'rpn_bbox_outside_weights' python_param { module: 'rpn.anchor_target_layer' layer: 'AnchorTargetLayer' param_str: "'feat_stride': 16" } }

layer { name: "rpn_loss_cls" type: "SoftmaxWithLoss" bottom: "rpn_cls_score_reshape" bottom: "rpn_labels" propagate_down: 1 propagate_down: 0 top: "rpn_cls_loss" loss_weight: 1 loss_param { ignore_label: -1 normalize: true } }

layer { name: "rpn_loss_bbox" type: "SmoothL1Loss" bottom: "rpn_bbox_pred" bottom: "rpn_bbox_targets" bottom: 'rpn_bbox_inside_weights' bottom: 'rpn_bbox_outside_weights' top: "rpn_loss_bbox" loss_weight: 1 smooth_l1_loss_param { sigma: 3.0 } }

#========= RoI Proposal ============

layer { name: "rpn_cls_prob" type: "Softmax" bottom: "rpn_cls_score_reshape" top: "rpn_cls_prob" }

layer { name: 'rpn_cls_prob_reshape' type: 'Reshape' bottom: 'rpn_cls_prob' top: 'rpn_cls_prob_reshape' reshape_param { shape { dim: 0 dim: 54 dim: -1 dim: 0 } } }

layer { name: 'proposal' type: 'Python' bottom: 'rpn_cls_prob_reshape' bottom: 'rpn_bbox_pred' bottom: 'im_info' top: 'rpn_rois'

top: 'rpn_scores'

python_param { module: 'rpn.proposal_layer' layer: 'ProposalLayer' param_str: "'feat_stride': 16" } }

#layer {

name: 'debug-data'

type: 'Python'

bottom: 'data'

bottom: 'rpn_rois'

bottom: 'rpn_scores'

python_param {

module: 'rpn.debug_layer'

layer: 'RPNDebugLayer'

}

#}

layer { name: 'roi-data' type: 'Python' bottom: 'rpn_rois' bottom: 'gt_boxes' top: 'rois' top: 'labels' top: 'bbox_targets' top: 'bbox_inside_weights' top: 'bbox_outside_weights' python_param { module: 'rpn.proposal_target_layer' layer: 'ProposalTargetLayer' param_str: "'num_classes': 4" #21 } }

#========= RCNN ============

layer { name: "roi_pool5" type: "ROIPooling" bottom: "conv5_5/sep" bottom: "rois" top: "pool5" roi_pooling_param { pooled_w: 7 pooled_h: 7 spatial_scale: 0.0625 # 1/16 } } layer { name: "fc6" type: "InnerProduct" bottom: "pool5" top: "fc6" param { lr_mult: 1 } param { lr_mult: 2 } inner_product_param { num_output: 4096 } } layer { name: "relu6" type: "ReLU" bottom: "fc6" top: "fc6" } layer { name: "drop6" type: "Dropout" bottom: "fc6" top: "fc6" dropout_param { dropout_ratio: 0.5 } } layer { name: "fc7" type: "InnerProduct" bottom: "fc6" top: "fc7" param { lr_mult: 1 } param { lr_mult: 2 } inner_product_param { num_output: 4096 } } layer { name: "relu7" type: "ReLU" bottom: "fc7" top: "fc7" } layer { name: "drop7" type: "Dropout" bottom: "fc7" top: "fc7" dropout_param { dropout_ratio: 0.5 } } layer { name: "cls_score" type: "InnerProduct" bottom: "fc7" top: "cls_score" param { lr_mult: 1 } param { lr_mult: 2 } inner_product_param { num_output: 4 #21 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" value: 0 } } }

layer { name: "accuracy" type: "Accuracy" bottom: "cls_score" bottom: "labels" top: "accuracy" include { phase: TRAIN } }

layer { type: 'Python' name: 'py_accuracy' top: 'py_accuracy' bottom: 'cls_score' bottom: 'labels' python_param { # the module name -- usually the filename -- that needs to be in $PYTHONPATH module: 'rpn.python_confmat' # the layer name -- the class name in the module layer: 'PythonConfMat' param_str: '{"test_iter":20}' } include { phase: TRAIN } }

layer { name: "bbox_pred" type: "InnerProduct" bottom: "fc7" top: "bbox_pred" param { lr_mult: 1 } param {
lr_mult: 2 } inner_product_param { num_output: 16 #84 weight_filler { type: "gaussian" std: 0.001 } bias_filler { type: "constant" value: 0 } } }

layer { name: "loss_cls" type: "SoftmaxWithLoss" bottom: "cls_score" bottom: "labels" propagate_down: 1 propagate_down: 0 top: "loss_cls" loss_weight: 1 } layer { name: "loss_bbox" type: "SmoothL1Loss" bottom: "bbox_pred" bottom: "bbox_targets" bottom: "bbox_inside_weights" bottom: "bbox_outside_weights" top: "loss_bbox" loss_weight: 1 }