summary | shortlog | log | commit | commitdiff | tree
raw | patch | inline | side by side (parent: 1f8c99d)
raw | patch | inline | side by side (parent: 1f8c99d)
author | Luke Yeager <luke.yeager@gmail.com> | |
Fri, 20 May 2016 00:45:54 +0000 (17:45 -0700) | ||
committer | Luke Yeager <luke.yeager@gmail.com> | |
Thu, 26 May 2016 20:59:22 +0000 (13:59 -0700) |
Uses an all-in-one network
examples/kitti/detectnet_network.prototxt | [new file with mode: 0644] | patch | blob |
examples/kitti/detectnet_solver.prototxt | [new file with mode: 0644] | patch | blob |
examples/kitti/detectnet_time.sh | [new file with mode: 0755] | patch | blob |
examples/kitti/detectnet_train.sh | [new file with mode: 0755] | patch | blob |
diff --git a/examples/kitti/detectnet_network.prototxt b/examples/kitti/detectnet_network.prototxt
--- /dev/null
@@ -0,0 +1,2546 @@
+# DetectNet network
+
+# Data/Input layers
+name: "DetectNet"
+layer {
+ name: "train_data"
+ type: "Data"
+ top: "data"
+ data_param {
+ backend: LMDB
+ source: "examples/kitti/kitti_train_images.lmdb"
+ batch_size: 10
+ }
+ include: { phase: TRAIN }
+}
+layer {
+ name: "train_label"
+ type: "Data"
+ top: "label"
+ data_param {
+ backend: LMDB
+ source: "examples/kitti/kitti_train_labels.lmdb"
+ batch_size: 10
+ }
+ include: { phase: TRAIN }
+}
+layer {
+ name: "val_data"
+ type: "Data"
+ top: "data"
+ data_param {
+ backend: LMDB
+ source: "examples/kitti/kitti_test_images.lmdb"
+ batch_size: 6
+ }
+ include: { phase: TEST stage: "val" }
+}
+layer {
+ name: "val_label"
+ type: "Data"
+ top: "label"
+ data_param {
+ backend: LMDB
+ source: "examples/kitti/kitti_test_labels.lmdb"
+ batch_size: 6
+ }
+ include: { phase: TEST stage: "val" }
+}
+layer {
+ name: "deploy_data"
+ type: "Input"
+ top: "data"
+ input_param {
+ shape {
+ dim: 1
+ dim: 3
+ dim: 384
+ dim: 1248
+ }
+ }
+ include: { phase: TEST not_stage: "val" }
+}
+
+# Data transformation layers
+layer {
+ name: "train_transform"
+ type: "DetectNetTransformation"
+ bottom: "data"
+ bottom: "label"
+ top: "transformed_data"
+ top: "transformed_label"
+ detectnet_groundtruth_param: {
+ stride: 16
+ scale_cvg: 0.4
+ gridbox_type: GRIDBOX_MIN
+ coverage_type: RECTANGULAR
+ min_cvg_len: 20
+ obj_norm: true
+ image_size_x: 1248
+ image_size_y: 384
+ crop_bboxes: true
+ }
+ detectnet_augmentation_param: {
+ crop_prob: 1
+ shift_x: 32
+ shift_y: 32
+ flip_prob: 0.5
+ rotation_prob: 0
+ max_rotate_degree: 5
+ scale_prob: 0.4
+ scale_min: 0.8
+ scale_max: 1.2
+ hue_rotation_prob: 0.8
+ hue_rotation: 30
+ desaturation_prob: 0.8
+ desaturation_max: 0.8
+ }
+ transform_param: {
+ mean_value: 127
+ }
+ include: { phase: TRAIN }
+}
+layer {
+ name: "val_transform"
+ type: "DetectNetTransformation"
+ bottom: "data"
+ bottom: "label"
+ top: "transformed_data"
+ top: "transformed_label"
+ detectnet_groundtruth_param: {
+ stride: 16
+ scale_cvg: 0.4
+ gridbox_type: GRIDBOX_MIN
+ coverage_type: RECTANGULAR
+ min_cvg_len: 20
+ obj_norm: true
+ image_size_x: 1248
+ image_size_y: 384
+ crop_bboxes: false
+ }
+ transform_param: {
+ mean_value: 127
+ }
+ include: { phase: TEST stage: "val" }
+}
+layer {
+ name: "deploy_transform"
+ type: "Power"
+ bottom: "data"
+ top: "transformed_data"
+ power_param {
+ shift: -127
+ }
+ include: { phase: TEST not_stage: "val" }
+}
+
+# Label conversion layers
+layer {
+ name: "slice-label"
+ type: "Slice"
+ bottom: "transformed_label"
+ top: "foreground-label"
+ top: "bbox-label"
+ top: "size-label"
+ top: "obj-label"
+ top: "coverage-label"
+ slice_param {
+ slice_dim: 1
+ slice_point: 1
+ slice_point: 5
+ slice_point: 7
+ slice_point: 8
+ }
+ include { phase: TRAIN }
+ include { phase: TEST stage: "val" }
+}
+layer {
+ name: "coverage-block"
+ type: "Concat"
+ bottom: "foreground-label"
+ bottom: "foreground-label"
+ bottom: "foreground-label"
+ bottom: "foreground-label"
+ top: "coverage-block"
+ concat_param {
+ concat_dim: 1
+ }
+ include { phase: TRAIN }
+ include { phase: TEST stage: "val" }
+}
+layer {
+ name: "size-block"
+ type: "Concat"
+ bottom: "size-label"
+ bottom: "size-label"
+ top: "size-block"
+ concat_param {
+ concat_dim: 1
+ }
+ include { phase: TRAIN }
+ include { phase: TEST stage: "val" }
+}
+layer {
+ name: "obj-block"
+ type: "Concat"
+ bottom: "obj-label"
+ bottom: "obj-label"
+ bottom: "obj-label"
+ bottom: "obj-label"
+ top: "obj-block"
+ concat_param {
+ concat_dim: 1
+ }
+ include { phase: TRAIN }
+ include { phase: TEST stage: "val" }
+}
+layer {
+ name: "bb-label-norm"
+ type: "Eltwise"
+ bottom: "bbox-label"
+ bottom: "size-block"
+ top: "bbox-label-norm"
+ eltwise_param {
+ operation: PROD
+ }
+ include { phase: TRAIN }
+ include { phase: TEST stage: "val" }
+}
+layer {
+ name: "bb-obj-norm"
+ type: "Eltwise"
+ bottom: "bbox-label-norm"
+ bottom: "obj-block"
+ top: "bbox-obj-label-norm"
+ eltwise_param {
+ operation: PROD
+ }
+ include { phase: TRAIN }
+ include { phase: TEST stage: "val" }
+}
+
+######################################################################
+# Start of convolutional network
+######################################################################
+
+layer {
+ name: "conv1/7x7_s2"
+ type: "Convolution"
+ bottom: "transformed_data"
+ top: "conv1/7x7_s2"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 64
+ pad: 3
+ kernel_size: 7
+ stride: 2
+ weight_filler {
+ type: "xavier"
+ std: 0.1
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+
+layer {
+ name: "conv1/relu_7x7"
+ type: "ReLU"
+ bottom: "conv1/7x7_s2"
+ top: "conv1/7x7_s2"
+}
+
+layer {
+ name: "pool1/3x3_s2"
+ type: "Pooling"
+ bottom: "conv1/7x7_s2"
+ top: "pool1/3x3_s2"
+ pooling_param {
+ pool: MAX
+ kernel_size: 3
+ stride: 2
+ }
+}
+
+layer {
+ name: "pool1/norm1"
+ type: "LRN"
+ bottom: "pool1/3x3_s2"
+ top: "pool1/norm1"
+ lrn_param {
+ local_size: 5
+ alpha: 0.0001
+ beta: 0.75
+ }
+}
+
+layer {
+ name: "conv2/3x3_reduce"
+ type: "Convolution"
+ bottom: "pool1/norm1"
+ top: "conv2/3x3_reduce"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 64
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.1
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+
+layer {
+ name: "conv2/relu_3x3_reduce"
+ type: "ReLU"
+ bottom: "conv2/3x3_reduce"
+ top: "conv2/3x3_reduce"
+}
+
+layer {
+ name: "conv2/3x3"
+ type: "Convolution"
+ bottom: "conv2/3x3_reduce"
+ top: "conv2/3x3"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 192
+ pad: 1
+ kernel_size: 3
+ weight_filler {
+ type: "xavier"
+ std: 0.03
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+
+layer {
+ name: "conv2/relu_3x3"
+ type: "ReLU"
+ bottom: "conv2/3x3"
+ top: "conv2/3x3"
+}
+
+layer {
+ name: "conv2/norm2"
+ type: "LRN"
+ bottom: "conv2/3x3"
+ top: "conv2/norm2"
+ lrn_param {
+ local_size: 5
+ alpha: 0.0001
+ beta: 0.75
+ }
+}
+
+layer {
+ name: "pool2/3x3_s2"
+ type: "Pooling"
+ bottom: "conv2/norm2"
+ top: "pool2/3x3_s2"
+ pooling_param {
+ pool: MAX
+ kernel_size: 3
+ stride: 2
+ }
+}
+
+layer {
+ name: "inception_3a/1x1"
+ type: "Convolution"
+ bottom: "pool2/3x3_s2"
+ top: "inception_3a/1x1"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 64
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.03
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+
+layer {
+ name: "inception_3a/relu_1x1"
+ type: "ReLU"
+ bottom: "inception_3a/1x1"
+ top: "inception_3a/1x1"
+}
+
+layer {
+ name: "inception_3a/3x3_reduce"
+ type: "Convolution"
+ bottom: "pool2/3x3_s2"
+ top: "inception_3a/3x3_reduce"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 96
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.09
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+
+layer {
+ name: "inception_3a/relu_3x3_reduce"
+ type: "ReLU"
+ bottom: "inception_3a/3x3_reduce"
+ top: "inception_3a/3x3_reduce"
+}
+
+layer {
+ name: "inception_3a/3x3"
+ type: "Convolution"
+ bottom: "inception_3a/3x3_reduce"
+ top: "inception_3a/3x3"
+ 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"
+ std: 0.03
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+
+layer {
+ name: "inception_3a/relu_3x3"
+ type: "ReLU"
+ bottom: "inception_3a/3x3"
+ top: "inception_3a/3x3"
+}
+
+layer {
+ name: "inception_3a/5x5_reduce"
+ type: "Convolution"
+ bottom: "pool2/3x3_s2"
+ top: "inception_3a/5x5_reduce"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 16
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.2
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_3a/relu_5x5_reduce"
+ type: "ReLU"
+ bottom: "inception_3a/5x5_reduce"
+ top: "inception_3a/5x5_reduce"
+}
+layer {
+ name: "inception_3a/5x5"
+ type: "Convolution"
+ bottom: "inception_3a/5x5_reduce"
+ top: "inception_3a/5x5"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 32
+ pad: 2
+ kernel_size: 5
+ weight_filler {
+ type: "xavier"
+ std: 0.03
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_3a/relu_5x5"
+ type: "ReLU"
+ bottom: "inception_3a/5x5"
+ top: "inception_3a/5x5"
+}
+
+layer {
+ name: "inception_3a/pool"
+ type: "Pooling"
+ bottom: "pool2/3x3_s2"
+ top: "inception_3a/pool"
+ pooling_param {
+ pool: MAX
+ kernel_size: 3
+ stride: 1
+ pad: 1
+ }
+}
+
+layer {
+ name: "inception_3a/pool_proj"
+ type: "Convolution"
+ bottom: "inception_3a/pool"
+ top: "inception_3a/pool_proj"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 32
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.1
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_3a/relu_pool_proj"
+ type: "ReLU"
+ bottom: "inception_3a/pool_proj"
+ top: "inception_3a/pool_proj"
+}
+
+layer {
+ name: "inception_3a/output"
+ type: "Concat"
+ bottom: "inception_3a/1x1"
+ bottom: "inception_3a/3x3"
+ bottom: "inception_3a/5x5"
+ bottom: "inception_3a/pool_proj"
+ top: "inception_3a/output"
+}
+
+layer {
+ name: "inception_3b/1x1"
+ type: "Convolution"
+ bottom: "inception_3a/output"
+ top: "inception_3b/1x1"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 128
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.03
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+
+layer {
+ name: "inception_3b/relu_1x1"
+ type: "ReLU"
+ bottom: "inception_3b/1x1"
+ top: "inception_3b/1x1"
+}
+
+layer {
+ name: "inception_3b/3x3_reduce"
+ type: "Convolution"
+ bottom: "inception_3a/output"
+ top: "inception_3b/3x3_reduce"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 128
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.09
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_3b/relu_3x3_reduce"
+ type: "ReLU"
+ bottom: "inception_3b/3x3_reduce"
+ top: "inception_3b/3x3_reduce"
+}
+layer {
+ name: "inception_3b/3x3"
+ type: "Convolution"
+ bottom: "inception_3b/3x3_reduce"
+ top: "inception_3b/3x3"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 192
+ pad: 1
+ kernel_size: 3
+ weight_filler {
+ type: "xavier"
+ std: 0.03
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_3b/relu_3x3"
+ type: "ReLU"
+ bottom: "inception_3b/3x3"
+ top: "inception_3b/3x3"
+}
+
+layer {
+ name: "inception_3b/5x5_reduce"
+ type: "Convolution"
+ bottom: "inception_3a/output"
+ top: "inception_3b/5x5_reduce"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 32
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.2
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_3b/relu_5x5_reduce"
+ type: "ReLU"
+ bottom: "inception_3b/5x5_reduce"
+ top: "inception_3b/5x5_reduce"
+}
+layer {
+ name: "inception_3b/5x5"
+ type: "Convolution"
+ bottom: "inception_3b/5x5_reduce"
+ top: "inception_3b/5x5"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 96
+ pad: 2
+ kernel_size: 5
+ weight_filler {
+ type: "xavier"
+ std: 0.03
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_3b/relu_5x5"
+ type: "ReLU"
+ bottom: "inception_3b/5x5"
+ top: "inception_3b/5x5"
+}
+
+layer {
+ name: "inception_3b/pool"
+ type: "Pooling"
+ bottom: "inception_3a/output"
+ top: "inception_3b/pool"
+ pooling_param {
+ pool: MAX
+ kernel_size: 3
+ stride: 1
+ pad: 1
+ }
+}
+layer {
+ name: "inception_3b/pool_proj"
+ type: "Convolution"
+ bottom: "inception_3b/pool"
+ top: "inception_3b/pool_proj"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 64
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.1
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_3b/relu_pool_proj"
+ type: "ReLU"
+ bottom: "inception_3b/pool_proj"
+ top: "inception_3b/pool_proj"
+}
+layer {
+ name: "inception_3b/output"
+ type: "Concat"
+ bottom: "inception_3b/1x1"
+ bottom: "inception_3b/3x3"
+ bottom: "inception_3b/5x5"
+ bottom: "inception_3b/pool_proj"
+ top: "inception_3b/output"
+}
+
+layer {
+ name: "pool3/3x3_s2"
+ type: "Pooling"
+ bottom: "inception_3b/output"
+ top: "pool3/3x3_s2"
+ pooling_param {
+ pool: MAX
+ kernel_size: 3
+ stride: 2
+ }
+}
+
+layer {
+ name: "inception_4a/1x1"
+ type: "Convolution"
+ bottom: "pool3/3x3_s2"
+ top: "inception_4a/1x1"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 192
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.03
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+
+layer {
+ name: "inception_4a/relu_1x1"
+ type: "ReLU"
+ bottom: "inception_4a/1x1"
+ top: "inception_4a/1x1"
+}
+
+layer {
+ name: "inception_4a/3x3_reduce"
+ type: "Convolution"
+ bottom: "pool3/3x3_s2"
+ top: "inception_4a/3x3_reduce"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 96
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.09
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+
+layer {
+ name: "inception_4a/relu_3x3_reduce"
+ type: "ReLU"
+ bottom: "inception_4a/3x3_reduce"
+ top: "inception_4a/3x3_reduce"
+}
+
+layer {
+ name: "inception_4a/3x3"
+ type: "Convolution"
+ bottom: "inception_4a/3x3_reduce"
+ top: "inception_4a/3x3"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 208
+ pad: 1
+ kernel_size: 3
+ weight_filler {
+ type: "xavier"
+ std: 0.03
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+
+layer {
+ name: "inception_4a/relu_3x3"
+ type: "ReLU"
+ bottom: "inception_4a/3x3"
+ top: "inception_4a/3x3"
+}
+
+layer {
+ name: "inception_4a/5x5_reduce"
+ type: "Convolution"
+ bottom: "pool3/3x3_s2"
+ top: "inception_4a/5x5_reduce"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 16
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.2
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_4a/relu_5x5_reduce"
+ type: "ReLU"
+ bottom: "inception_4a/5x5_reduce"
+ top: "inception_4a/5x5_reduce"
+}
+layer {
+ name: "inception_4a/5x5"
+ type: "Convolution"
+ bottom: "inception_4a/5x5_reduce"
+ top: "inception_4a/5x5"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 48
+ pad: 2
+ kernel_size: 5
+ weight_filler {
+ type: "xavier"
+ std: 0.03
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_4a/relu_5x5"
+ type: "ReLU"
+ bottom: "inception_4a/5x5"
+ top: "inception_4a/5x5"
+}
+layer {
+ name: "inception_4a/pool"
+ type: "Pooling"
+ bottom: "pool3/3x3_s2"
+ top: "inception_4a/pool"
+ pooling_param {
+ pool: MAX
+ kernel_size: 3
+ stride: 1
+ pad: 1
+ }
+}
+layer {
+ name: "inception_4a/pool_proj"
+ type: "Convolution"
+ bottom: "inception_4a/pool"
+ top: "inception_4a/pool_proj"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 64
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.1
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_4a/relu_pool_proj"
+ type: "ReLU"
+ bottom: "inception_4a/pool_proj"
+ top: "inception_4a/pool_proj"
+}
+layer {
+ name: "inception_4a/output"
+ type: "Concat"
+ bottom: "inception_4a/1x1"
+ bottom: "inception_4a/3x3"
+ bottom: "inception_4a/5x5"
+ bottom: "inception_4a/pool_proj"
+ top: "inception_4a/output"
+}
+
+layer {
+ name: "inception_4b/1x1"
+ type: "Convolution"
+ bottom: "inception_4a/output"
+ top: "inception_4b/1x1"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 160
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.03
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+
+layer {
+ name: "inception_4b/relu_1x1"
+ type: "ReLU"
+ bottom: "inception_4b/1x1"
+ top: "inception_4b/1x1"
+}
+layer {
+ name: "inception_4b/3x3_reduce"
+ type: "Convolution"
+ bottom: "inception_4a/output"
+ top: "inception_4b/3x3_reduce"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 112
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.09
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_4b/relu_3x3_reduce"
+ type: "ReLU"
+ bottom: "inception_4b/3x3_reduce"
+ top: "inception_4b/3x3_reduce"
+}
+layer {
+ name: "inception_4b/3x3"
+ type: "Convolution"
+ bottom: "inception_4b/3x3_reduce"
+ top: "inception_4b/3x3"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 224
+ pad: 1
+ kernel_size: 3
+ weight_filler {
+ type: "xavier"
+ std: 0.03
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_4b/relu_3x3"
+ type: "ReLU"
+ bottom: "inception_4b/3x3"
+ top: "inception_4b/3x3"
+}
+layer {
+ name: "inception_4b/5x5_reduce"
+ type: "Convolution"
+ bottom: "inception_4a/output"
+ top: "inception_4b/5x5_reduce"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 24
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.2
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_4b/relu_5x5_reduce"
+ type: "ReLU"
+ bottom: "inception_4b/5x5_reduce"
+ top: "inception_4b/5x5_reduce"
+}
+layer {
+ name: "inception_4b/5x5"
+ type: "Convolution"
+ bottom: "inception_4b/5x5_reduce"
+ top: "inception_4b/5x5"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 64
+ pad: 2
+ kernel_size: 5
+ weight_filler {
+ type: "xavier"
+ std: 0.03
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_4b/relu_5x5"
+ type: "ReLU"
+ bottom: "inception_4b/5x5"
+ top: "inception_4b/5x5"
+}
+layer {
+ name: "inception_4b/pool"
+ type: "Pooling"
+ bottom: "inception_4a/output"
+ top: "inception_4b/pool"
+ pooling_param {
+ pool: MAX
+ kernel_size: 3
+ stride: 1
+ pad: 1
+ }
+}
+layer {
+ name: "inception_4b/pool_proj"
+ type: "Convolution"
+ bottom: "inception_4b/pool"
+ top: "inception_4b/pool_proj"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 64
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.1
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_4b/relu_pool_proj"
+ type: "ReLU"
+ bottom: "inception_4b/pool_proj"
+ top: "inception_4b/pool_proj"
+}
+layer {
+ name: "inception_4b/output"
+ type: "Concat"
+ bottom: "inception_4b/1x1"
+ bottom: "inception_4b/3x3"
+ bottom: "inception_4b/5x5"
+ bottom: "inception_4b/pool_proj"
+ top: "inception_4b/output"
+}
+
+layer {
+ name: "inception_4c/1x1"
+ type: "Convolution"
+ bottom: "inception_4b/output"
+ top: "inception_4c/1x1"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 128
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.03
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+
+layer {
+ name: "inception_4c/relu_1x1"
+ type: "ReLU"
+ bottom: "inception_4c/1x1"
+ top: "inception_4c/1x1"
+}
+
+layer {
+ name: "inception_4c/3x3_reduce"
+ type: "Convolution"
+ bottom: "inception_4b/output"
+ top: "inception_4c/3x3_reduce"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 128
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.09
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+
+layer {
+ name: "inception_4c/relu_3x3_reduce"
+ type: "ReLU"
+ bottom: "inception_4c/3x3_reduce"
+ top: "inception_4c/3x3_reduce"
+}
+layer {
+ name: "inception_4c/3x3"
+ type: "Convolution"
+ bottom: "inception_4c/3x3_reduce"
+ top: "inception_4c/3x3"
+ 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"
+ std: 0.03
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_4c/relu_3x3"
+ type: "ReLU"
+ bottom: "inception_4c/3x3"
+ top: "inception_4c/3x3"
+}
+layer {
+ name: "inception_4c/5x5_reduce"
+ type: "Convolution"
+ bottom: "inception_4b/output"
+ top: "inception_4c/5x5_reduce"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 24
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.2
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_4c/relu_5x5_reduce"
+ type: "ReLU"
+ bottom: "inception_4c/5x5_reduce"
+ top: "inception_4c/5x5_reduce"
+}
+layer {
+ name: "inception_4c/5x5"
+ type: "Convolution"
+ bottom: "inception_4c/5x5_reduce"
+ top: "inception_4c/5x5"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 64
+ pad: 2
+ kernel_size: 5
+ weight_filler {
+ type: "xavier"
+ std: 0.03
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_4c/relu_5x5"
+ type: "ReLU"
+ bottom: "inception_4c/5x5"
+ top: "inception_4c/5x5"
+}
+layer {
+ name: "inception_4c/pool"
+ type: "Pooling"
+ bottom: "inception_4b/output"
+ top: "inception_4c/pool"
+ pooling_param {
+ pool: MAX
+ kernel_size: 3
+ stride: 1
+ pad: 1
+ }
+}
+layer {
+ name: "inception_4c/pool_proj"
+ type: "Convolution"
+ bottom: "inception_4c/pool"
+ top: "inception_4c/pool_proj"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 64
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.1
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_4c/relu_pool_proj"
+ type: "ReLU"
+ bottom: "inception_4c/pool_proj"
+ top: "inception_4c/pool_proj"
+}
+layer {
+ name: "inception_4c/output"
+ type: "Concat"
+ bottom: "inception_4c/1x1"
+ bottom: "inception_4c/3x3"
+ bottom: "inception_4c/5x5"
+ bottom: "inception_4c/pool_proj"
+ top: "inception_4c/output"
+}
+
+layer {
+ name: "inception_4d/1x1"
+ type: "Convolution"
+ bottom: "inception_4c/output"
+ top: "inception_4d/1x1"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 112
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.1
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_4d/relu_1x1"
+ type: "ReLU"
+ bottom: "inception_4d/1x1"
+ top: "inception_4d/1x1"
+}
+layer {
+ name: "inception_4d/3x3_reduce"
+ type: "Convolution"
+ bottom: "inception_4c/output"
+ top: "inception_4d/3x3_reduce"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 144
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.1
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_4d/relu_3x3_reduce"
+ type: "ReLU"
+ bottom: "inception_4d/3x3_reduce"
+ top: "inception_4d/3x3_reduce"
+}
+layer {
+ name: "inception_4d/3x3"
+ type: "Convolution"
+ bottom: "inception_4d/3x3_reduce"
+ top: "inception_4d/3x3"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 288
+ pad: 1
+ kernel_size: 3
+ weight_filler {
+ type: "xavier"
+ std: 0.1
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_4d/relu_3x3"
+ type: "ReLU"
+ bottom: "inception_4d/3x3"
+ top: "inception_4d/3x3"
+}
+layer {
+ name: "inception_4d/5x5_reduce"
+ type: "Convolution"
+ bottom: "inception_4c/output"
+ top: "inception_4d/5x5_reduce"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 32
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.1
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_4d/relu_5x5_reduce"
+ type: "ReLU"
+ bottom: "inception_4d/5x5_reduce"
+ top: "inception_4d/5x5_reduce"
+}
+layer {
+ name: "inception_4d/5x5"
+ type: "Convolution"
+ bottom: "inception_4d/5x5_reduce"
+ top: "inception_4d/5x5"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 64
+ pad: 2
+ kernel_size: 5
+ weight_filler {
+ type: "xavier"
+ std: 0.1
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_4d/relu_5x5"
+ type: "ReLU"
+ bottom: "inception_4d/5x5"
+ top: "inception_4d/5x5"
+}
+layer {
+ name: "inception_4d/pool"
+ type: "Pooling"
+ bottom: "inception_4c/output"
+ top: "inception_4d/pool"
+ pooling_param {
+ pool: MAX
+ kernel_size: 3
+ stride: 1
+ pad: 1
+ }
+}
+layer {
+ name: "inception_4d/pool_proj"
+ type: "Convolution"
+ bottom: "inception_4d/pool"
+ top: "inception_4d/pool_proj"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 64
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.1
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_4d/relu_pool_proj"
+ type: "ReLU"
+ bottom: "inception_4d/pool_proj"
+ top: "inception_4d/pool_proj"
+}
+layer {
+ name: "inception_4d/output"
+ type: "Concat"
+ bottom: "inception_4d/1x1"
+ bottom: "inception_4d/3x3"
+ bottom: "inception_4d/5x5"
+ bottom: "inception_4d/pool_proj"
+ top: "inception_4d/output"
+}
+
+layer {
+ name: "inception_4e/1x1"
+ type: "Convolution"
+ bottom: "inception_4d/output"
+ top: "inception_4e/1x1"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 256
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.03
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_4e/relu_1x1"
+ type: "ReLU"
+ bottom: "inception_4e/1x1"
+ top: "inception_4e/1x1"
+}
+layer {
+ name: "inception_4e/3x3_reduce"
+ type: "Convolution"
+ bottom: "inception_4d/output"
+ top: "inception_4e/3x3_reduce"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 160
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.09
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_4e/relu_3x3_reduce"
+ type: "ReLU"
+ bottom: "inception_4e/3x3_reduce"
+ top: "inception_4e/3x3_reduce"
+}
+layer {
+ name: "inception_4e/3x3"
+ type: "Convolution"
+ bottom: "inception_4e/3x3_reduce"
+ top: "inception_4e/3x3"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 320
+ pad: 1
+ kernel_size: 3
+ weight_filler {
+ type: "xavier"
+ std: 0.03
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_4e/relu_3x3"
+ type: "ReLU"
+ bottom: "inception_4e/3x3"
+ top: "inception_4e/3x3"
+}
+layer {
+ name: "inception_4e/5x5_reduce"
+ type: "Convolution"
+ bottom: "inception_4d/output"
+ top: "inception_4e/5x5_reduce"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 32
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.2
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_4e/relu_5x5_reduce"
+ type: "ReLU"
+ bottom: "inception_4e/5x5_reduce"
+ top: "inception_4e/5x5_reduce"
+}
+layer {
+ name: "inception_4e/5x5"
+ type: "Convolution"
+ bottom: "inception_4e/5x5_reduce"
+ top: "inception_4e/5x5"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 128
+ pad: 2
+ kernel_size: 5
+ weight_filler {
+ type: "xavier"
+ std: 0.03
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_4e/relu_5x5"
+ type: "ReLU"
+ bottom: "inception_4e/5x5"
+ top: "inception_4e/5x5"
+}
+layer {
+ name: "inception_4e/pool"
+ type: "Pooling"
+ bottom: "inception_4d/output"
+ top: "inception_4e/pool"
+ pooling_param {
+ pool: MAX
+ kernel_size: 3
+ stride: 1
+ pad: 1
+ }
+}
+layer {
+ name: "inception_4e/pool_proj"
+ type: "Convolution"
+ bottom: "inception_4e/pool"
+ top: "inception_4e/pool_proj"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 128
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.1
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_4e/relu_pool_proj"
+ type: "ReLU"
+ bottom: "inception_4e/pool_proj"
+ top: "inception_4e/pool_proj"
+}
+layer {
+ name: "inception_4e/output"
+ type: "Concat"
+ bottom: "inception_4e/1x1"
+ bottom: "inception_4e/3x3"
+ bottom: "inception_4e/5x5"
+ bottom: "inception_4e/pool_proj"
+ top: "inception_4e/output"
+}
+
+
+
+layer {
+ name: "inception_5a/1x1"
+ type: "Convolution"
+ bottom: "inception_4e/output"
+ top: "inception_5a/1x1"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 256
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.03
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_5a/relu_1x1"
+ type: "ReLU"
+ bottom: "inception_5a/1x1"
+ top: "inception_5a/1x1"
+}
+
+layer {
+ name: "inception_5a/3x3_reduce"
+ type: "Convolution"
+ bottom: "inception_4e/output"
+ top: "inception_5a/3x3_reduce"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 160
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.09
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_5a/relu_3x3_reduce"
+ type: "ReLU"
+ bottom: "inception_5a/3x3_reduce"
+ top: "inception_5a/3x3_reduce"
+}
+
+layer {
+ name: "inception_5a/3x3"
+ type: "Convolution"
+ bottom: "inception_5a/3x3_reduce"
+ top: "inception_5a/3x3"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 320
+ pad: 1
+ kernel_size: 3
+ weight_filler {
+ type: "xavier"
+ std: 0.03
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_5a/relu_3x3"
+ type: "ReLU"
+ bottom: "inception_5a/3x3"
+ top: "inception_5a/3x3"
+}
+layer {
+ name: "inception_5a/5x5_reduce"
+ type: "Convolution"
+ bottom: "inception_4e/output"
+ top: "inception_5a/5x5_reduce"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 32
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.2
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_5a/relu_5x5_reduce"
+ type: "ReLU"
+ bottom: "inception_5a/5x5_reduce"
+ top: "inception_5a/5x5_reduce"
+}
+layer {
+ name: "inception_5a/5x5"
+ type: "Convolution"
+ bottom: "inception_5a/5x5_reduce"
+ top: "inception_5a/5x5"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 128
+ pad: 2
+ kernel_size: 5
+ weight_filler {
+ type: "xavier"
+ std: 0.03
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_5a/relu_5x5"
+ type: "ReLU"
+ bottom: "inception_5a/5x5"
+ top: "inception_5a/5x5"
+}
+layer {
+ name: "inception_5a/pool"
+ type: "Pooling"
+ bottom: "inception_4e/output"
+ top: "inception_5a/pool"
+ pooling_param {
+ pool: MAX
+ kernel_size: 3
+ stride: 1
+ pad: 1
+ }
+}
+layer {
+ name: "inception_5a/pool_proj"
+ type: "Convolution"
+ bottom: "inception_5a/pool"
+ top: "inception_5a/pool_proj"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 128
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.1
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_5a/relu_pool_proj"
+ type: "ReLU"
+ bottom: "inception_5a/pool_proj"
+ top: "inception_5a/pool_proj"
+}
+layer {
+ name: "inception_5a/output"
+ type: "Concat"
+ bottom: "inception_5a/1x1"
+ bottom: "inception_5a/3x3"
+ bottom: "inception_5a/5x5"
+ bottom: "inception_5a/pool_proj"
+ top: "inception_5a/output"
+}
+
+layer {
+ name: "inception_5b/1x1"
+ type: "Convolution"
+ bottom: "inception_5a/output"
+ top: "inception_5b/1x1"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 384
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.1
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_5b/relu_1x1"
+ type: "ReLU"
+ bottom: "inception_5b/1x1"
+ top: "inception_5b/1x1"
+}
+layer {
+ name: "inception_5b/3x3_reduce"
+ type: "Convolution"
+ bottom: "inception_5a/output"
+ top: "inception_5b/3x3_reduce"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 1
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 192
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.1
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_5b/relu_3x3_reduce"
+ type: "ReLU"
+ bottom: "inception_5b/3x3_reduce"
+ top: "inception_5b/3x3_reduce"
+}
+layer {
+ name: "inception_5b/3x3"
+ type: "Convolution"
+ bottom: "inception_5b/3x3_reduce"
+ top: "inception_5b/3x3"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 384
+ pad: 1
+ kernel_size: 3
+ weight_filler {
+ type: "xavier"
+ std: 0.1
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_5b/relu_3x3"
+ type: "ReLU"
+ bottom: "inception_5b/3x3"
+ top: "inception_5b/3x3"
+}
+layer {
+ name: "inception_5b/5x5_reduce"
+ type: "Convolution"
+ bottom: "inception_5a/output"
+ top: "inception_5b/5x5_reduce"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 48
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.1
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_5b/relu_5x5_reduce"
+ type: "ReLU"
+ bottom: "inception_5b/5x5_reduce"
+ top: "inception_5b/5x5_reduce"
+}
+layer {
+ name: "inception_5b/5x5"
+ type: "Convolution"
+ bottom: "inception_5b/5x5_reduce"
+ top: "inception_5b/5x5"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 128
+ pad: 2
+ kernel_size: 5
+ weight_filler {
+ type: "xavier"
+ std: 0.1
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_5b/relu_5x5"
+ type: "ReLU"
+ bottom: "inception_5b/5x5"
+ top: "inception_5b/5x5"
+}
+layer {
+ name: "inception_5b/pool"
+ type: "Pooling"
+ bottom: "inception_5a/output"
+ top: "inception_5b/pool"
+ pooling_param {
+ pool: MAX
+ kernel_size: 3
+ stride: 1
+ pad: 1
+ }
+}
+layer {
+ name: "inception_5b/pool_proj"
+ type: "Convolution"
+ bottom: "inception_5b/pool"
+ top: "inception_5b/pool_proj"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 128
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.1
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.2
+ }
+ }
+}
+layer {
+ name: "inception_5b/relu_pool_proj"
+ type: "ReLU"
+ bottom: "inception_5b/pool_proj"
+ top: "inception_5b/pool_proj"
+}
+layer {
+ name: "inception_5b/output"
+ type: "Concat"
+ bottom: "inception_5b/1x1"
+ bottom: "inception_5b/3x3"
+ bottom: "inception_5b/5x5"
+ bottom: "inception_5b/pool_proj"
+ top: "inception_5b/output"
+}
+layer {
+ name: "pool5/drop_s1"
+ type: "Dropout"
+ bottom: "inception_5b/output"
+ top: "pool5/drop_s1"
+ dropout_param {
+ dropout_ratio: 0.4
+ }
+}
+layer {
+ name: "cvg/classifier"
+ type: "Convolution"
+ bottom: "pool5/drop_s1"
+ top: "cvg/classifier"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 1
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.03
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.
+ }
+ }
+}
+layer {
+ name: "coverage/sig"
+ type: "Sigmoid"
+ bottom: "cvg/classifier"
+ top: "coverage"
+}
+layer {
+ name: "bbox/regressor"
+ type: "Convolution"
+ bottom: "pool5/drop_s1"
+ top: "bboxes"
+ param {
+ lr_mult: 1
+ decay_mult: 1
+ }
+ param {
+ lr_mult: 2
+ decay_mult: 0
+ }
+ convolution_param {
+ num_output: 4
+ kernel_size: 1
+ weight_filler {
+ type: "xavier"
+ std: 0.03
+ }
+ bias_filler {
+ type: "constant"
+ value: 0.
+ }
+ }
+}
+
+######################################################################
+# End of convolutional network
+######################################################################
+
+# Convert bboxes
+layer {
+ name: "bbox_mask"
+ type: "Eltwise"
+ bottom: "bboxes"
+ bottom: "coverage-block"
+ top: "bboxes-masked"
+ eltwise_param {
+ operation: PROD
+ }
+ include { phase: TRAIN }
+ include { phase: TEST stage: "val" }
+}
+layer {
+ name: "bbox-norm"
+ type: "Eltwise"
+ bottom: "bboxes-masked"
+ bottom: "size-block"
+ top: "bboxes-masked-norm"
+ eltwise_param {
+ operation: PROD
+ }
+ include { phase: TRAIN }
+ include { phase: TEST stage: "val" }
+}
+layer {
+ name: "bbox-obj-norm"
+ type: "Eltwise"
+ bottom: "bboxes-masked-norm"
+ bottom: "obj-block"
+ top: "bboxes-obj-masked-norm"
+ eltwise_param {
+ operation: PROD
+ }
+ include { phase: TRAIN }
+ include { phase: TEST stage: "val" }
+}
+
+# Loss layers
+layer {
+ name: "bbox_loss"
+ type: "L1Loss"
+ bottom: "bboxes-obj-masked-norm"
+ bottom: "bbox-obj-label-norm"
+ top: "loss_bbox"
+ loss_weight: 2
+ include { phase: TRAIN }
+ include { phase: TEST stage: "val" }
+}
+layer {
+ name: "coverage_loss"
+ type: "EuclideanLoss"
+ bottom: "coverage"
+ bottom: "coverage-label"
+ top: "loss_coverage"
+ include { phase: TRAIN }
+ include { phase: TEST stage: "val" }
+}
+
+# Cluster bboxes
+layer {
+ type: 'Python'
+ name: 'cluster'
+ bottom: 'coverage'
+ bottom: 'bboxes'
+ top: 'bbox-list'
+ python_param {
+ module: 'caffe.layers.detectnet.clustering'
+ layer: 'ClusterDetections'
+ param_str : '1248, 352, 16, 0.6, 3, 0.02, 22'
+ }
+ include: { phase: TEST }
+}
+
+# Calculate mean average precision
+layer {
+ type: 'Python'
+ name: 'cluster_gt'
+ bottom: 'coverage-label'
+ bottom: 'bbox-label'
+ top: 'bbox-list-label'
+ python_param {
+ module: 'caffe.layers.detectnet.clustering'
+ layer: 'ClusterGroundtruth'
+ param_str : '1248, 352, 16'
+ }
+ include: { phase: TEST stage: "val" }
+}
+layer {
+ type: 'Python'
+ name: 'score'
+ bottom: 'bbox-list-label'
+ bottom: 'bbox-list'
+ top: 'bbox-list-scored'
+ python_param {
+ module: 'caffe.layers.detectnet.mean_ap'
+ layer: 'ScoreDetections'
+ }
+ include: { phase: TEST stage: "val" }
+}
+layer {
+ type: 'Python'
+ name: 'mAP'
+ bottom: 'bbox-list-scored'
+ top: 'mAP'
+ top: 'precision'
+ top: 'recall'
+ python_param {
+ module: 'caffe.layers.detectnet.mean_ap'
+ layer: 'mAP'
+ param_str : '1248, 352, 16'
+ }
+ include: { phase: TEST stage: "val" }
+}
diff --git a/examples/kitti/detectnet_solver.prototxt b/examples/kitti/detectnet_solver.prototxt
--- /dev/null
@@ -0,0 +1,21 @@
+# DetectNet solver
+net: "examples/kitti/detectnet_network.prototxt"
+test_state { stage: "val" }
+
+max_iter: 38000 # ~60 train epochs
+test_interval: 1280 # ~2 train epochs
+test_iter: 185 # 1 test epoch
+snapshot: 1280 # ~2 train epochs
+snapshot_prefix: "examples/kitti/detectnet_snapshot"
+display: 160
+
+solver_type: ADAM
+base_lr: 0.0002
+lr_policy: "step"
+stepsize: 12000
+gamma: 0.1
+momentum: 0.9
+momentum2: 0.999
+weight_decay: 1e-08
+
+solver_mode: GPU
diff --git a/examples/kitti/detectnet_time.sh b/examples/kitti/detectnet_time.sh
--- /dev/null
@@ -0,0 +1 @@
+build/tools/caffe time -model examples/kitti/detectnet_network.prototxt $@
diff --git a/examples/kitti/detectnet_train.sh b/examples/kitti/detectnet_train.sh
--- /dev/null
@@ -0,0 +1,4 @@
+build/tools/caffe train \
+ -solver examples/kitti/detectnet_solver.prototxt \
+ -weights models/bvlc_googlenet/bvlc_googlenet.caffemodel \
+ $@