This is a model from the paper:
A Deep Siamese Network for Scene Detection in Broadcast Videos
Lorenzo Baraldi, Costantino Grana, Rita Cucchiara
Proceedings of the 23rd ACM International Conference on Multimedia, 2015
Please cite the paper if you use the models.
| net: "examples/DeepScene/train_val.prototxt" | |
| test_iter: 1000 | |
| test_interval: 10 | |
| base_lr: 0.001 | |
| lr_policy: "step" | |
| gamma: 0.1 | |
| stepsize: 500 | |
| display: 1 | |
| max_iter: 100 | |
| momentum: 0.9 | |
| weight_decay: 0.0005 | |
| snapshot: 50 | |
| snapshot_prefix: "examples/DeepScene/snapshots/snapshot_" | |
| solver_mode: GPU |
| ############################################################ | |
| # BEGIN | |
| ############################################################ | |
| name: "ScenesSiamese" | |
| ############################################################ | |
| # DATA LAYERS | |
| ############################################################ | |
| # Train data layers | |
| ############################################################ | |
| layer { | |
| name: "data_image" | |
| type: "ImageData" | |
| top: "image" | |
| top: "label_image" | |
| include { phase: TRAIN } | |
| image_data_param { | |
| source: "/raid/lbaraldi/scene/bbc_train_image.txt" | |
| batch_size: 100 | |
| } | |
| transform_param { | |
| mirror: true | |
| crop_size: 227 | |
| mean_file: "data/ilsvrc12/imagenet_mean.binaryproto" | |
| } | |
| } | |
| layer { | |
| name: "data_image_p" | |
| type: "ImageData" | |
| top: "image_p" | |
| top: "label_image_p" | |
| include { phase: TRAIN } | |
| image_data_param { | |
| source: "/raid/lbaraldi/scene/bbc_train_image_p.txt" | |
| batch_size: 100 | |
| } | |
| transform_param { | |
| mirror: true | |
| crop_size: 227 | |
| mean_file: "data/ilsvrc12/imagenet_mean.binaryproto" | |
| } | |
| } | |
| layer { | |
| name: "data_multimodal" | |
| type: "HDF5Data" | |
| top: "time" | |
| top: "time_p" | |
| top: "shot_id" | |
| top: "shot_id_p" | |
| top: "histograms" | |
| top: "histograms_p" | |
| top: "label" | |
| include { phase: TRAIN } | |
| hdf5_data_param { | |
| source: "/raid/lbaraldi/scene/bbc_train_h5.txt" | |
| batch_size: 100 | |
| } | |
| } | |
| ############################################################ | |
| # Test data layers | |
| ############################################################ | |
| layer { | |
| name: "data_image" | |
| type: "ImageData" | |
| top: "image" | |
| top: "label_image" | |
| include { phase: TEST } | |
| image_data_param { | |
| source: "/raid/lbaraldi/scene/bbc_test_image.txt" | |
| batch_size: 100 | |
| } | |
| transform_param { | |
| mirror: true | |
| crop_size: 227 | |
| mean_file: "data/ilsvrc12/imagenet_mean.binaryproto" | |
| } | |
| } | |
| layer { | |
| name: "data_image_p" | |
| type: "ImageData" | |
| top: "image_p" | |
| top: "label_image_p" | |
| include { phase: TEST } | |
| image_data_param { | |
| source: "/raid/lbaraldi/scene/bbc_test_image_p.txt" | |
| batch_size: 100 | |
| } | |
| transform_param { | |
| mirror: true | |
| crop_size: 227 | |
| mean_file: "data/ilsvrc12/imagenet_mean.binaryproto" | |
| } | |
| } | |
| layer { | |
| name: "data_multimodal" | |
| type: "HDF5Data" | |
| top: "time" | |
| top: "time_p" | |
| top: "shot_id" | |
| top: "shot_id_p" | |
| top: "histograms" | |
| top: "histograms_p" | |
| top: "label" | |
| include { phase: TEST } | |
| hdf5_data_param { | |
| source: "/raid/lbaraldi/scene/bbc_test_h5.txt" | |
| batch_size: 100 | |
| } | |
| } | |
| ############################################################ | |
| # FIRST CONVOLUTIONAL NEURAL NETWORK | |
| ############################################################ | |
| layer { | |
| name: "conv1" | |
| type: "Convolution" | |
| bottom: "image" | |
| top: "conv1" | |
| param { | |
| name: "conv1_w" | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| name: "conv1_b" | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 96 | |
| kernel_size: 11 | |
| stride: 4 | |
| weight_filler { | |
| type: "gaussian" | |
| std: 0.01 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| } | |
| layer { | |
| name: "relu1" | |
| type: "ReLU" | |
| bottom: "conv1" | |
| top: "conv1" | |
| } | |
| layer { | |
| name: "pool1" | |
| type: "Pooling" | |
| bottom: "conv1" | |
| top: "pool1" | |
| pooling_param { | |
| pool: MAX | |
| kernel_size: 3 | |
| stride: 2 | |
| } | |
| } | |
| layer { | |
| name: "norm1" | |
| type: "LRN" | |
| bottom: "pool1" | |
| top: "norm1" | |
| lrn_param { | |
| local_size: 5 | |
| alpha: 0.0001 | |
| beta: 0.75 | |
| } | |
| } | |
| layer { | |
| name: "conv2" | |
| type: "Convolution" | |
| bottom: "norm1" | |
| top: "conv2" | |
| param { | |
| name: "conv2_w" | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| name: "conv2_b" | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 256 | |
| pad: 2 | |
| kernel_size: 5 | |
| group: 2 | |
| weight_filler { | |
| type: "gaussian" | |
| std: 0.01 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 1 | |
| } | |
| } | |
| } | |
| layer { | |
| name: "relu2" | |
| type: "ReLU" | |
| bottom: "conv2" | |
| top: "conv2" | |
| } | |
| layer { | |
| name: "pool2" | |
| type: "Pooling" | |
| bottom: "conv2" | |
| top: "pool2" | |
| pooling_param { | |
| pool: MAX | |
| kernel_size: 3 | |
| stride: 2 | |
| } | |
| } | |
| layer { | |
| name: "norm2" | |
| type: "LRN" | |
| bottom: "pool2" | |
| top: "norm2" | |
| lrn_param { | |
| local_size: 5 | |
| alpha: 0.0001 | |
| beta: 0.75 | |
| } | |
| } | |
| layer { | |
| name: "conv3" | |
| type: "Convolution" | |
| bottom: "norm2" | |
| top: "conv3" | |
| param { | |
| name: "conv3_w" | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| name: "conv3_b" | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 384 | |
| pad: 1 | |
| kernel_size: 3 | |
| weight_filler { | |
| type: "gaussian" | |
| std: 0.01 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| } | |
| layer { | |
| name: "relu3" | |
| type: "ReLU" | |
| bottom: "conv3" | |
| top: "conv3" | |
| } | |
| layer { | |
| name: "conv4" | |
| type: "Convolution" | |
| bottom: "conv3" | |
| top: "conv4" | |
| param { | |
| name: "conv4_w" | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| name: "conv4_b" | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 384 | |
| pad: 1 | |
| kernel_size: 3 | |
| group: 2 | |
| weight_filler { | |
| type: "gaussian" | |
| std: 0.01 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 1 | |
| } | |
| } | |
| } | |
| layer { | |
| name: "relu4" | |
| type: "ReLU" | |
| bottom: "conv4" | |
| top: "conv4" | |
| } | |
| layer { | |
| name: "conv5" | |
| type: "Convolution" | |
| bottom: "conv4" | |
| top: "conv5" | |
| param { | |
| name: "conv5_w" | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| name: "conv5_b" | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 256 | |
| pad: 1 | |
| kernel_size: 3 | |
| group: 2 | |
| weight_filler { | |
| type: "gaussian" | |
| std: 0.01 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 1 | |
| } | |
| } | |
| } | |
| layer { | |
| name: "relu5" | |
| type: "ReLU" | |
| bottom: "conv5" | |
| top: "conv5" | |
| } | |
| layer { | |
| name: "pool5" | |
| type: "Pooling" | |
| bottom: "conv5" | |
| top: "pool5" | |
| pooling_param { | |
| pool: MAX | |
| kernel_size: 3 | |
| stride: 2 | |
| } | |
| } | |
| layer { | |
| name: "fc6" | |
| type: "InnerProduct" | |
| bottom: "pool5" | |
| top: "fc6" | |
| param { | |
| name: "fc6_w" | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| name: "fc6_b" | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| inner_product_param { | |
| num_output: 4096 | |
| weight_filler { | |
| type: "gaussian" | |
| std: 0.005 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 1 | |
| } | |
| } | |
| } | |
| 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 { | |
| name: "fc7_w" | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| name: "fc7_b" | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| inner_product_param { | |
| num_output: 4096 | |
| weight_filler { | |
| type: "gaussian" | |
| std: 0.005 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 1 | |
| } | |
| } | |
| } | |
| 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: "fc8" | |
| type: "InnerProduct" | |
| bottom: "fc7" | |
| top: "fc8" | |
| param { | |
| name: "fc8_w" | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| name: "fc8_b" | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| inner_product_param { | |
| num_output: 1183 | |
| weight_filler { | |
| type: "gaussian" | |
| std: 0.01 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| } | |
| layer { | |
| name: "fc8_relu" | |
| type: "ReLU" | |
| bottom: "fc8" | |
| top: "fc8" | |
| } | |
| ############################################################ | |
| # SECOND CONVOLUTIONAL NEURAL NETWORK | |
| ############################################################ | |
| layer { | |
| name: "conv1_p" | |
| type: "Convolution" | |
| bottom: "image_p" | |
| top: "conv1_p" | |
| param { | |
| name: "conv1_w" | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| name: "conv1_b" | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 96 | |
| kernel_size: 11 | |
| stride: 4 | |
| weight_filler { | |
| type: "gaussian" | |
| std: 0.01 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| } | |
| layer { | |
| name: "relu1_p" | |
| type: "ReLU" | |
| bottom: "conv1_p" | |
| top: "conv1_p" | |
| } | |
| layer { | |
| name: "pool1_p" | |
| type: "Pooling" | |
| bottom: "conv1_p" | |
| top: "pool1_p" | |
| pooling_param { | |
| pool: MAX | |
| kernel_size: 3 | |
| stride: 2 | |
| } | |
| } | |
| layer { | |
| name: "norm1_p" | |
| type: "LRN" | |
| bottom: "pool1_p" | |
| top: "norm1_p" | |
| lrn_param { | |
| local_size: 5 | |
| alpha: 0.0001 | |
| beta: 0.75 | |
| } | |
| } | |
| layer { | |
| name: "conv2_p" | |
| type: "Convolution" | |
| bottom: "norm1_p" | |
| top: "conv2_p" | |
| param { | |
| name: "conv2_w" | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| name: "conv2_b" | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 256 | |
| pad: 2 | |
| kernel_size: 5 | |
| group: 2 | |
| weight_filler { | |
| type: "gaussian" | |
| std: 0.01 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 1 | |
| } | |
| } | |
| } | |
| layer { | |
| name: "relu2_p" | |
| type: "ReLU" | |
| bottom: "conv2_p" | |
| top: "conv2_p" | |
| } | |
| layer { | |
| name: "pool2_p" | |
| type: "Pooling" | |
| bottom: "conv2_p" | |
| top: "pool2_p" | |
| pooling_param { | |
| pool: MAX | |
| kernel_size: 3 | |
| stride: 2 | |
| } | |
| } | |
| layer { | |
| name: "norm2_p" | |
| type: "LRN" | |
| bottom: "pool2_p" | |
| top: "norm2_p" | |
| lrn_param { | |
| local_size: 5 | |
| alpha: 0.0001 | |
| beta: 0.75 | |
| } | |
| } | |
| layer { | |
| name: "conv3_p" | |
| type: "Convolution" | |
| bottom: "norm2_p" | |
| top: "conv3_p" | |
| param { | |
| name: "conv3_w" | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| name: "conv3_b" | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 384 | |
| pad: 1 | |
| kernel_size: 3 | |
| weight_filler { | |
| type: "gaussian" | |
| std: 0.01 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| } | |
| layer { | |
| name: "relu3_p" | |
| type: "ReLU" | |
| bottom: "conv3_p" | |
| top: "conv3_p" | |
| } | |
| layer { | |
| name: "conv4_p" | |
| type: "Convolution" | |
| bottom: "conv3_p" | |
| top: "conv4_p" | |
| param { | |
| name: "conv4_w" | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| name: "conv4_b" | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 384 | |
| pad: 1 | |
| kernel_size: 3 | |
| group: 2 | |
| weight_filler { | |
| type: "gaussian" | |
| std: 0.01 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 1 | |
| } | |
| } | |
| } | |
| layer { | |
| name: "relu4_p" | |
| type: "ReLU" | |
| bottom: "conv4_p" | |
| top: "conv4_p" | |
| } | |
| layer { | |
| name: "conv5_p" | |
| type: "Convolution" | |
| bottom: "conv4_p" | |
| top: "conv5_p" | |
| param { | |
| name: "conv5_w" | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| name: "conv5_b" | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 256 | |
| pad: 1 | |
| kernel_size: 3 | |
| group: 2 | |
| weight_filler { | |
| type: "gaussian" | |
| std: 0.01 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 1 | |
| } | |
| } | |
| } | |
| layer { | |
| name: "relu5_p" | |
| type: "ReLU" | |
| bottom: "conv5_p" | |
| top: "conv5_p" | |
| } | |
| layer { | |
| name: "pool5_p" | |
| type: "Pooling" | |
| bottom: "conv5_p" | |
| top: "pool5_p" | |
| pooling_param { | |
| pool: MAX | |
| kernel_size: 3 | |
| stride: 2 | |
| } | |
| } | |
| layer { | |
| name: "fc6_p" | |
| type: "InnerProduct" | |
| bottom: "pool5_p" | |
| top: "fc6_p" | |
| param { | |
| name: "fc6_w" | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| name: "fc6_b" | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| inner_product_param { | |
| num_output: 4096 | |
| weight_filler { | |
| type: "gaussian" | |
| std: 0.005 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 1 | |
| } | |
| } | |
| } | |
| layer { | |
| name: "relu6_p" | |
| type: "ReLU" | |
| bottom: "fc6_p" | |
| top: "fc6_p" | |
| } | |
| layer { | |
| name: "drop6_p" | |
| type: "Dropout" | |
| bottom: "fc6_p" | |
| top: "fc6_p" | |
| dropout_param { | |
| dropout_ratio: 0.5 | |
| } | |
| } | |
| layer { | |
| name: "fc7_p" | |
| type: "InnerProduct" | |
| bottom: "fc6_p" | |
| top: "fc7_p" | |
| param { | |
| name: "fc7_w" | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| name: "fc7_b" | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| inner_product_param { | |
| num_output: 4096 | |
| weight_filler { | |
| type: "gaussian" | |
| std: 0.005 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 1 | |
| } | |
| } | |
| } | |
| layer { | |
| name: "relu7_p" | |
| type: "ReLU" | |
| bottom: "fc7_p" | |
| top: "fc7_p" | |
| } | |
| layer { | |
| name: "drop7_p" | |
| type: "Dropout" | |
| bottom: "fc7_p" | |
| top: "fc7_p" | |
| dropout_param { | |
| dropout_ratio: 0.5 | |
| } | |
| } | |
| layer { | |
| name: "fc8_p" | |
| type: "InnerProduct" | |
| bottom: "fc7_p" | |
| top: "fc8_p" | |
| param { | |
| name: "fc8_w" | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| name: "fc8_b" | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| inner_product_param { | |
| num_output: 1183 | |
| weight_filler { | |
| type: "gaussian" | |
| std: 0.01 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| } | |
| layer { | |
| name: "fc8_p_relu" | |
| type: "ReLU" | |
| bottom: "fc8_p" | |
| top: "fc8_p" | |
| } | |
| ############################################################ | |
| # MERGE + LAST IP LAYERS | |
| ############################################################ | |
| layer { | |
| name: "merge" | |
| type: "Concat" | |
| bottom: "fc8" | |
| bottom: "time" | |
| bottom: "histograms" | |
| top: "merge" | |
| } | |
| layer { | |
| name: "merge_p" | |
| type: "Concat" | |
| bottom: "fc8_p" | |
| bottom: "time_p" | |
| bottom: "histograms_p" | |
| top: "merge_p" | |
| } | |
| layer { | |
| name: "fc_final" | |
| type: "InnerProduct" | |
| bottom: "merge" | |
| top: "fc_final" | |
| param { | |
| name: "fc_final_w" | |
| lr_mult: 4 # Higher learning rate since this layer is starting from random | |
| decay_mult: 1 | |
| } | |
| param { | |
| name: "fc_final_b" | |
| lr_mult: 4 # Higher learning rate since this layer is starting from random | |
| decay_mult: 0 | |
| } | |
| inner_product_param { | |
| num_output: 200 | |
| weight_filler { | |
| type: "gaussian" | |
| std: 0.01 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0.01 | |
| } | |
| } | |
| } | |
| layer { | |
| name: "fc_final_p" | |
| type: "InnerProduct" | |
| bottom: "merge_p" | |
| top: "fc_final_p" | |
| param { | |
| name: "fc_final_w" | |
| lr_mult: 4 # Higher learning rate since this layer is starting from random | |
| decay_mult: 1 | |
| } | |
| param { | |
| name: "fc_final_b" | |
| lr_mult: 4 # Higher learning rate since this layer is starting from random | |
| decay_mult: 0 | |
| } | |
| inner_product_param { | |
| num_output: 200 | |
| weight_filler { | |
| type: "gaussian" | |
| std: 0.01 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0.01 | |
| } | |
| } | |
| } | |
| ############################################################ | |
| # LOSS/ACCURACY LAYERS | |
| ############################################################ | |
| layer { | |
| name: "loss" | |
| type: "ContrastiveLoss" | |
| bottom: "fc_final" | |
| bottom: "fc_final_p" | |
| bottom: "label" | |
| top: "loss" | |
| contrastive_loss_param { | |
| margin: 1.0 | |
| } | |
| } | |
| ############################################################ | |
| # END | |
| ############################################################ | |
| layer { | |
| name: "shot_id_silence" | |
| type: "Silence" | |
| bottom: "shot_id" | |
| } | |
| layer { | |
| name: "shot_id_silence_p" | |
| type: "Silence" | |
| bottom: "shot_id_p" | |
| } | |
| layer { | |
| name: "label_image_silence" | |
| type: "Silence" | |
| bottom: "label_image" | |
| } | |
| layer { | |
| name: "label_image_silence_p" | |
| type: "Silence" | |
| bottom: "label_image_p" | |
| } |
I can't find the bbc_train_image.txt, bbc_train_image_p.txt, bbc_train_h5.txt, bbc_test_image.txt, bbc_test_image_p.txt, bbc_test_h5.txt.
Where can I find them or download them?
I am sorry to disturb you.
I have downloaded your model of scene detection in 23rd ACM International Conference on Multimedia, 2015.
However, I can't find the bbc_train_image.txt, bbc_train_image_p.txt, bbc_train_h5.txt, bbc_test_image.txt, bbc_test_image_p.txt, bbc_test_h5.txt.
Where can I find them or download them?