Network In Network

readme.md

NIN-Imagenet: a small(29MB) model for imagenet, yet performs slightly better than AlexNet, and fast to train. (Note: a more caffe-compatible version with correct convolutional weights shape: https://drive.google.com/folderview?id=0B0IedYUunOQINEFtUi1QNWVhVVU&usp=drive_web)

Time Performance comparison without GPU:

CPU: Intel® Core™ i7-4790 CPU @ 3.60GHz × 8
BLAS: MKL

Alexnet:

Average Forward pass: 175.213 ms.
Average Backward pass: 201.576 ms.
Average Forward-Backward: 376.84 ms.

Network In Network

Average Forward pass: 186.398 ms.
Average Backward pass: 151.068 ms.
Average Forward-Backward: 337.52 ms.

[GoogleNet] (https://github.com/BVLC/caffe/tree/master/models/bvlc_googlenet?utm_content=buffer3208a&utm_medium=social&utm_source=plus.google.com&utm_campaign=buffer)

Average Forward pass: 875.507 ms.
Average Backward pass: 396.282 ms.
Average Forward-Backward: 1271.9 ms.

[VGG16] (https://gist.github.com/jimmie33/27c1c0a7736ba66c2395)

Bad performance for training and testing.

 Average Forward pass: 2551.37 ms.
 Average Backward pass: 2138.39 ms.
 Average Forward-Backward: 4689.82 ms.

VGG_CNN_S

 Average Forward pass: 543.115 ms.
 Average Backward pass: 616.355 ms.
 Average Forward-Backward: 1159.52 ms.

deploy.prototxt

name: "nin_imagenet"
input: "data"
input_shape {
  dim: 10
  dim: 3
  dim: 224
  dim: 224
}
layers {
  bottom: "data"
  top: "conv1"
  name: "conv1"
  type: CONVOLUTION
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 96
    kernel_size: 11
    stride: 4
    weight_filler {
      type: "gaussian"
      mean: 0
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layers {
  bottom: "conv1"
  top: "conv1"
  name: "relu0"
  type: RELU
}
layers {
  bottom: "conv1"
  top: "cccp1"
  name: "cccp1"
  type: CONVOLUTION
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 96
    kernel_size: 1
    stride: 1
    weight_filler {
      type: "gaussian"
      mean: 0
      std: 0.05
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layers {
  bottom: "cccp1"
  top: "cccp1"
  name: "relu1"
  type: RELU
}
layers {
  bottom: "cccp1"
  top: "cccp2"
  name: "cccp2"
  type: CONVOLUTION
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 96
    kernel_size: 1
    stride: 1
    weight_filler {
      type: "gaussian"
      mean: 0
      std: 0.05
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layers {
  bottom: "cccp2"
  top: "cccp2"
  name: "relu2"
  type: RELU
}
layers {
  bottom: "cccp2"
  top: "pool0"
  name: "pool0"
  type: POOLING
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layers {
  bottom: "pool0"
  top: "conv2"
  name: "conv2"
  type: CONVOLUTION
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 256
    pad: 2
    kernel_size: 5
    stride: 1
    weight_filler {
      type: "gaussian"
      mean: 0
      std: 0.05
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layers {
  bottom: "conv2"
  top: "conv2"
  name: "relu3"
  type: RELU
}
layers {
  bottom: "conv2"
  top: "cccp3"
  name: "cccp3"
  type: CONVOLUTION
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 256
    kernel_size: 1
    stride: 1
    weight_filler {
      type: "gaussian"
      mean: 0
      std: 0.05
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layers {
  bottom: "cccp3"
  top: "cccp3"
  name: "relu5"
  type: RELU
}
layers {
  bottom: "cccp3"
  top: "cccp4"
  name: "cccp4"
  type: CONVOLUTION
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 256
    kernel_size: 1
    stride: 1
    weight_filler {
      type: "gaussian"
      mean: 0
      std: 0.05
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layers {
  bottom: "cccp4"
  top: "cccp4"
  name: "relu6"
  type: RELU
}
layers {
  bottom: "cccp4"
  top: "pool2"
  name: "pool2"
  type: POOLING
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layers {
  bottom: "pool2"
  top: "conv3"
  name: "conv3"
  type: CONVOLUTION
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 384
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "gaussian"
      mean: 0
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layers {
  bottom: "conv3"
  top: "conv3"
  name: "relu7"
  type: RELU
}
layers {
  bottom: "conv3"
  top: "cccp5"
  name: "cccp5"
  type: CONVOLUTION
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 384
    kernel_size: 1
    stride: 1
    weight_filler {
      type: "gaussian"
      mean: 0
      std: 0.05
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layers {
  bottom: "cccp5"
  top: "cccp5"
  name: "relu8"
  type: RELU
}
layers {
  bottom: "cccp5"
  top: "cccp6"
  name: "cccp6"
  type: CONVOLUTION
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 384
    kernel_size: 1
    stride: 1
    weight_filler {
      type: "gaussian"
      mean: 0
      std: 0.05
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layers {
  bottom: "cccp6"
  top: "cccp6"
  name: "relu9"
  type: RELU
}
layers {
  bottom: "cccp6"
  top: "pool3"
  name: "pool3"
  type: POOLING
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layers {
  bottom: "pool3"
  top: "pool3"
  name: "drop"
  type: DROPOUT
  dropout_param {
    dropout_ratio: 0.5
  }
}
layers {
  bottom: "pool3"
  top: "conv4"
  name: "conv4"
  type: CONVOLUTION
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 1024
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "gaussian"
      mean: 0
      std: 0.05
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layers {
  bottom: "conv4"
  top: "conv4"
  name: "relu10"
  type: RELU
}
layers {
  bottom: "conv4"
  top: "cccp7"
  name: "cccp7"
  type: CONVOLUTION
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 1024
    kernel_size: 1
    stride: 1
    weight_filler {
      type: "gaussian"
      mean: 0
      std: 0.05
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layers {
  bottom: "cccp7"
  top: "cccp7"
  name: "relu11"
  type: RELU
}
layers {
  bottom: "cccp7"
  top: "cccp8"
  name: "cccp8"
  type: CONVOLUTION
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 1000
    kernel_size: 1
    stride: 1
    weight_filler {
      type: "gaussian"
      mean: 0
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layers {
  bottom: "cccp8"
  top: "cccp8"
  name: "relu12"
  type: RELU
}
layers {
  bottom: "cccp8"
  top: "pool4"
  name: "pool4"
  type: POOLING
  pooling_param {
    pool: AVE
    kernel_size: 6
    stride: 1
  }
}