Finetuning CaffeNet on Flickr Style

readme.md

name	caffemodel	caffemodel_url	license	sha1	caffe_commit	gist_id
Finetuning CaffeNet on Flickr Style	finetune_flickr_style.caffemodel	http://dl.caffe.berkeleyvision.org/finetune_flickr_style.caffemodel	non-commercial	b61b5cef7d771b53b0c488e78d35ccadc073e9cf	737ea5e936821b5c69f9c3952d72693ae5843370	034c6ac3865563b69e60

This model is trained exactly as described in docs/finetune_flickr_style/readme.md, using all 80000 images. The final performance:

I1017 07:36:17.370688 31333 solver.cpp:228] Iteration 100000, loss = 0.757952
I1017 07:36:17.370730 31333 solver.cpp:247] Iteration 100000, Testing net (#0)
I1017 07:36:34.248730 31333 solver.cpp:298]     Test net output #0: accuracy = 0.3916

License

The Flickr Style dataset contains only URLs to images. Some of the images may have copyright. Training a category-recognition model for research/non-commercial use may constitute fair use of this data, but the result should not be used for commercial purposes.

solver.prototxt

net: "models/finetune_flickr_style/train_val.prototxt"
test_iter: 100
test_interval: 1000
# lr for fine-tuning should be lower than when starting from scratch
base_lr: 0.001
lr_policy: "step"
gamma: 0.1
# stepsize should also be lower, as we're closer to being done
stepsize: 20000
display: 20
max_iter: 100000
momentum: 0.9
weight_decay: 0.0005
snapshot: 10000
snapshot_prefix: "models/finetune_flickr_style/finetune_flickr_style"
# uncomment the following to default to CPU mode solving
# solver_mode: CPU

val.prototxt

name: "FlickrStyleCaffeNet"
layers {
  name: "data"
  type: IMAGE_DATA
  top: "data"
  top: "label"
  image_data_param {
    source: "data/flickr_style/train.txt"
    batch_size: 50
    new_height: 256
    new_width: 256
  }
  transform_param {
    crop_size: 227
    mean_file: "data/ilsvrc12/imagenet_mean.binaryproto"
    mirror: true
  }
  include: { phase: TRAIN }
}
layers {
  name: "data"
  type: IMAGE_DATA
  top: "data"
  top: "label"
  image_data_param {
    source: "data/flickr_style/train.txt"
    batch_size: 50
    new_height: 256
    new_width: 256
  }
  transform_param {
    crop_size: 227
    mean_file: "data/ilsvrc12/imagenet_mean.binaryproto"
    mirror: false
  }
  include: { phase: TEST }
}
layers {
  name: "conv1"
  type: CONVOLUTION
  bottom: "data"
  top: "conv1"
  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"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layers {
  name: "relu1"
  type: RELU
  bottom: "conv1"
  top: "conv1"
}
layers {
  name: "pool1"
  type: POOLING
  bottom: "conv1"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layers {
  name: "norm1"
  type: LRN
  bottom: "pool1"
  top: "norm1"
  lrn_param {
    local_size: 5
    alpha: 0.0001
    beta: 0.75
  }
}
layers {
  name: "conv2"
  type: CONVOLUTION
  bottom: "norm1"
  top: "conv2"
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 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
    }
  }
}
layers {
  name: "relu2"
  type: RELU
  bottom: "conv2"
  top: "conv2"
}
layers {
  name: "pool2"
  type: POOLING
  bottom: "conv2"
  top: "pool2"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layers {
  name: "norm2"
  type: LRN
  bottom: "pool2"
  top: "norm2"
  lrn_param {
    local_size: 5
    alpha: 0.0001
    beta: 0.75
  }
}
layers {
  name: "conv3"
  type: CONVOLUTION
  bottom: "norm2"
  top: "conv3"
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 384
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layers {
  name: "relu3"
  type: RELU
  bottom: "conv3"
  top: "conv3"
}
layers {
  name: "conv4"
  type: CONVOLUTION
  bottom: "conv3"
  top: "conv4"
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 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
    }
  }
}
layers {
  name: "relu4"
  type: RELU
  bottom: "conv4"
  top: "conv4"
}
layers {
  name: "conv5"
  type: CONVOLUTION
  bottom: "conv4"
  top: "conv5"
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 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
    }
  }
}
layers {
  name: "relu5"
  type: RELU
  bottom: "conv5"
  top: "conv5"
}
layers {
  name: "pool5"
  type: POOLING
  bottom: "conv5"
  top: "pool5"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layers {
  name: "fc6"
  type: INNER_PRODUCT
  bottom: "pool5"
  top: "fc6"
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  inner_product_param {
    num_output: 4096
    weight_filler {
      type: "gaussian"
      std: 0.005
    }
    bias_filler {
      type: "constant"
      value: 1
    }
  }
}
layers {
  name: "relu6"
  type: RELU
  bottom: "fc6"
  top: "fc6"
}
layers {
  name: "drop6"
  type: DROPOUT
  bottom: "fc6"
  top: "fc6"
  dropout_param {
    dropout_ratio: 0.5
  }
}
layers {
  name: "fc7"
  type: INNER_PRODUCT
  bottom: "fc6"
  top: "fc7"
  # Note that blobs_lr can be set to 0 to disable any fine-tuning of this, and any other, layer
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  inner_product_param {
    num_output: 4096
    weight_filler {
      type: "gaussian"
      std: 0.005
    }
    bias_filler {
      type: "constant"
      value: 1
    }
  }
}
layers {
  name: "relu7"
  type: RELU
  bottom: "fc7"
  top: "fc7"
}
layers {
  name: "drop7"
  type: DROPOUT
  bottom: "fc7"
  top: "fc7"
  dropout_param {
    dropout_ratio: 0.5
  }
}
layers {
  name: "fc8_flickr"
  type: INNER_PRODUCT
  bottom: "fc7"
  top: "fc8_flickr"
  # blobs_lr is set to higher than for other layers, because this layer is starting from random while the others are already trained
  blobs_lr: 10
  blobs_lr: 20
  weight_decay: 1
  weight_decay: 0
  inner_product_param {
    num_output: 20
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layers {
  name: "loss"
  type: SOFTMAX_LOSS
  bottom: "fc8_flickr"
  bottom: "label"
}
layers {
  name: "accuracy"
  type: ACCURACY
  bottom: "fc8_flickr"
  bottom: "label"
  top: "accuracy"
  include: { phase: TEST }
}

Is the accuracy in this pretrained model 0.3916 only?

how about top5 error rate?

Why do you have 'source: "data/flickr_style/train.txt"' in both TRAIN phase and TEST phase in val.prototxt?