add feature learning models

brujorpt · Dec 3, 2016 · 1b74812 · 1b74812
1 parent 3c43aed
commit 1b74812
Show file tree

Hide file tree

Showing 5 changed files with 561 additions and 0 deletions.
diff --git a/README.md b/README.md
@@ -8,6 +8,7 @@
 This repository contains:
  - (1) a test time demonstration using a pre-trained colorization network (in IPython notebook)
  - (2) code for training a colorization network
+ - (3) pre-trained AlexNet, used for representation learning tests
 
 ### Clone this repository ###
 Clone the master branch of the respository using `git clone -b master --single-branch https://github.com/richzhang/colorization.git`
@@ -51,6 +52,14 @@ If you do this, link your modified Caffe build as `./caffe-colorization` in the
 
 For completeness, this will also load model `./models/colorization_release_v2_norebal.caffemodel`, which is was trained without class rebalancing. This model will provide duller but "safer" colorizations. This will also load model `./models/colorization_release_v1.caffemodel`, which was used to generate the results in the [arXiv v1](arxiv.org/pdf/1603.08511v1.pdf) paper.
 
+### (3) Representation Learning models ###
+
+(1) Run `./models/fetch_alexnet_model.sh`. load model `./models/alexnet_release_450000_nobn_fc_rs.caffemodel`. This model was used for the representation learning tests.
+
+(2) You have two choices.
+(i) If you do the color conversion into Lab space outside of the network, use prototxt `./models/alexnet_deploy_lab.prototxt`. The input blob will be an image in Lab color space
+(ii) If you wish to do the color conversion inside of the network, use prototxt `./models/alexnet_deploy.prototxt`. The input should be BGR images, non-mean centered, in [0,255]. You will have to follow Caffe installation (described in step (2) in the previous section).
+
 ### Citation ###
 If you find this model useful for your resesarch, please use this [bibtex](http://richzhang.github.io/colorization/resources/bibtex_eccv2016_colorization.txt) to cite.
 

diff --git a/models/alexnet_deploy.prototxt b/models/alexnet_deploy.prototxt
@@ -0,0 +1,275 @@
+name: "Colornet"
+layer {
+  name: "data"
+  top: "data" # BGR [0,255] ***non-mean centered***
+  type: "Input"
+  input_param { shape { dim: 1 dim: 3 dim: 227 dim: 227 } }
+}
+# **************************
+# ***** PROCESS COLORS *****
+# **************************
+layer { # Convert to lab
+  name: "img_lab"
+  type: "ColorConv"
+  bottom: "data"
+  top: "img_lab"
+  propagate_down: false
+  color_conv_param {
+    input: 0 # BGR
+    output: 3 # Lab
+  }
+}
+layer {
+  name: "img_slice"
+  type: "Slice"
+  bottom: "img_lab"
+  top: "img_l" # [0,100]
+  top: "data_ab" # [-110,110]
+  propagate_down: false
+  slice_param {
+    axis: 1
+    slice_point: 1
+  }
+}
+layer {
+  name: "silence_ab"
+  type: "Silence"
+  bottom: "data_ab"
+}
+layer { # 0-center lightness channel
+  name: "data_l"
+  type: "Convolution"
+  bottom: "img_l"
+  top: "data_l" # scaled and centered lightness value
+  propagate_down: false
+  param {lr_mult: 0 decay_mult: 0}
+  param {lr_mult: 0 decay_mult: 0}
+  convolution_param {
+    kernel_size: 1
+    num_output: 1
+  }
+}
+layer {
+  name: "conv1"
+  type: "Convolution"
+  bottom: "data_l"
+  top: "conv1"
+  param {    lr_mult: 1    decay_mult: 1  }
+  param {    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: "conv2"
+  type: "Convolution"
+  bottom: "pool1"
+  top: "conv2"
+  param {    lr_mult: 1    decay_mult: 1  }
+  param {    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: "conv3"
+  type: "Convolution"
+  bottom: "pool2"
+  top: "conv3"
+  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: "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 {    lr_mult: 1    decay_mult: 1  }
+  param {    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 {    lr_mult: 1    decay_mult: 1  }
+  param {    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 {    lr_mult: 1    decay_mult: 1  }
+  param {    lr_mult: 2    decay_mult: 0  }
+  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    decay_mult: 1  }
+  param {    lr_mult: 2    decay_mult: 0  }
+  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
+  }
+}
+