Add VGG networks.

data/download_models.sh

@@ -5,8 +5,11 @@ cd "$(dirname "${BASH_SOURCE[0]}")" || (echo "Could not change dir" && exit 1)
 pwd
 
 for modeldir in models/*; do
-	pushd "$modeldir"
+	if ! pushd "$modeldir" &>/dev/null; then
+		continue
+	fi
+
 	wget --continue -i weights_url -N
-	popd
+	popd || exit 1
 done
 

data/models/README.md

@@ -0,0 +1,53 @@
+# FMRI example models
+
+The following sections describe the models included in this repository,
+with attribution. The repository also includes deinplaced versions of
+the models, where relevant.
+
+## alexnet
+
+AlexNet trained on ILSVRC 2012, almost exactly as described in ImageNet
+classification with deep convolutional neural networks by Krizhevsky et
+al. in NIPS 2012. (Trained by Evan Shelhamer @shelhamer)
+
+## caffenet
+
+AlexNet trained on ILSVRC 2012, with a minor variation from the version
+as described in ImageNet classification with deep convolutional neural
+networks by Krizhevsky et al. in NIPS 2012. (Trained by Jeff Donahue
+@jeffdonahue)
+
+## vgg-16
+
+The model is an improved version of the 16-layer model used by the VGG
+team in the ILSVRC-2014 competition. The details can be found in the
+following [arXiv paper](http://arxiv.org/pdf/1409.1556):
+
+    Very Deep Convolutional Networks for Large-Scale Image Recognition
+    K. Simonyan, A. Zisserman
+    arXiv:1409.1556
+
+Please cite the paper if you use the model.
+
+In the paper, the model is denoted as the configuration `D` trained with
+scale jittering. The input images should be zero-centered by mean pixel
+(rather than mean image) subtraction. Namely, the following BGR values
+should be subtracted: `[103.939, 116.779, 123.68]`.
+
+
+## vgg-19
+
+The model is an improved version of the 19-layer model used by the VGG
+team in the ILSVRC-2014 competition. The details can be found in the
+following [arXiv paper](http://arxiv.org/pdf/1409.1556):
+
+    Very Deep Convolutional Networks for Large-Scale Image Recognition
+    K. Simonyan, A. Zisserman
+    arXiv:1409.1556
+
+Please cite the paper if you use the model.
+
+In the paper, the model is denoted as the configuration `E` trained with
+scale jittering. The input images should be zero-centered by mean pixel
+(rather than mean image) subtraction. Namely, the following BGR values
+should be subtracted: `[103.939, 116.779, 123.68]`.

data/models/vgg-16/model-dedup.prototxt

@@ -0,0 +1,345 @@
+name: "VGG_ILSVRC_16_layers"
+layers {
+  bottom: "data"
+  top: "conv1_1"
+  name: "conv1_1"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 64
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv1_1"
+  top: "relu1_1"
+  name: "relu1_1"
+  type: RELU
+}
+layers {
+  bottom: "relu1_1"
+  top: "conv1_2"
+  name: "conv1_2"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 64
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv1_2"
+  top: "relu1_2"
+  name: "relu1_2"
+  type: RELU
+}
+layers {
+  bottom: "relu1_2"
+  top: "pool1"
+  name: "pool1"
+  type: POOLING
+  pooling_param {
+    pool: MAX
+    kernel_size: 2
+    stride: 2
+  }
+}
+layers {
+  bottom: "pool1"
+  top: "conv2_1"
+  name: "conv2_1"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 128
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv2_1"
+  top: "relu2_1"
+  name: "relu2_1"
+  type: RELU
+}
+layers {
+  bottom: "relu2_1"
+  top: "conv2_2"
+  name: "conv2_2"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 128
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv2_2"
+  top: "relu2_2"
+  name: "relu2_2"
+  type: RELU
+}
+layers {
+  bottom: "relu2_2"
+  top: "pool2"
+  name: "pool2"
+  type: POOLING
+  pooling_param {
+    pool: MAX
+    kernel_size: 2
+    stride: 2
+  }
+}
+layers {
+  bottom: "pool2"
+  top: "conv3_1"
+  name: "conv3_1"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 256
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv3_1"
+  top: "relu3_1"
+  name: "relu3_1"
+  type: RELU
+}
+layers {
+  bottom: "relu3_1"
+  top: "conv3_2"
+  name: "conv3_2"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 256
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv3_2"
+  top: "relu3_2"
+  name: "relu3_2"
+  type: RELU
+}
+layers {
+  bottom: "relu3_2"
+  top: "conv3_3"
+  name: "conv3_3"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 256
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv3_3"
+  top: "relu3_3"
+  name: "relu3_3"
+  type: RELU
+}
+layers {
+  bottom: "relu3_3"
+  top: "pool3"
+  name: "pool3"
+  type: POOLING
+  pooling_param {
+    pool: MAX
+    kernel_size: 2
+    stride: 2
+  }
+}
+layers {
+  bottom: "pool3"
+  top: "conv4_1"
+  name: "conv4_1"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv4_1"
+  top: "relu4_1"
+  name: "relu4_1"
+  type: RELU
+}
+layers {
+  bottom: "relu4_1"
+  top: "conv4_2"
+  name: "conv4_2"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv4_2"
+  top: "relu4_2"
+  name: "relu4_2"
+  type: RELU
+}
+layers {
+  bottom: "relu4_2"
+  top: "conv4_3"
+  name: "conv4_3"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv4_3"
+  top: "relu4_3"
+  name: "relu4_3"
+  type: RELU
+}
+layers {
+  bottom: "relu4_3"
+  top: "pool4"
+  name: "pool4"
+  type: POOLING
+  pooling_param {
+    pool: MAX
+    kernel_size: 2
+    stride: 2
+  }
+}
+layers {
+  bottom: "pool4"
+  top: "conv5_1"
+  name: "conv5_1"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv5_1"
+  top: "relu5_1"
+  name: "relu5_1"
+  type: RELU
+}
+layers {
+  bottom: "relu5_1"
+  top: "conv5_2"
+  name: "conv5_2"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv5_2"
+  top: "relu5_2"
+  name: "relu5_2"
+  type: RELU
+}
+layers {
+  bottom: "relu5_2"
+  top: "conv5_3"
+  name: "conv5_3"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv5_3"
+  top: "relu5_3"
+  name: "relu5_3"
+  type: RELU
+}
+layers {
+  bottom: "relu5_3"
+  top: "pool5"
+  name: "pool5"
+  type: POOLING
+  pooling_param {
+    pool: MAX
+    kernel_size: 2
+    stride: 2
+  }
+}
+layers {
+  bottom: "pool5"
+  top: "fc6"
+  name: "fc6"
+  type: INNER_PRODUCT
+  inner_product_param {
+    num_output: 4096
+  }
+}
+layers {
+  bottom: "fc6"
+  top: "relu6"
+  name: "relu6"
+  type: RELU
+}
+layers {
+  bottom: "relu6"
+  top: "drop6"
+  name: "drop6"
+  type: DROPOUT
+  dropout_param {
+    dropout_ratio: 0.5
+  }
+}
+layers {
+  bottom: "drop6"
+  top: "fc7"
+  name: "fc7"
+  type: INNER_PRODUCT
+  inner_product_param {
+    num_output: 4096
+  }
+}
+layers {
+  bottom: "fc7"
+  top: "relu7"
+  name: "relu7"
+  type: RELU
+}
+layers {
+  bottom: "relu7"
+  top: "drop7"
+  name: "drop7"
+  type: DROPOUT
+  dropout_param {
+    dropout_ratio: 0.5
+  }
+}
+layers {
+  bottom: "drop7"
+  top: "fc8"
+  name: "fc8"
+  type: INNER_PRODUCT
+  inner_product_param {
+    num_output: 1000
+  }
+}
+layers {
+  bottom: "fc8"
+  top: "prob"
+  name: "prob"
+  type: SOFTMAX
+}
+input: "data"
+input_dim: 10
+input_dim: 3
+input_dim: 224
+input_dim: 224

data/models/vgg-16/model.prototxt

@@ -0,0 +1,345 @@
+name: "VGG_ILSVRC_16_layers"
+input: "data"
+input_dim: 10
+input_dim: 3
+input_dim: 224
+input_dim: 224
+layers {
+  bottom: "data"
+  top: "conv1_1"
+  name: "conv1_1"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 64
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv1_1"
+  top: "conv1_1"
+  name: "relu1_1"
+  type: RELU
+}
+layers {
+  bottom: "conv1_1"
+  top: "conv1_2"
+  name: "conv1_2"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 64
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv1_2"
+  top: "conv1_2"
+  name: "relu1_2"
+  type: RELU
+}
+layers {
+  bottom: "conv1_2"
+  top: "pool1"
+  name: "pool1"
+  type: POOLING
+  pooling_param {
+    pool: MAX
+    kernel_size: 2
+    stride: 2
+  }
+}
+layers {
+  bottom: "pool1"
+  top: "conv2_1"
+  name: "conv2_1"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 128
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv2_1"
+  top: "conv2_1"
+  name: "relu2_1"
+  type: RELU
+}
+layers {
+  bottom: "conv2_1"
+  top: "conv2_2"
+  name: "conv2_2"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 128
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv2_2"
+  top: "conv2_2"
+  name: "relu2_2"
+  type: RELU
+}
+layers {
+  bottom: "conv2_2"
+  top: "pool2"
+  name: "pool2"
+  type: POOLING
+  pooling_param {
+    pool: MAX
+    kernel_size: 2
+    stride: 2
+  }
+}
+layers {
+  bottom: "pool2"
+  top: "conv3_1"
+  name: "conv3_1"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 256
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv3_1"
+  top: "conv3_1"
+  name: "relu3_1"
+  type: RELU
+}
+layers {
+  bottom: "conv3_1"
+  top: "conv3_2"
+  name: "conv3_2"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 256
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv3_2"
+  top: "conv3_2"
+  name: "relu3_2"
+  type: RELU
+}
+layers {
+  bottom: "conv3_2"
+  top: "conv3_3"
+  name: "conv3_3"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 256
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv3_3"
+  top: "conv3_3"
+  name: "relu3_3"
+  type: RELU
+}
+layers {
+  bottom: "conv3_3"
+  top: "pool3"
+  name: "pool3"
+  type: POOLING
+  pooling_param {
+    pool: MAX
+    kernel_size: 2
+    stride: 2
+  }
+}
+layers {
+  bottom: "pool3"
+  top: "conv4_1"
+  name: "conv4_1"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv4_1"
+  top: "conv4_1"
+  name: "relu4_1"
+  type: RELU
+}
+layers {
+  bottom: "conv4_1"
+  top: "conv4_2"
+  name: "conv4_2"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv4_2"
+  top: "conv4_2"
+  name: "relu4_2"
+  type: RELU
+}
+layers {
+  bottom: "conv4_2"
+  top: "conv4_3"
+  name: "conv4_3"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv4_3"
+  top: "conv4_3"
+  name: "relu4_3"
+  type: RELU
+}
+layers {
+  bottom: "conv4_3"
+  top: "pool4"
+  name: "pool4"
+  type: POOLING
+  pooling_param {
+    pool: MAX
+    kernel_size: 2
+    stride: 2
+  }
+}
+layers {
+  bottom: "pool4"
+  top: "conv5_1"
+  name: "conv5_1"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv5_1"
+  top: "conv5_1"
+  name: "relu5_1"
+  type: RELU
+}
+layers {
+  bottom: "conv5_1"
+  top: "conv5_2"
+  name: "conv5_2"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv5_2"
+  top: "conv5_2"
+  name: "relu5_2"
+  type: RELU
+}
+layers {
+  bottom: "conv5_2"
+  top: "conv5_3"
+  name: "conv5_3"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv5_3"
+  top: "conv5_3"
+  name: "relu5_3"
+  type: RELU
+}
+layers {
+  bottom: "conv5_3"
+  top: "pool5"
+  name: "pool5"
+  type: POOLING
+  pooling_param {
+    pool: MAX
+    kernel_size: 2
+    stride: 2
+  }
+}
+layers {
+  bottom: "pool5"
+  top: "fc6"
+  name: "fc6"
+  type: INNER_PRODUCT
+  inner_product_param {
+    num_output: 4096
+  }
+}
+layers {
+  bottom: "fc6"
+  top: "fc6"
+  name: "relu6"
+  type: RELU
+}
+layers {
+  bottom: "fc6"
+  top: "fc6"
+  name: "drop6"
+  type: DROPOUT
+  dropout_param {
+    dropout_ratio: 0.5
+  }
+}
+layers {
+  bottom: "fc6"
+  top: "fc7"
+  name: "fc7"
+  type: INNER_PRODUCT
+  inner_product_param {
+    num_output: 4096
+  }
+}
+layers {
+  bottom: "fc7"
+  top: "fc7"
+  name: "relu7"
+  type: RELU
+}
+layers {
+  bottom: "fc7"
+  top: "fc7"
+  name: "drop7"
+  type: DROPOUT
+  dropout_param {
+    dropout_ratio: 0.5
+  }
+}
+layers {
+  bottom: "fc7"
+  top: "fc8"
+  name: "fc8"
+  type: INNER_PRODUCT
+  inner_product_param {
+    num_output: 1000
+  }
+}
+layers {
+  bottom: "fc8"
+  top: "prob"
+  name: "prob"
+  type: SOFTMAX
+}

data/models/vgg-16/weights_url

@@ -0,0 +1 @@
+http://www.robots.ox.ac.uk/~vgg/software/very_deep/caffe/VGG_ILSVRC_16_layers.caffemodel

data/models/vgg-19/model-dedup.prototxt

@@ -0,0 +1,396 @@
+name: "VGG_ILSVRC_19_layers"
+layers {
+  bottom: "data"
+  top: "conv1_1"
+  name: "conv1_1"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 64
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv1_1"
+  top: "relu1_1"
+  name: "relu1_1"
+  type: RELU
+}
+layers {
+  bottom: "relu1_1"
+  top: "conv1_2"
+  name: "conv1_2"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 64
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv1_2"
+  top: "relu1_2"
+  name: "relu1_2"
+  type: RELU
+}
+layers {
+  bottom: "relu1_2"
+  top: "pool1"
+  name: "pool1"
+  type: POOLING
+  pooling_param {
+    pool: MAX
+    kernel_size: 2
+    stride: 2
+  }
+}
+layers {
+  bottom: "pool1"
+  top: "conv2_1"
+  name: "conv2_1"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 128
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv2_1"
+  top: "relu2_1"
+  name: "relu2_1"
+  type: RELU
+}
+layers {
+  bottom: "relu2_1"
+  top: "conv2_2"
+  name: "conv2_2"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 128
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv2_2"
+  top: "relu2_2"
+  name: "relu2_2"
+  type: RELU
+}
+layers {
+  bottom: "relu2_2"
+  top: "pool2"
+  name: "pool2"
+  type: POOLING
+  pooling_param {
+    pool: MAX
+    kernel_size: 2
+    stride: 2
+  }
+}
+layers {
+  bottom: "pool2"
+  top: "conv3_1"
+  name: "conv3_1"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 256
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv3_1"
+  top: "relu3_1"
+  name: "relu3_1"
+  type: RELU
+}
+layers {
+  bottom: "relu3_1"
+  top: "conv3_2"
+  name: "conv3_2"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 256
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv3_2"
+  top: "relu3_2"
+  name: "relu3_2"
+  type: RELU
+}
+layers {
+  bottom: "relu3_2"
+  top: "conv3_3"
+  name: "conv3_3"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 256
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv3_3"
+  top: "relu3_3"
+  name: "relu3_3"
+  type: RELU
+}
+layers {
+  bottom: "relu3_3"
+  top: "conv3_4"
+  name: "conv3_4"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 256
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv3_4"
+  top: "relu3_4"
+  name: "relu3_4"
+  type: RELU
+}
+layers {
+  bottom: "relu3_4"
+  top: "pool3"
+  name: "pool3"
+  type: POOLING
+  pooling_param {
+    pool: MAX
+    kernel_size: 2
+    stride: 2
+  }
+}
+layers {
+  bottom: "pool3"
+  top: "conv4_1"
+  name: "conv4_1"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv4_1"
+  top: "relu4_1"
+  name: "relu4_1"
+  type: RELU
+}
+layers {
+  bottom: "relu4_1"
+  top: "conv4_2"
+  name: "conv4_2"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv4_2"
+  top: "relu4_2"
+  name: "relu4_2"
+  type: RELU
+}
+layers {
+  bottom: "relu4_2"
+  top: "conv4_3"
+  name: "conv4_3"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv4_3"
+  top: "relu4_3"
+  name: "relu4_3"
+  type: RELU
+}
+layers {
+  bottom: "relu4_3"
+  top: "conv4_4"
+  name: "conv4_4"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv4_4"
+  top: "relu4_4"
+  name: "relu4_4"
+  type: RELU
+}
+layers {
+  bottom: "relu4_4"
+  top: "pool4"
+  name: "pool4"
+  type: POOLING
+  pooling_param {
+    pool: MAX
+    kernel_size: 2
+    stride: 2
+  }
+}
+layers {
+  bottom: "pool4"
+  top: "conv5_1"
+  name: "conv5_1"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv5_1"
+  top: "relu5_1"
+  name: "relu5_1"
+  type: RELU
+}
+layers {
+  bottom: "relu5_1"
+  top: "conv5_2"
+  name: "conv5_2"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv5_2"
+  top: "relu5_2"
+  name: "relu5_2"
+  type: RELU
+}
+layers {
+  bottom: "relu5_2"
+  top: "conv5_3"
+  name: "conv5_3"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv5_3"
+  top: "relu5_3"
+  name: "relu5_3"
+  type: RELU
+}
+layers {
+  bottom: "relu5_3"
+  top: "conv5_4"
+  name: "conv5_4"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv5_4"
+  top: "relu5_4"
+  name: "relu5_4"
+  type: RELU
+}
+layers {
+  bottom: "relu5_4"
+  top: "pool5"
+  name: "pool5"
+  type: POOLING
+  pooling_param {
+    pool: MAX
+    kernel_size: 2
+    stride: 2
+  }
+}
+layers {
+  bottom: "pool5"
+  top: "fc6"
+  name: "fc6"
+  type: INNER_PRODUCT
+  inner_product_param {
+    num_output: 4096
+  }
+}
+layers {
+  bottom: "fc6"
+  top: "relu6"
+  name: "relu6"
+  type: RELU
+}
+layers {
+  bottom: "relu6"
+  top: "drop6"
+  name: "drop6"
+  type: DROPOUT
+  dropout_param {
+    dropout_ratio: 0.5
+  }
+}
+layers {
+  bottom: "drop6"
+  top: "fc7"
+  name: "fc7"
+  type: INNER_PRODUCT
+  inner_product_param {
+    num_output: 4096
+  }
+}
+layers {
+  bottom: "fc7"
+  top: "relu7"
+  name: "relu7"
+  type: RELU
+}
+layers {
+  bottom: "relu7"
+  top: "drop7"
+  name: "drop7"
+  type: DROPOUT
+  dropout_param {
+    dropout_ratio: 0.5
+  }
+}
+layers {
+  bottom: "drop7"
+  top: "fc8"
+  name: "fc8"
+  type: INNER_PRODUCT
+  inner_product_param {
+    num_output: 1000
+  }
+}
+layers {
+  bottom: "fc8"
+  top: "prob"
+  name: "prob"
+  type: SOFTMAX
+}
+input: "data"
+input_dim: 10
+input_dim: 3
+input_dim: 224
+input_dim: 224

data/models/vgg-19/model.prototxt

@@ -0,0 +1,396 @@
+name: "VGG_ILSVRC_19_layers"
+input: "data"
+input_dim: 10
+input_dim: 3
+input_dim: 224
+input_dim: 224
+layers {
+  bottom: "data"
+  top: "conv1_1"
+  name: "conv1_1"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 64
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv1_1"
+  top: "conv1_1"
+  name: "relu1_1"
+  type: RELU
+}
+layers {
+  bottom: "conv1_1"
+  top: "conv1_2"
+  name: "conv1_2"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 64
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv1_2"
+  top: "conv1_2"
+  name: "relu1_2"
+  type: RELU
+}
+layers {
+  bottom: "conv1_2"
+  top: "pool1"
+  name: "pool1"
+  type: POOLING
+  pooling_param {
+    pool: MAX
+    kernel_size: 2
+    stride: 2
+  }
+}
+layers {
+  bottom: "pool1"
+  top: "conv2_1"
+  name: "conv2_1"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 128
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv2_1"
+  top: "conv2_1"
+  name: "relu2_1"
+  type: RELU
+}
+layers {
+  bottom: "conv2_1"
+  top: "conv2_2"
+  name: "conv2_2"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 128
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv2_2"
+  top: "conv2_2"
+  name: "relu2_2"
+  type: RELU
+}
+layers {
+  bottom: "conv2_2"
+  top: "pool2"
+  name: "pool2"
+  type: POOLING
+  pooling_param {
+    pool: MAX
+    kernel_size: 2
+    stride: 2
+  }
+}
+layers {
+  bottom: "pool2"
+  top: "conv3_1"
+  name: "conv3_1"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 256
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv3_1"
+  top: "conv3_1"
+  name: "relu3_1"
+  type: RELU
+}
+layers {
+  bottom: "conv3_1"
+  top: "conv3_2"
+  name: "conv3_2"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 256
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv3_2"
+  top: "conv3_2"
+  name: "relu3_2"
+  type: RELU
+}
+layers {
+  bottom: "conv3_2"
+  top: "conv3_3"
+  name: "conv3_3"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 256
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv3_3"
+  top: "conv3_3"
+  name: "relu3_3"
+  type: RELU
+}
+layers {
+  bottom: "conv3_3"
+  top: "conv3_4"
+  name: "conv3_4"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 256
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv3_4"
+  top: "conv3_4"
+  name: "relu3_4"
+  type: RELU
+}
+layers {
+  bottom: "conv3_4"
+  top: "pool3"
+  name: "pool3"
+  type: POOLING
+  pooling_param {
+    pool: MAX
+    kernel_size: 2
+    stride: 2
+  }
+}
+layers {
+  bottom: "pool3"
+  top: "conv4_1"
+  name: "conv4_1"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv4_1"
+  top: "conv4_1"
+  name: "relu4_1"
+  type: RELU
+}
+layers {
+  bottom: "conv4_1"
+  top: "conv4_2"
+  name: "conv4_2"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv4_2"
+  top: "conv4_2"
+  name: "relu4_2"
+  type: RELU
+}
+layers {
+  bottom: "conv4_2"
+  top: "conv4_3"
+  name: "conv4_3"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv4_3"
+  top: "conv4_3"
+  name: "relu4_3"
+  type: RELU
+}
+layers {
+  bottom: "conv4_3"
+  top: "conv4_4"
+  name: "conv4_4"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv4_4"
+  top: "conv4_4"
+  name: "relu4_4"
+  type: RELU
+}
+layers {
+  bottom: "conv4_4"
+  top: "pool4"
+  name: "pool4"
+  type: POOLING
+  pooling_param {
+    pool: MAX
+    kernel_size: 2
+    stride: 2
+  }
+}
+layers {
+  bottom: "pool4"
+  top: "conv5_1"
+  name: "conv5_1"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv5_1"
+  top: "conv5_1"
+  name: "relu5_1"
+  type: RELU
+}
+layers {
+  bottom: "conv5_1"
+  top: "conv5_2"
+  name: "conv5_2"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv5_2"
+  top: "conv5_2"
+  name: "relu5_2"
+  type: RELU
+}
+layers {
+  bottom: "conv5_2"
+  top: "conv5_3"
+  name: "conv5_3"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv5_3"
+  top: "conv5_3"
+  name: "relu5_3"
+  type: RELU
+}
+layers {
+  bottom: "conv5_3"
+  top: "conv5_4"
+  name: "conv5_4"
+  type: CONVOLUTION
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+  }
+}
+layers {
+  bottom: "conv5_4"
+  top: "conv5_4"
+  name: "relu5_4"
+  type: RELU
+}
+layers {
+  bottom: "conv5_4"
+  top: "pool5"
+  name: "pool5"
+  type: POOLING
+  pooling_param {
+    pool: MAX
+    kernel_size: 2
+    stride: 2
+  }
+}
+layers {
+  bottom: "pool5"
+  top: "fc6"
+  name: "fc6"
+  type: INNER_PRODUCT
+  inner_product_param {
+    num_output: 4096
+  }
+}
+layers {
+  bottom: "fc6"
+  top: "fc6"
+  name: "relu6"
+  type: RELU
+}
+layers {
+  bottom: "fc6"
+  top: "fc6"
+  name: "drop6"
+  type: DROPOUT
+  dropout_param {
+    dropout_ratio: 0.5
+  }
+}
+layers {
+  bottom: "fc6"
+  top: "fc7"
+  name: "fc7"
+  type: INNER_PRODUCT
+  inner_product_param {
+    num_output: 4096
+  }
+}
+layers {
+  bottom: "fc7"
+  top: "fc7"
+  name: "relu7"
+  type: RELU
+}
+layers {
+  bottom: "fc7"
+  top: "fc7"
+  name: "drop7"
+  type: DROPOUT
+  dropout_param {
+    dropout_ratio: 0.5
+  }
+}
+layers {
+  bottom: "fc7"
+  top: "fc8"
+  name: "fc8"
+  type: INNER_PRODUCT
+  inner_product_param {
+    num_output: 1000
+  }
+}
+layers {
+  bottom: "fc8"
+  top: "prob"
+  name: "prob"
+  type: SOFTMAX
+}

data/models/vgg-19/weights_url

@@ -0,0 +1 @@
+http://www.robots.ox.ac.uk/~vgg/software/very_deep/caffe/VGG_ILSVRC_19_layers.caffemodel

tools/deinplace.py

@@ -33,7 +33,8 @@ def load_net(args):
 
 def deinplace(args, net):
     outputs = {}
-    for layer in net.layer:
+    layers = net.layer if net.layer else net.layers
+    for layer in layers:
         for idx, bottom in enumerate(layer.bottom):
             if bottom in outputs and bottom != outputs[bottom]:
                 if args.verbose: