oopsno

name: "pascal3DDatsetPose16Cat_Model3"
layer {
  name: "data"
  type: "DummyData"
  top: "data"
}
layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"

oopsno

from __future__ import print_function
from sys import argv, stderr

def load_test():
    import caffe
    caffe.Net(argv[-1], caffe.TEST)

def load_train():
    import caffe
    from sys import argv

oopsno

# VGG 16-layer network convolutional finetuning
# Network modified to have smaller receptive field (128 pixels)
# and smaller stride (8 pixels) when run in convolutional mode.
#
# In this model we also change max pooling size in the first 4 layers
# from 2 to 3 while retaining stride = 2
# which makes it easier to exactly align responses at different layers.
#
# For alignment to work, we set (we choose 32x so as to be able to evaluate
# the model for all different subsampling sizes):

oopsno

name: "Fisher Yu's Context Train Net @ PASCAL VOC 2012"
layer {
  name: "data"
  type: "BinLabelData"
  top: "data"
  top: "label"
  bin_label_data_param {
    bin_list_path: "PASCAL_VOC2012"
    label_list_path: "PASCAL_VOC2012"
    batch_size: 14

oopsno

name: "Fisher Yu's Context Train Net @ PASCAL VOC 2012"
layer {
  name: "data"
  type: "BinLabelData"
  top: "data"
  top: "label"
  bin_label_data_param {
    bin_list_path: "PASCAL_VOC2012"
    label_list_path: "PASCAL_VOC2012"
    batch_size: 14

oopsno

name: "Fisher Yu's Frontend Test Net @ PASCAL VOC 2012"
layer {
  name: "data"
  type: "ImageLabelData"
  top: "data"
  top: "label"
  transform_param {
    mirror: false
    crop_size: 500
    mean_value: 102.93

oopsno

name: "Fisher Yu's Frontend Train Net @ PASCAL VOC 2012"
layer {
  name: "data"
  type: "ImageLabelData"
  top: "data"
  top: "label"
  transform_param {
    mirror: true
    crop_size: 500
    mean_value: 102.93

oopsno

name: "PSPNet-ResNet50+B1236+AVE+DR"
input: "data"
input_dim: 1
input_dim: 3
input_dim: 473
input_dim: 473

layer {
  name: "conv1_1_3x3_s2"
  type: "Convolution"