ProGamerGov

#This script performs the linear color transfer step that 
#leongatys/NeuralImageSynthesis' Scale Control code performs.
#https://github.com/leongatys/NeuralImageSynthesis/blob/master/ExampleNotebooks/ScaleControl.ipynb
import scipy
import h5py
import skimage
import os
from skimage import io,transform,img_as_float
from skimage.io import imread,imsave
from collections import OrderedDict

ProGamerGov

require 'torch'
require 'nn'
require 'image'
require 'optim'

require 'loadcaffe'


local cmd = torch.CmdLine()

ProGamerGov

require 'torch'
require 'nn'
require 'image'
require 'optim'

require 'loadcaffe'


local cmd = torch.CmdLine()

ProGamerGov

import tensorflow as tf

# Creates a graph.
a = tf.constant([1.0, 2.0, 3.0, 4.0, 5.0, 6.0], shape=[2, 3], name='a')
b = tf.constant([1.0, 2.0, 3.0, 4.0, 5.0, 6.0], shape=[3, 2], name='b')
c = tf.matmul(a, b)
# Creates a session with log_device_placement set to True.
sess = tf.Session(config=tf.ConfigProto(log_device_placement=True))
# Runs the op.
print sess.run(c)

ProGamerGov

name: "VGG16_SOD_finetune"
layer {
  name: "data"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TRAIN
  }
  transform_param {

ProGamerGov

Datasts: 

https://github.com/ChristosChristofidis/awesome-deep-learning#datasets


Style Transfer Projects: 

https://github.com/jcjohnson/neural-style/wiki/Similar-to-Neural-Style

ProGamerGov

name: "Resnet_50_1by2"
force_backward: true
# Note - replace below layer with your data layer
layer {
  name: "data"
  type: "MemoryData"
  top: "data"
  top: "label"
  transform_param {
    crop_size: 224

ProGamerGov

`simon1.tar.gz` 586 images (only colored) | 184 MB
`simon2.tar.gz` 725 images (including uncolored sketches and photos of sketches) | 282 MB

None of the images have been resized or cropped yet. 
A txt file called "filelist.txt" lists every image's name, 
so all you need to do is add the category value and the paths 
for use in Caffe when making your train.txt and val.txt files. 

ProGamerGov

`simon1.tar.gz` 586 images (only colored) | 184 MB
`simon2.tar.gz` 725 images (including uncolored sketches and photos of sketches) | 282 MB

None of the images have been resized or cropped yet. A txt file called "filelist.txt" lists every image's name, so all you need to do is add the category and path for use in Caffe. 

ProGamerGov

$ ./build/tools/caffe time --model=models/NIN/train_val.prototxt






Check failed: status.ok() Failed to open leveldb cifar-train-leveldb
Invalid argument: cifar-train-leveldb: does not exist (create_if_missing is false)
*** Check failure stack trace: ***