What is ILSVRC2013

• Large Scale Visual Recognition Challenge 2014

How to get images from imageNet

Get wnid list

• You need to prepare csv file of wnid.
• I created the csv file by shaping LSVRC page.(http://image-net.org/challenges/LSVRC/2014/browse-synsets)
• Here is sample csv file (data/classification_categorys.csv).

Run get_image_from_imagenet.py

• This script to get the image from imagenet.
• Simply, this script get image url by wnid, and download image file.
• I have excluded the following file.
  • flicr not found image file
  • cannot open file
  • Too small file

  cd data
  python get_image_from_imagenet.py
  

  • download-API
    • wnids : http://image-net.org/challenges/LSVRC/2014/browse-synsets
    • image : http://imagenet.stanford.edu/api/text/imagenet.synset.geturls?wnid=[wnid]
    • word : http://www.image-net.org/api/text/wordnet.synset.getwords?wnid=[wnid]

• When I execute make_dataset.py, the error has occurred.
• I edited train_example_path of pylearn2/scripts/tutorials/grbm_smd/make_dataset.py.

IOError: permission error creating /Library/Python/2.7/site-packages/pylearn2/scripts/tutorials/grbm_smd/cifar10_preprocessed_train.pkl

• environment values

export PYLEARN2_DATA_PATH=/Users/karino-t/data
export PYLEARN2_VIEWER_COMMAND="open -Wn"

• (3, 224, 224)

• 1. 96 kernel, (11, 11) max-pooling
• 2. 256 kernel, (5,5,48) max-pooling
• 3. 384 kernel, (3,3,256) all connect with second layer
• 4. 384 kernel, (3,3,192)
• 5. 384 kernel, (3,3,192) max-pooling

• 6. 2048+2048 sigmoid?, tanh?, other?
• 7. 2048+2048
• 8. softmax 1000

• data augmentation
• dropout (full connected layer ?)