1. Remove unused  arguments.
2. Refine doc.
3. Change 'device' to 'use_gpu'.

1. Remove illustration of arguments.
2. Make inference support for more format input.

1. Add document.
2. Add arguments for saving model and init model.
3. Refine inference.py and eval.py.
4. Make ctc_reader.py support for custom data.

1. Move all network defining to 'crnn_ctc_model.py'
2. Add initilizer for some layers
3. Rename 'fluid/ocr' to 'fluid/ocr_recognition'
4. Remove copyright
5. Rename some functions

1. Remove 'ocr_ctc' directory to 'ocr'.
2. Init README.md
3. Fix learning rate and l2
4. Refine training log format
5. Reduce arguments of train function
6. Set filter_size of im2sequence dynamicly
7. Add fc op before GRU op